Graph-structured data plays a pivotal role in modeling complex relationships. However, real-world graphs are often incomplete due to data collection and observational constraints, severely limiting the effectiveness of modern graph learning pipelines. While existing Graph Data Augmentation (GDA) methods attempt to refine graph structures for improved downstream performance, they are typically label-dependent, computationally expensive, and inherently transductive, limiting their applicability in practical scenarios. In this work, we present a novel feature-centric graph data augmentation framework that bypasses explicit structure modeling by operating directly in the embedding space. Through a self-supervised inverse masking process, our method captures latent ties between observed and complete graphs, enabling recovery of unobserved structural signals through refined node representations. To enhance robustness under noisy and sparse supervision, we introduce a message regularizer and a bootstrap strategy for effective training and generalization. Evaluated on ten graph datasets spanning multiple domains, our approach, SelfAug, consistently outperforms state-of-the-art methods in both accuracy and efficiency across inductive and cold-start settings, highlighting its potential as a scalable and generalizable solution for real-world graph learning scenarios.

Yuping Lin, Zitao Li, Yue Xing, Pengfei He, Yingqian Cui, Yaliang Li, Bolin Ding, Jingren Zhou, Jiliang Tang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zidi Xiong, Yuping Lin, Wenya Xie, Pengfei He, Zirui Liu, Jiliang Tang, Himabindu Lakkaraju, Zhen Xiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Large Language Model (LLM) agents have become increasingly prevalent across various realworld applications.They enhance decisionmaking by storing private user-agent interactions in the memory module for demonstrations, introducing new privacy risks for LLM agents.In this work, we systematically investigate the vulnerability of LLM agents to our proposed Memory EXTRaction Attack (MEXTRA) under a black-box setting.To extract private information from memory, we propose an effective attacking prompt design and an automated prompt generation method based on different levels of knowledge about the LLM agent.Experiments on two representative agents demonstrate the effectiveness of MEXTRA.Moreover, we explore key factors influencing memory leakage from both the agent designer's and the attacker's perspectives.Our findings highlight the urgent need for effective memory safeguards in LLM agent design and deployment.

Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigations have been conducted to understand CoT, the underlying transformer used in these studies isolates the CoT reasoning process into separated in-context learning steps (Stepwise ICL). In this work, we theoretically show that, compared to Stepwise ICL, the transformer gains better error correction ability and more accurate predictions if the reasoning from earlier steps (Coherent CoT) is integrated. Given that this coherent reasoning changes the behavior of the transformer, we further investigate the sensitivity of the transformer with Coherent CoT when the demonstration examples are corrupted at the inference stage. Our theoretical results indicate that the transformer is more sensitive to errors in intermediate reasoning steps than the final outcome. Building upon this observation, we propose an improvement on CoT by incorporating both correct and incorrect reasoning paths in the demonstration. Our experiments validate the effectiveness of the proposed approach.

We present a theoretical analysis of the performance of transformer with softmax attention in in-context learning with linear regression tasks. While the existing theoretical literature predominantly focuses on providing convergence upper bounds to show that trained transformers with single-/multi-head attention can obtain a good in-context learning performance, our research centers on comparing the exact convergence of single- and multi-head attention more rigorously. We conduct an exact theoretical analysis to demonstrate that multi-head attention with a substantial embedding dimension performs better than single-head attention. When the number of in-context examples $D$ increases, the prediction loss using single-/multi-head attention is in $O(1/D)$, and the one for multi-head attention has a smaller multiplicative constant. In addition to the simplest data distribution setting, our technical framework in calculating the exact convergence further facilitates studying more scenarios, e.g., noisy labels, local examples, correlated features, and prior knowledge. We observe that, in general, multi-head attention is preferred over single-head attention. Our results verify the effectiveness of the design of multi-head attention in the transformer architecture.

Text-to-image (T2I) diffusion models have shown exceptional capabilities in generating images that closely correspond to textual prompts. However, the advancement of T2I diffusion models presents significant risks, as the models could be exploited for malicious purposes, such as generating images with violence or nudity, or creating unauthorized portraits of public figures in inappropriate contexts. To mitigate these risks, concept removal methods have been proposed. These methods aim to modify diffusion models to prevent the generation of malicious and unwanted concepts. Despite these efforts, existing research faces several challenges: (1) a lack of consistent comparisons on a comprehensive dataset, (2) ineffective prompts in harmful and nudity concepts, (3) overlooked evaluation of the ability to generate the benign part within prompts containing malicious concepts. To address these gaps, we propose to benchmark the concept removal methods by introducing a new dataset, Six-CD, along with a novel evaluation metric. In this benchmark, we conduct a thorough evaluation of concept removals, with the experimental observations and discussions offering valuable insights in the field.

In recent years, large language models (LLMs) have revolutionized the field of natural language processing.However, they often suffer from knowledge gaps and hallucinations.Graph retrieval-augmented generation (GraphRAG) enhances LLM reasoning by integrating structured knowledge from external graphs.However, we identify two key challenges that plague GraphRAG: (1) Retrieving noisy and irrelevant information can degrade performance and (2) Excessive reliance on external knowledge suppresses the model's intrinsic reasoning.To address these issues, we propose GraphRAG-FI (Filtering & Integration), consisting of GraphRAG-Filtering and GraphRAG-Integration. GraphRAG-Filtering employs a two-stage filtering mechanism to refine retrieved information.GraphRAG-Integration employs a logits-based selection strategy to balance external knowledge from GraphRAG with the LLM's intrinsic reasoning, reducing over-reliance on retrievals.Experiments on knowledge graph QA tasks demonstrate that GraphRAG-FI significantly improves reasoning performance across multiple backbone models, establishing a more reliable and effective GraphRAG framework.

Shenglai Zeng, Jiankun Zhang, Pengfei He, Jie Ren, Tianqi Zheng, Hanqing Lu, Han Xu, Hui Liu, Yue Xing, Jiliang Tang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Recent years have witnessed significant advancements in graph machine learning (GML), with its applications spanning numerous domains. However, the focus of GML has predominantly been on developing powerful models, often overlooking a crucial initial step: constructing suitable graphs from common data formats, such as tabular data. This construction process is fundamental to applying graph-based models, yet it remains largely understudied and lacks formalization. Our research aims to address this gap by formalizing the graph construction problem and proposing an effective solution. We identify two critical challenges to achieve this goal: 1. The absence of dedicated datasets to formalize and evaluate the effectiveness of graph construction methods, and 2. Existing automatic construction methods can only be applied to some specific cases, while tedious human engineering is required to generate high-quality graphs. To tackle these challenges, we present a two-fold contribution. First, we introduce a set of datasets to formalize and evaluate graph construction methods. Second, we propose an LLM-based solution, AutoG, automatically generating high-quality graph schemas without human intervention. The experimental results demonstrate that the quality of constructed graphs is critical to downstream task performance, and AutoG can generate high-quality graphs that rival those produced by human experts. Our code can be accessible from https://github.com/amazon-science/Automatic-Table-to-Graph-Generation.

Benchmarking the capabilities and limitations of large language models (LLMs) in graph-related tasks is becoming an increasingly popular and crucial area of research. Recent studies have shown that LLMs exhibit a preliminary ability to understand graph structures and node features. However, the potential of LLMs in graph pattern mining remains largely unexplored. This is a key component in fields such as computational chemistry, biology, and social network analysis. To bridge this gap, this work introduces a comprehensive benchmark to assess LLMs' capabilities in graph pattern tasks. We have developed a benchmark that evaluates whether LLMs can understand graph patterns based on either terminological or topological descriptions. Additionally, our benchmark tests the LLMs' capacity to autonomously discover graph patterns from data. The benchmark encompasses both synthetic and real datasets, and a variety of models, with a total of 11 tasks and 7 models. Our experimental framework is designed for easy expansion to accommodate new models and datasets. Our findings reveal that: (1) LLMs have preliminary abilities to understand graph patterns, with O1-mini outperforming in the majority of tasks; (2) Formatting input graph data to align with the knowledge acquired during pretraining can enhance performance; (3) LLMs employ diverse potential algorithms to solve one task, with performance varying based on their execution capabilities.

Large Language Models (LLMs) are revolutionizing E-Commerce by enabling product recommendation, search, classification, question answering, and advertising applications. Their increasing adoption in real-world systems underscores their potential; however, challenges persist in ensuring accuracy, efficiency, fairness, and privacy. This workshop aims to bring together researchers and industry practitioners to explore both the limitations and opportunities of LLMs in e-commerce. The workshop seeks to foster collaboration, bridge the gap between academia and industry, and drive innovation in the application of LLMs to E-Commerce through discussions on model design, algorithmic advancements, and practical deployment.

Graphs, which encode pairwise relations between entities, serve as a fundamental data structure across real-world domains. Many critical applications can be formulated as graph-based tasks, and graph machine learning (GML), from the shallow embedding models to graph neural networks and further advanced to the most powerful graph transformers, has been well-established to automate knowledge discovery and decision-making on graphs. In parallel, the recent emergence of large foundational models has driven machine learning into a new era of Generative Artificial Intelligence (Gen-AI), and this revolution presents both unprecedented opportunities and profound challenges for the well-established GML paradigms. However, few investigations have analyzed and envisioned how GML should evolve to harness these opportunities, address these challenges, and embrace this new Gen-AI era. To fill in this gap, we organize the first international Workshop on Machine Learning on Graphs in the Era of Generative Artificial Intelligence (MLoG-GenAI), held in connection with the 31st ACM Conference on Knowledge Discovery and Data Mining, which provides a venue to gather academic researchers and industry practitioners to discuss and picture the development of GML in the new Gen-AI era.

A fundamental challenge in understanding graph neural networks (GNNs) lies in characterizing their optimization dynamics and loss landscape geometry, critical for improving interpretability and robustness. While mode connectivity-a lens for analyzing geometric properties of loss landscapes-has proven insightful for other deep learning architectures, its implications for GNNs remain unexplored. This work presents the first investigation of mode connectivity in GNNs. We uncover that GNNs exhibit distinct non-linear mode connectivity, diverging from patterns observed in fully-connected networks or CNNs. Crucially, we demonstrate that graph structure, rather than model architecture, dominates this behavior, with graph properties like homophily correlating with mode connectivity patterns. We further establish a link between mode connectivity and generalization, proposing a generalization bound based on loss barriers and revealing its utility as a diagnostic tool. Our findings further bridge theoretical insights with practical implications: they rationalize domain alignment strategies in graph learning and provide a foundation for refining GNN training paradigms.

State-of-the-art link prediction (LP) models demonstrate impressive benchmark results. However, popular benchmark datasets often assume that training, validation, and testing samples are represen- tative of the overall dataset distribution. In real-world situations, this assumption is often incorrect; uncontrolled factors lead new dataset samples to come from a different distribution than train- ing samples. Additionally, the majority of recent work with graph dataset shift focuses on node- and graph-level tasks, largely ignor- ing link-level tasks. To bridge this gap, we introduce a novel splitting strategy, known as LPShift, which utilizes structural properties to induce a controlled distribution shift. We verify LPShift's effect through empirical evaluation of SOTA LP models on 16 LPShift variants of original dataset splits, with results indicating drastic changes to model performance. Additional experiments demon- strate graph structure has a strong influence on the success of current generalization methods. The source code is available here https://github.com/revolins/LPShift.

Knowledge Graph Completion (KGC) attempts to predict missing facts in a Knowledge Graph (KG). Recently, there's been an increased focus on designing KGC methods that can excel in the inductive setting, where a portion or all of the entities and relations seen in inference are unobserved during training. Numerous benchmark datasets have been proposed for inductive KGC, all of which are subsets of existing KGs used for transductive KGC. However, we find that the current procedure for constructing inductive KGC datasets inadvertently creates a shortcut that can be exploited even while disregarding the relational information. Specifically, we observe that the Personalized PageRank (PPR) score can achieve strong or near SOTA performance on most datasets. In this paper, we study the root cause of this problem. Using these insights, we propose an alternative strategy for constructing inductive KGC datasets that helps mitigate the PPR shortcut. We then benchmark multiple popular methods using the newly constructed datasets and analyze their performance. The new benchmark datasets help promote a better understanding of the capabilities and challenges of inductive KGC by removing any shortcuts that obfuscate performance. The code and dataset and can be found https://github.com/HarryShomer/Better-Inductive-KGC.

Large language models (LLMs) based on Transformer architecture are powerful but face challenges with deployment, inference latency, and costly fine-tuning. These limitations highlight the emerging potential of small language models (SLMs), which can either replace LLMs through innovative architectures and technologies, or assist them as efficient proxy or reward models. Emerging architectures such as Mamba and xLSTM address the quadratic scaling of inference with window length in Transformers by enabling linear scaling. To maximize SLM performance, test-time compute scaling strategies reduce the performance gap with LLMs by allocating extra compute budget during test time. Beyond standalone usage, SLMs could also assist in LLMs via weak-to-strong learning, proxy tuning, and guarding, fostering secure and efficient LLM deployment. Lastly, the trustworthiness of SLMs remains a critical yet underexplored research area. However, there is a lack of tutorials on cutting-edge SLM technologies, prompting us to conduct one.

Shenglai Zeng, Jiankun Zhang, Bingheng Li, Yuping Lin, Tianqi Zheng, Dante Everaert, Hanqing Lu, Hui Liu, Hui Liu, Yue Xing, Monica Xiao Cheng, Jiliang Tang. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Recent studies suggest that large language models (LLMs) possess the capability to solve graph reasoning tasks. Notably, even when graph structures are embedded within textual descriptions, LLMs can still effectively answer related questions. This raises a fundamental question: How can a decoder-only Transformer architecture understand underlying graph structures? To address this, we start with the substructure extraction task, interpreting the inner mechanisms inside the transformers and analyzing the impact of the input queries. Specifically, through both empirical results and theoretical analysis, we present Induced Substructure Filtration (ISF), a perspective that captures the substructure identification in the multi-layer transformers. We further validate the ISF process in LLMs, revealing consistent internal dynamics across layers. Building on these insights, we explore the broader capabilities of Transformers in handling diverse graph types. Specifically, we introduce the concept of thinking in substructures to efficiently extract complex composite patterns, and demonstrate that decoder-only Transformers can successfully extract substructures from attributed graphs, such as molecular graphs. Together, our findings offer a new insight on how sequence-based Transformers perform the substructure extraction task over graph data.

Foundation models (FMs) have shown great promise in single-cell genomics, yet current approaches, such as scGPT, Geneformer, and scFoundation, rely on centralized training and language modeling objectives that overlook the tabular nature of single-cell data and raise significant privacy concerns. We present TABULA, a foundation model designed for single-cell transcriptomics, which integrates a novel tabular modeling objective and federated learning framework to enable privacy-preserving pretraining across decentralized datasets. TABULA directly models the cell-by-gene expression matrix through column-wise gene reconstruction and row-wise cell contrastive learning, capturing both gene-level relationships and cell-level heterogeneity without imposing artificial gene sequence order. Extensive experiments demonstrate the effectiveness of TABULA: despite using only half the pretraining data, TABULA achieves state-of-the-art performance across key tasks, including gene imputation, perturbation prediction, cell type annotation, and multi-omics integration. It is important to note that as public single-cell datasets continue to grow, TABULA provides a scalable and privacy-aware foundation that not only validates the feasibility of federated tabular modeling but also establishes a generalizable framework for training future models under similar privacy-preserving settings.

Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised memory bank may easily produce harmful outputs when the past records retrieved for demonstration are malicious. In this paper, we propose a novel Memory INJection Attack, MINJA, without assuming that the attacker can directly modify the memory bank of the agent. The attacker injects malicious records into the memory bank by only **interacting with the agent via queries and output observations**. These malicious records are designed to elicit a sequence of malicious reasoning steps corresponding to a different target query during the agent's execution of the victim user's query. Specifically, we introduce a sequence of *bridging steps* to link victim queries to the malicious reasoning steps. During the memory injection, we propose an *indication prompt* that guides the agent to autonomously generate similar bridging steps, with a *progressive shortening strategy* that gradually removes the indication prompt, such that the malicious record will be easily retrieved when processing later victim queries. Our extensive experiments across diverse agents demonstrate the effectiveness of MINJA in compromising agent memory. With minimal requirements for execution, MINJA enables any user to influence agent memory, highlighting the risk.

Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle to scale up data due to heterogeneity across graphs. To achieve effective data scaling, we aim to develop a general model that is able to capture diverse data patterns of graphs and can be utilized to adaptively help the downstream tasks. To this end, we propose UniAug, a universal graph structure augmentor built on a diffusion model. We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns. In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model via guided generation. By leveraging the pre-trained diffusion model for structure augmentation, we consistently achieve performance improvements across various downstream tasks in a plug-and-play manner. To the best of our knowledge, this study represents the first demonstration of a data-scaling graph structure augmentor on graphs across domains.

Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases remains an open challenge due to task heterogeneity. Specifically, there exist many possible downstream tasks, as tasks are defined based on relational schema graphs, temporal dependencies, and SQL-defined label logics. An effective pre-training framework is desired to take these factors into account in order to obtain task-aware representations. By incorporating knowledge of the underlying distribution that drives label generation, downstream tasks can benefit from relevant side-channel information. To bridge this gap, we introduce Task Vector Estimation (TVE), a novel pre-training framework that constructs predictive supervisory signals via set-based aggregation over schema traversal graphs, explicitly modeling next-window relational dynamics. We formalize our approach through an information-theoretic lens, demonstrating that task-informed representations retain more relevant signals than those obtained without task priors. Extensive experiments on the RelBench benchmark show that TVE consistently outperforms traditional pre-training baselines. Our findings advocate for pre-training objectives that encode task heterogeneity and temporal structure as design principles for predictive modeling on relational databases. Our code is publicly available at https://github.com/quang-truong/task-vector-estimation.

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their success. However, concerns have been raised about the unauthorized use of copyrighted materials and potential copyright infringement. Existing methods, such as sample-level Membership Inference Attacks (MIA) and distribution-based dataset, inference distinguish member and non-member data by leveraging the common observation that models tend to memorize and show greater confidence in member data. Nevertheless, these methods face challenges when applied to LLMs and VLMs, such as the requirement for ground-truth member data or non-member data that shares the same distribution as the test data. In this paper, we propose a novel dataset-level membership inference method based on Self-Comparison. We find that a member prefix followed by a non-member suffix (paraphrased from a member suffix) can further trigger the model's memorization on training data. Instead of directly comparing member and non-member data, we introduce paraphrasing to the second half of the sequence and evaluate how the likelihood changes before and after paraphrasing. Unlike prior approaches, our method does not require access to ground-truth member data or non-member data in identical distribution, making it more practical. Extensive experiments demonstrate that our proposed method outperforms traditional MIA and dataset inference techniques across various datasets and models, including GPT-4o.

Knowledge tracing (KT) involves utilizing historical data from students’ learning interactions to model their mastery of knowledge over time, with the aim of predicting their future performance in interactions. Recently, significant advancements have been achieved through the application of various deep learning methodologies to address the KT challenge. However, a considerable proportion of deep learning-based knowledge tracing (DLKT) approaches exhibit striking similarities in their methodologies, and model designs, and even the outcomes demonstrate minimal divergence. In addition, the evaluation procedures employed in current DLKT studies are not standardized, resulting in substantial inconsistencies in the reported area under the curve (AUC) outcomes, despite analyzing the same model on identical datasets. To address the two aforementioned problems, this paper proposes a generalized DLKT framework and represents the existing DLKT models with five components, i.e., multimodal data encoder, student knowledge memory, auxiliary knowledge base, learning outcome objective, and computational efficiency and scalability. Furthermore, we develop and open source a standardized DLKT benchmark platform namedpyKT,1that consists of a standardized set of integrated data preprocessing procedures on 9 popular datasets across different domains, and 21 frequently compared DLKT model implementations. WithpyKT, we conduct empirical and reproducible research to assess the performance of prevalent DLKT algorithms in an unbiased and clear setting over multiple data sources. Finally, we discuss the applications of KT techniques in the educational sector and their future development directions.

Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu, Han Xu, Pengfei He, Yue Xing, Shuaiqiang Wang, Jiliang Tang, Dawei Yin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Online shopping platforms, such as Amazon, offer services to billions of people worldwide. Unlike web search or other search engines, product search engines have their unique characteristics, primarily featuring short queries which are mostly a combination of product attributes and structured product search space. The uniqueness of product search underscores the crucial importance of the query understanding component. However, there are limited studies focusing on exploring this impact within real-world product search engines. In this work, we aim to bridge this gap by conducting a comprehensive study and sharing our year-long journey investigating how the query understanding service impacts Amazon Product Search. Firstly, we explore how query understanding-based ranking features influence the ranking process. Next, we delve into how the query understanding system contributes to understanding the performance of a ranking model. Building on the insights gained from our study on the evaluation of the query understanding-based ranking model, we propose a query understanding-based multi-task learning framework for ranking. We present our studies and investigations on Amazon Search.

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents.Although there are diverse jailbreak attack strategies, there is no unified understanding on why some methods succeed and others fail.This paper explores the behavior of harmful and harmless prompts in the LLM's representation space to investigate the intrinsic properties of successful jailbreak attacks.We hypothesize that successful attacks share some similar properties: They are effective in moving the representation of the harmful prompt towards the direction to the harmless prompts.We leverage hidden representations into the objective of existing jailbreak attacks to move the attacks along the acceptance direction, and conduct experiments to validate the above hypothesis using the proposed objective.We hope this study provides new insights into understanding how LLMs understand harmfulness information.1 * These authors contributed equally to this work.1 Our code is available at https://github.com/ yuplin2333/representation-space-jailbreak.

Large Language Models (LLMs) are capable of producing content that perpetuates stereotypes, discrimination, and toxicity.The recently proposed moral self-correction is a computationally efficient method for reducing harmful content in the responses of LLMs.However, the process of how injecting self-correction instructions can modify the behavior of LLMs remains under-explored.In this paper, we explore the effectiveness of moral self-correction by answering three research questions: (1) In what scenarios does moral self-correction work?( 2) What are the internal mechanisms of LLMs, e.g., hidden states, that are influenced by moral selfcorrection instructions?(3) Is intrinsic moral self-correction actually superficial in terms of reduced immorality in hidden states?We argue that self-correction can help LLMs find a shortcut to more morally correct output, rather than truly reducing the immorality stored in hidden states.Through empirical investigation with tasks of language generation and multi-choice question answering, we conclude: (i) LLMs exhibit good performance across both tasks, and self-correction instructions are particularly beneficial when the correct answer is already top-ranked; (ii) The morality levels in intermediate hidden states are strong indicators as to whether one instruction would be more effective than another; (iii) Based on our analysis of intermediate hidden states and task case studies of self-correction behaviors, we are first to propose the hypothesis that intrinsic moral self-correction is in fact superficial.

In recent years, there have been remarkable advancements in node classification achieved by Graph Neural Networks (GNNs). However, they necessitate abundant high-quality labels to ensure promising performance. In contrast, Large Language Models (LLMs) exhibit impressive zero-shot proficiency on text-attributed graphs. Yet, they face challenges in efficiently processing structural data and suffer from high inference costs. In light of these observations, this work introduces a label-free node classification on graphs with LLMs pipeline, LLM-GNN. It amalgamates the strengths of both GNNs and LLMs while mitigating their limitations. Specifically, LLMs are leveraged to annotate a small portion of nodes and then GNNs are trained on LLMs' annotations to make predictions for the remaining large portion of nodes. The implementation of LLM-GNN faces a unique challenge: how can we actively select nodes for LLMs to annotate and consequently enhance the GNN training? How can we leverage LLMs to obtain annotations of high quality, representativeness, and diversity, thereby enhancing GNN performance with less cost? To tackle this challenge, we develop an annotation quality heuristic and leverage the confidence scores derived from LLMs to advanced node selection. Comprehensive experimental results validate the effectiveness of LLM-GNN. In particular, LLM-GNN can achieve an accuracy of 74.9\% on a vast-scale dataset \products with a cost less than 1 dollar.

Graph Neural Networks (GNNs) have seen significant achievements in semi-supervised node classification. Yet, their efficacy often hinges on access to high-quality labeled node samples, which may not always be available in real-world scenarios. While active learning is commonly employed across various domains to pinpoint and label high-quality samples based on data features, graph data present unique challenges due to their intrinsic structures that render nodes non-i.i.d. Furthermore, biases emerge from the positioning of labeled nodes; for instance, nodes closer to the labeled counterparts often yield better performance. To better leverage graph structure and mitigate structural bias in active learning, we present a unified optimization framework (SCARCE), which is also easily incorporated with node features. Extensive experiments demonstrate that the proposed method not only improves the GNNs performance but also paves the way for more fair results.

Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference failures. While previous studies have executed different types of attacks, one major challenge that greatly limits their effectiveness is the uncertainty of the re-training process after the injection of poisoning samples. It includes the uncertainty of training initialization, algorithm and model architecture. To address this challenge, we propose a new strategy called **Sharpness-Aware Data Poisoning Attack (SAPA)**. In particular, it leverages the concept of DNNs' loss landscape sharpness to optimize the poisoning effect on the (approximately) worst re-trained model. Extensive experiments demonstrate that SAPA offers a general and principled strategy that significantly enhances various types of poisoning attacks against various types of re-training uncertainty.

Link prediction, a fundamental task on graphs, has proven indispensable in various applications, e.g., friend recommendation, protein analysis, and drug interaction prediction. However, since datasets span a multitude of domains, they could have distinct underlying mechanisms of link formation. Evidence in existing literature underscores the absence of a universally best algorithm suitable for all datasets. In this paper, we endeavor to explore principles of link prediction across diverse datasets from a data-centric perspective. We recognize three fundamental factors critical to link prediction: local structural proximity, global structural proximity, and feature proximity. We then unearth relationships among those factors where (i) global structural proximity only shows effectiveness when local structural proximity is deficient. (ii) The incompatibility can be found between feature and structural proximity. Such incompatibility leads to GNNs for Link Prediction (GNN4LP) consistently underperforming on edges where the feature proximity factor dominates. Inspired by these new insights from a data perspective, we offer practical instruction for GNN4LP model design and guidelines for selecting appropriate benchmark datasets for more comprehensive evaluations.

The current state-of-the-art single-cell pre-trained models are greatly inspired by the success of large language models. They trained transformers by treating genes as tokens and cells as sentences. However, three fundamental differences between single-cell data and natural language data are overlooked: (1) scRNA-seq data are presented as bag-of-genes instead of sequences of RNAs; (2) Cell-cell relations are more intricate and important than inter-sentence relations; and (3) The quantity of single-cell data is considerably inferior to text data, and they are very noisy. In light of these characteristics, we propose a new pre-trained model, $\textit{CellPLM}$, which takes cells as tokens and tissues as sentences. In addition, we leverage spatially-resolved transcriptomic data in pre-training to facilitate learning cell-cell relationships and introduce a Gaussian prior distribution as an additional inductive bias to overcome data limitations. $\textit{CellPLM}$ is the first single-cell pre-trained transformer that encodes cell-cell relations and it consistently outperforms existing pre-trained and non-pre-trained models in diverse downstream tasks, with 100 times higher inference speed on generating cell embeddings than previous pre-trained models.

Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and capability (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones, suggesting that open-source models can achieve high levels of trustworthiness without additional mechanisms like moderator, offering valuable insights for developers in this field. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Besides these observations, we’ve uncovered key insights into the multifaceted trustworthiness in LLMs. We emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. We advocate that the establishment of an AI alliance between industry, academia, the open-source community to foster collaboration is imperative to advance the trustworthiness of LLMs.

How would randomly shuffling feature vectors among nodes from the same class affect graph neural networks (GNNs)? The feature shuffle, intuitively, perturbs the dependence between graph topology and features (A-X dependence) for GNNs to learn from. Surprisingly, we observe a consistent and significant improvement in GNN performance following the feature shuffle. Having overlooked the impact of A-X dependence on GNNs, the prior literature does not provide a satisfactory understanding of the phenomenon. Thus, we raise two research questions. First, how should A-X dependence be measured, while controlling for potential confounds? Second, how does A-X dependence affect GNNs? In response, we (i) propose a principled measure for A-X dependence, (ii) design a random graph model that controls A-X dependence, (iii) establish a theory on how A-X dependence relates to graph convolution, and (iv) present empirical analysis on real-world graphs that align with the theory. We conclude that A-X dependence mediates the effect of graph convolution, such that smaller dependence improves GNN-based node classification.

Solving large-scale linear programming (LP) problems is an important task in various areas such as communication networks, power systems, finance and logistics. Recently, two distinct approaches have emerged to expedite LP solving: (i) First-order methods (FOMs); (ii) Learning to optimize (L2O). In this work, we propose an FOM-unrolled neural network (NN) called PDHG-Net, and propose a two-stage L2O method to solve large-scale LP problems. The new architecture PDHG-Net is designed by unrolling the recently emerged PDHG method into a neural network, combined with channel-expansion techniques borrowed from graph neural networks. We prove that the proposed PDHG-Net can recover PDHG algorithm, thus can approximate optimal solutions of LP instances with a polynomial number of neurons. We propose a two-stage inference approach: first use PDHG-Net to generate an approximate solution, and then apply PDHG algorithm to further improve the solution. Experiments show that our approach can significantly accelerate LP solving, achieving up to a 3$\times$ speedup compared to FOMs for large-scale LP problems.

Graph Foundation Models (GFMs) are emerging as a significant research topic in the graph domain, aiming to develop graph models trained on extensive and diverse data to enhance their applicability across various tasks and domains. Developing GFMs presents unique challenges over traditional Graph Neural Networks (GNNs), which are typically trained from scratch for specific tasks on particular datasets. The primary challenge in constructing GFMs lies in effectively leveraging vast and diverse graph data to achieve positive transfer. Drawing inspiration from existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a "graph vocabulary'', in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, expressiveness, and stability. Such a vocabulary perspective can potentially advance the future GFM design in line with the neural scaling laws. All relevant resources with GFM design can be found here.

Graph neural networks (GNNs) have exhibited remarkable performance under the assumption that test data comes from the same distribution of training data. However, in real-world scenarios, this assumption may not always be valid. Consequently, there is a growing focus on exploring the Out-of-Distribution (OOD) problem in the context of graphs. Most existing efforts have primarily concentrated on improving graph OOD generalization from two model-agnostic perspectives: data-driven methods and strategy-based learning. However, there has been limited attention dedicated to investigating the impact of well-known GNN model architectures on graph OOD generalization, which is orthogonal to existing research. In this work, we provide the first comprehensive investigation of OOD generalization on graphs from an architecture perspective, by examining the common building blocks of modern GNNs. Through extensive experiments, we reveal that both the graph self-attention mechanism and the decoupled architecture contribute positively to graph OOD generalization. In contrast, we observe that the linear classification layer tends to compromise graph OOD generalization capability. Furthermore, we provide in-depth theoretical insights and discussions to underpin these discoveries. These insights have empowered us to develop a novel GNN backbone model, DGat, designed to harness the robust properties of both graph self-attention mechanism and the decoupled architecture. Extensive experimental results demonstrate the effectiveness of our model under graph OOD, exhibiting substantial and consistent enhancements across various training strategies. Our codes are available at https://github.com/KaiGuo20/DGAT **REMOVE 2nd URL**://github.com/KaiGuo20/DGAT.

Link prediction is a common task on graph-structured data that has seen applications in a variety of domains. Classically, hand-crafted heuristics were used for this task. Heuristic measures are chosen such that they correlate well with the underlying factors related to link formation. In recent years, a new class of methods has emerged that combines the advantages of message-passing neural networks (MPNN) and heuristics methods. These methods perform predictions by using the output of an MPNN in conjunction with a "pairwise encoding" that captures the relationship between nodes in the candidate link. They have been shown to achieve strong performance on numerous datasets. However, current pairwise encodings often contain a strong inductive bias, using the same underlying factors to classify all links. This limits the ability of existing methods to learn how to properly classify a variety of different links that may form from different factors. To address this limitation, we propose a new method, LPFormer, which attempts to adaptively learn the pairwise encodings for each link. LPFormer models the link factors via an attention module that learns the pairwise encoding that exists between nodes by modeling multiple factors integral to link prediction. Extensive experiments demonstrate that LPFormer can achieve SOTA performance on numerous datasets while maintaining efficiency. The code is available at The code is available at https://github.com/HarryShomer/LPFormer.

Recent advanced AI technologies, especially large language models (LLMs) like GPTs, have significantly advanced the field of data mining and led to the development of various LLM-based applications. AI for education (AI4EDU) is a vibrant multi-disciplinary field of data mining, machine learning, and education, with increasing importance and extraordinary potential. In this field, LLM and adaptive learning-based models can be utilized as interfaces in human-in-the-loop education systems, where the model serves as a mediator among the teacher, students, and machine capabilities, including its own. This perspective has several benefits, including the ability to personalize interactions, allow unprecedented flexibility and adaptivity for human-AI collaboration and improve the user experience. However, several challenges still exist, including the need for more robust and efficient algorithms, designing effective user interfaces, and ensuring ethical considerations are addressed. This workshop aims to bring together researchers and practitioners from academia and industry to explore cutting-edge AI technologies for personalized education, especially the potential of LLMs and adaptive learning technologies.

Cellular networks provide the most accessible emergency services with ubiquitous coverage, yet their emergency-specific designs remain largely unexplored. To systematically explore potential design defects that lead to failures or delays in emergency services, we introduce M911-Verifier, an emergency-specific model checking tool. It reveals many counterintuitive findings regarding the ubiquitous access support for cellular emergency services. Our study shows that, despite sufficient wireless signal coverage, users may still experience prolonged emergency call setup times, call initiation failures, or call drops due to flaws in the design of cellular emergency services. These design defects arise from three major causes: problematic network selection for initiating emergency calls, emergency-unaware call operation, and network escalation forbidden during emergency calls. The impacts of these defects have been experimentally validated across three U.S. carriers and two Taiwan carriers using commodity smartphones. Finally, we propose solutions and evaluate their effectiveness.

Low Power Wide-Area Network (LPWAN) has shown its long-distance and low-power features for aboveground Internet-of-Things (IoT) communication, presenting a potential to extend to underground cross-soil communication over a wide area, which has not been investigated before. The variation of soil conditions brings significant signal polarization misalignment, degrading communication reliability. We propose Demeter, a low-cost, low-power programmable antenna design to keep reliable cross-soil communication automatically. First, we propose a hardware architecture to enable polarization adjustment on commercial-off-the-shelf (COTS) single-RF-chain LoRa radio. Moreover, we develop a low-power programmable circuit to adjust polarization. We further design an energy-efficient heuristic calibration algorithm to keep signal polarization alignment automatically. We demonstrate Demeter in indoor environments. The antenna is buried in a plastic container filled with gardening soil to simulate the node underground. Meanwhile, we use the COTS LoRa gateway as a receiver to show the RSSI and SNR variations.

Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models that only apply the same pairwise information uniformly could achieve suboptimal performance. As a result, we propose a simple mixture of experts model Link-MoE for link prediction. Link-MoE utilizes various GNNs as experts and strategically selects the appropriate expert for each node pair based on various types of pairwise information. Experimental results across diverse real-world datasets demonstrate substantial performance improvement from Link-MoE. Notably, Link-Mo achieves a relative improvement of 18.71% on the MRR metric for the Pubmed dataset and 9.59% on the Hits@100 metric for the ogbl-ppa dataset, compared to the best baselines. The code is available at https://github.com/ml-ml/Link-MoE/.

Given the ubiquity of graph data and its applications in diverse domains, building a Graph Foundation Model (GFM) that can work well across different graphs and tasks with a unified backbone has recently garnered significant interests. A major obstacle to achieving this goal stems from the fact that graphs from different domains often exhibit diverse node features. Inspired by multi-modal models that align different modalities with natural language, the text has recently been adopted to provide a unified feature space for diverse graphs. Despite the great potential of these text-space GFMs, current research in this field is hampered by two problems. First, the absence of a comprehensive benchmark with unified problem settings hinders a clear understanding of the comparative effectiveness and practical value of different text-space GFMs. Second, there is a lack of sufficient datasets to thoroughly explore the methods' full potential and verify their effectiveness across diverse settings. To address these issues, we conduct a comprehensive benchmark providing novel text-space datasets and comprehensive evaluation under unified problem settings. Empirical results provide new insights and inspire future research directions. Our code and data are publicly available from https://github.com/CurryTang/TSGFM.

The page presentation biases in the information retrieval system, especially on the click behavior, is a well-known challenge that hinders improving ranking models' performance with implicit user feedback. Unbiased Learning to Rank~(ULTR) algorithms are then proposed to learn an unbiased ranking model with biased click data. However, most existing algorithms are specifically designed to mitigate position-related bias, e.g., trust bias, without considering biases induced by other features in search result page presentation(SERP), e.g. attractive bias induced by the multimedia. Unfortunately, those biases widely exist in industrial systems and may lead to an unsatisfactory search experience. Therefore, we introduce a new problem, i.e., whole-page Unbiased Learning to Rank(WP-ULTR), aiming to handle biases induced by whole-page SERP features simultaneously. It presents tremendous challenges: (1) a suitable user behavior model (user behavior hypothesis) can be hard to find; and (2) complex biases cannot be handled by existing algorithms. To address the above challenges, we propose a Bias Agnostic whole-page unbiased Learning to rank algorithm, named BAL, to automatically find the user behavior model with causal discovery and mitigate the biases induced by multiple SERP features with no specific design. Experimental results on a real-world dataset verify the effectiveness of the BAL.

Masked graph autoencoders have emerged as a powerful graph self-supervised learning method that has yet to be fully explored. In this paper, we unveil that the existing discrete edge masking and binary link reconstruction strategies are insufficient to learn topologically informative representations, from the perspective of message propagation on graph neural networks. These limitations include blocking message flows, vulnerability to over-smoothness, and suboptimal neighborhood discriminability. Inspired by these understandings, we explore non-discrete edge masks, which are sampled from a continuous and dispersive probability distribution instead of the discrete Bernoulli distribution. These masks restrict the amount of output messages for each edge, referred to as "bandwidths". We propose a novel, informative, and effective topological masked graph autoencoder using bandwidth masking and a layer-wise bandwidth prediction objective. We demonstrate its powerful graph topological learning ability both theoretically and empirically. Our proposed framework outperforms representative baselines in both self-supervised link prediction (improving the discrete edge reconstructors by at most 20%) and node classification on numerous datasets, solely with a structure-learning pretext. Our implementation is available at https://github.com/Newiz430/Bandana.

Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the single-cell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations.

Molecule discovery plays a crucial role in various scientific fields, advancing the design of tailored materials and drugs, which contributes to the development of society and human well-being. Specifically, molecule-caption translation is an important task for molecule discovery, aligning human understanding with molecular space. However, most of the existing methods heavily rely on domain experts, require excessive computational cost, or suffer from sub-optimal performance. On the other hand, Large Language Models (LLMs), like ChatGPT, have shown remarkable performance in various cross-modal tasks due to their powerful capabilities in natural language understanding, generalization, and in-context learning (ICL), which provides unprecedented opportunities to advance molecule discovery. Despite several previous works trying to apply LLMs in this task, the lack of domain-specific corpus and difficulties in training specialized LLMs still remain challenges. In this work, we propose a novel LLM-based framework (MolReGPT) for molecule-caption translation, where an In-Context Few-Shot Molecule Learning paradigm is introduced to empower molecule discovery with LLMs like ChatGPT to perform their in-context learning capability without domain-specific pre-training and fine-tuning. MolReGPT leverages the principle of molecular similarity to retrieve similar molecules and their text descriptions from a local database to enable LLMs to learn the task knowledge from context examples. We evaluate the effectiveness of MolReGPT on molecule-caption translation, including molecule understanding and text-based molecule generation. Experimental results show that compared to fine-tuned models, MolReGPT outperforms MolT5-base and is comparable to MolT5-large without additional training. To the best of our knowledge, MolReGPT is the first work to leverage LLMs via in-context learning in molecule-caption translation for advancing molecule discovery. Our work expands the scope of LLM applications, as well as providing a new paradigm for molecule discovery and design.

With the prosperity of e-commerce and web applications, Recommender Systems (RecSys) have become an indispensable and important component in our daily lives, providing personalized suggestions that cater to user preferences. While Deep Neural Networks (DNNs) have achieved significant advancements in enhancing recommender systems by modeling user-item interactions and incorporating their textual side information, these DNN-based methods still exhibit some limitations, such as difficulties in effectively understanding users' interests and capturing textual side information, inabilities in generalizing to various seen/unseen recommendation scenarios and reasoning on their predictions, etc. Meanwhile, the development of Large Language Models (LLMs), such as ChatGPT and GPT-4, has revolutionized the fields of Natural Language Processing (NLP) and Artificial Intelligence (AI), due to their remarkable abilities in fundamental responsibilities of language understanding and generation, as well as impressive generalization capabilities and reasoning skills. As a result, recent studies have actively attempted to harness the power of LLMs to enhance recommender systems. Given the rapid evolution of this research direction in recommender systems, there is a pressing need for a systematic overview that summarizes existing LLM-empowered recommender systems, so as to provide researchers and practitioners in relevant fields with an in-depth understanding. Therefore, in this survey, we conduct a comprehensive review of LLM-empowered recommender systems from various aspects including pre-training, fine-tuning, and prompting paradigms. More specifically, we first introduce the representative methods to harness the power of LLMs (as a feature encoder) for learning representations of users and items. Then, we systematically review the emerging advanced techniques of LLMs for enhancing recommender systems from three paradigms, namely pre-training, fine-tuning, and prompting. Finally, we comprehensively discuss the promising future directions in this emerging field.

Juanhui Li, Harry Shomer, Jiayuan Ding, Yiqi Wang, Yao Ma, Neil Shah, Jiliang Tang, Dawei Yin. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

The recent development of multimodal single-cell technology has made the possibility of acquiring multiple omics data from individual cells, thereby enabling a deeper understanding of cellular states and dynamics. Nevertheless, the proliferation of multimodal single-cell data also introduces tremendous challenges in modeling the complex interactions among different modalities. The recently advanced methods focus on constructing static interaction graphs and applying graph neural networks (GNNs) to learn from multimodal data. However, such static graphs can be suboptimal as they do not take advantage of the downstream task information; meanwhile GNNs also have some inherent limitations when deeply stacking GNN layers. To tackle these issues, in this work, we investigate how to leverage transformers for multimodal single-cell data in an end-to-end manner while exploiting downstream task information. In particular, we propose a scMoFormer framework which can readily incorporate external domain knowledge and model the interactions within each modality and cross modalities. Extensive experiments demonstrate that scMoFormer achieves superior performance on various benchmark datasets. Remarkably, scMoFormer won a Kaggle silver medal with the rank of 24/1221 (Top 2%) without ensemble in a NeurIPS 2022 competition1. Our implementation is publicly available at Github2.

Knowledge graph completion (KGC) aims to predict unseen edges in knowledge graphs (KGs), resulting in the discovery of new facts.A new class of methods have been proposed to tackle this problem by aggregating path information.These methods have shown tremendous ability in the task of KGC.However they are plagued by efficiency issues.Though there are a few recent attempts to address this through learnable path pruning, they often sacrifice the performance to gain efficiency.In this work, we identify two intrinsic limitations of these methods that affect the efficiency and representation quality.To address the limitations, we introduce a new method, TAGNet, which is able to efficiently propagate information.This is achieved by only aggregating paths in a fixed window for each source-target pair.We demonstrate that the complexity of TAGNet is independent of the number of layers.Extensive experiments demonstrate that TAGNet can cut down on the number of propagated messages by as much as 90% while achieving competitive performance on multiple KG datasets 1 .

Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks. Despite the great success, recent studies have shown that GNNs are still vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs. On the other hand, the explanation of GNNs (GnnExplainer for short) provides a better understanding of a trained GNN model by generating a small subgraph and features that are most influential for its prediction. In this paper, we first perform empirical studies to validate that GnnExplainer can act as an inspection tool and have the potential to detect the adversarial perturbations for graphs. This finding motivates us to further investigate a new problem: Whether a graph neural network and its explanations can be jointly attacked by modifying graphs with malicious desires? It is challenging to answer this question since the goals of adversarial attack and bypassing the GnnExplainer essentially contradict with each other. In this work, we give a confirmative answer for this question by proposing a novel attack framework (GEAttack) for graphs, which can attack both a GNN model and its explanations by exploiting their vulnerabilities simultaneously. To the best of our knowledge, this is the very first effort to attack both GNNs and explanations on graph-structured data for the trustworthiness of GNNs. Comprehensive experiments on various real-world datasets demonstrate the effectiveness of the proposed method.

Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optimization problem. This process is often inefficient in computation and memory usage. In this work, we propose a new optimization framework for semi-supervised learning on graphs from a multi-view learning perspective. The proposed framework can be conveniently solved by the alternating optimization algorithms, resulting in significantly improved efficiency. Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.

The studies on adversarial attacks and defenses have greatly improved the robustness of Deep Neural Networks (DNNs). Most advanced approaches have been overwhelmingly designed for continuous data such as images. However, these achievements are still hard to be generalized to categorical data. To bridge this gap, we propose a novel framework, Probabilistic Categorical Adversarial Attack (or PCAA). It transfers the discrete optimization problem of finding categorical adversarial examples to a continuous problem that can be solved via gradient-based methods. We analyze the optimality (attack success rate) and time complexity of PCAA to demonstrate its significant advantage over current search-based attacks. More importantly, through extensive empirical studies, we demonstrate that the well-established defenses for continuous data, such as adversarial training and TRADES, can be easily accommodated to defend DNNs for categorical data.

Diffusion models, as a novel generative paradigm, have achieved remarkable success in various image generation tasks such as image inpainting, image-to-text translation, and video generation. Graph generation is a crucial computational task on graphs with numerous real-world applications. It aims to learn the distribution of given graphs and then generate new graphs. Given the great success of diffusion models in image generation, increasing efforts have been made to leverage these techniques to advance graph generation in recent years. In this paper, we first provide a comprehensive overview of generative diffusion models on graphs, In particular, we review representative algorithms for three variants of graph diffusion models, i.e., Score Matching with Langevin Dynamics (SMLD), Denoising Diffusion Probabilistic Model (DDPM), and Score-based Generative Model (SGM). Then, we summarize the major applications of generative diffusion models on graphs with a specific focus on molecule and protein modeling. Finally, we discuss promising directions in generative diffusion models on graph-structured data.

Recent studies suggest that "memorization" is one necessary factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly fitted DNNs can memorize the labels of many atypical samples, generalize their memorization to correctly classify test atypical samples and enjoy better test performance. While, DNNs which are optimized via adversarial training algorithms can also achieve perfect training performance by memorizing the labels of atypical samples, as well as the adversarially perturbed atypical samples. However, adversarially trained models always suffer from poor generalization, with both relatively low clean accuracy and robustness on the test set. In this work, we study the effect of memorization in adversarial trained DNNs and disclose two important findings: (a) Memorizing atypical samples is only effective to improve DNN's accuracy on clean atypical samples, but hardly improve their adversarial robustness and (b) Memorizing certain atypical samples will even hurt the DNN's performance on typical samples. Based on these two findings, we propose Benign Adversarial Training (BAT) which can facilitate adversarial training to avoid fitting "harmful" atypical samples and fit as more "benign" atypical samples as possible. In our experiments, we validate the effectiveness of BAT, and show that it can achieve better clean accuracy vs. robustness trade-off than baseline methods, in benchmark datasets for image classification.

Deep Learning models are at the core of research in Artificial Intelligence research today. A tide in research for deep learning on graphs or graph neural networks. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, program synthesis and analysis, financial security, Drug Discovery and so on. However, there are still many challenges regarding a broad range of the topics in deep learning on graphs, from methodologies to applications, and from foundations to the new frontiers of GNNs. This international workshop on "Deep Learning on Graphs: Method and Applications (DLG-KDD'23)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges.

Graph Neural Networks (GNNs) have gained significant attention in recent years due to their ability to model complex relationships between entities in graph-structured data such as social networks, protein structures, and knowledge graphs. However, due to the size of real-world industrial graphs and the special architecture of GNNs, it is a long-lasting challenge for engineers and researchers to deploy GNNs on large-scale graphs, which significantly limits their applications in real-world applications. In this tutorial, we will cover the fundamental scalability challenges of GNNs, frontiers of large-scale GNNs including classic approaches and some newly emerging techniques, the evaluation and comparison of scalable GNNs, and their large-scale real-world applications. Overall, this tutorial aims to provide a systematic and comprehensive understanding of the challenges and state-of-the-art techniques for scaling GNNs. The summary and discussion on future directions will inspire engineers and researchers to explore new ideas and developments in this rapidly evolving field. The website of this tutorial is available at https://sites.google.com/ncsu.edu/gnnkdd2023tutorial.

Graph neural networks (GNNs) have achieved impressive impressions for graph-related tasks. However, most GNNs are primarily studied under the cases of signal domain with supervised training, which requires abundant task-specific labels and is difficult to transfer to other domains. There are few works focused on domain adaptation for graph node classification. They mainly focused on aligning the feature space of the source and target domains, without considering the feature alignment between different categories, which may lead to confusion of classification in the target domain. However, due to the scarcity of labels of the target domain, we cannot directly perform effective alignment of categories from different domains, which makes the problem more challenging. In this paper, we present the Spectral Augmentation for Graph Domain Adaptation (SA-GDA) for graph node classification. First, we observe that nodes with the same category in different domains exhibit similar characteristics in the spectral domain, while different classes are quite different. Following the observation, we align the category feature space of different domains in the spectral domain instead of aligning the whole features space, and we theoretical proof the stability of proposed SA-GDA. Then, we develop a dual graph convolutional network to jointly exploits local and global consistency for feature aggregation. Last, we utilize a domain classifier with an adversarial learning submodule to facilitate knowledge transfer between different domain graphs. Experimental results on a variety of publicly available datasets reveal the effectiveness of our SA-GDA.

Modeling customer shopping intentions is a crucial task for e-commerce, as it directly impacts user experience and engagement. Thus, accurately understanding customer preferences is essential for providing personalized recommendations. Session-based recommendation, which utilizes customer session data to predict their next interaction, has become increasingly popular. However, existing session datasets have limitations in terms of item attributes, user diversity, and dataset scale. As a result, they cannot comprehensively capture the spectrum of user behaviors and preferences.To bridge this gap, we present the Amazon Multilingual Multi-locale Shopping Session Dataset, namely Amazon-M2. It is the first multilingual dataset consisting of millions of user sessions from six different locales, where the major languages of products are English, German, Japanese, French, Italian, and Spanish.Remarkably, the dataset can help us enhance personalization and understanding of user preferences, which can benefit various existing tasks as well as enable new tasks. To test the potential of the dataset, we introduce three tasks in this work:(1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation.With the above tasks, we benchmark a range of algorithms on our proposed dataset, drawing new insights for further research and practice. In addition, based on the proposed dataset and tasks, we hosted a competition in the KDD CUP 2023 https://www.aicrowd.com/challenges/amazon-kdd-cup-23-multilingual-recommendation-challenge and have attracted thousands of users and submissions. The winning solutions and the associated workshop can be accessed at our website~https://kddcup23.github.io/.

Graph Neural Networks (GNNs) have emerged as a powerful tool for semi-supervised node classification tasks. However, recent studies have revealed various biases in GNNs stemming from both node features and graph topology. In this work, we uncover a new bias - label position bias, which indicates that the node closer to the labeled nodes tends to perform better. We introduce a new metric, the Label Proximity Score, to quantify this bias, and find that it is closely related to performance disparities. To address the label position bias, we propose a novel optimization framework for learning a label position unbiased graph structure, which can be applied to existing GNNs. Extensive experiments demonstrate that our proposed method not only outperforms backbone methods but also significantly mitigates the issue of label position bias in GNNs.

Link prediction attempts to predict whether an unseen edge exists based on only a portion of the graph. A flurry of methods has been created in recent years that attempt to make use of graph neural networks (GNNs) for this task. Furthermore, new and diverse datasets have also been created to better evaluate the effectiveness of these new models. However, multiple limitations currently exist that hinders our ability to properly evaluate these new methods. This includes, but is not limited to: (1) The underreporting of performance on multiple baselines, (2) A lack of a unified data split and evaluation metric on some datasets, (3) An unrealistic evaluation setting that produces negative samples that are easy to classify. To overcome these challenges we first conduct a fair comparison across prominent methods and datasets, utilizing the same dataset settings and hyperparameter settings. We then create a new real-world evaluation setting that samples difficult negative samples via multiple heuristics. The new evaluation setting helps promote new challenges and opportunities in link prediction by aligning the evaluation with real-world situations.

Knowledge tracing (KT) is a task that predicts students' future performance based on their historical learning interactions. With the rapid development of deep learning techniques, existing KT approaches follow a data-driven paradigm that uses massive problem-solving records to model students' learning processes. However, although the educational contexts contain various factors that may have an influence on student learning outcomes, existing public KT datasets mainly consist of anonymized ID-like features, which may hinder the research advances towards this field. Therefore, in this work, we present, \emph{XES3G5M}, a large-scale dataset with rich auxiliary information about questions and their associated knowledge components (KCs)\footnote{\label{ft:kc}A KC is a generalization of everyday terms like concept, principle, fact, or skill.}. The XES3G5M dataset is collected from a real-world online math learning platform, which contains 7,652 questions, and 865 KCs with 5,549,635 interactions from 18,066 students. To the best of our knowledge, the XES3G5M dataset not only has the largest number of KCs in math domain but contains the richest contextual information including tree structured KC relations, question types, textual contents and analysis and student response timestamps. Furthermore, we build a comprehensive benchmark on 19 state-of-the-art deep learning based knowledge tracing (DLKT) models. Extensive experiments demonstrate the effectiveness of leveraging the auxiliary information in our XES3G5M with DLKT models. We hope the proposed dataset can effectively facilitate the KT research work.

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns, exhibiting a structural disparity. However, the analysis of GNN performance with respect to nodes exhibiting different structural patterns, e.g., homophilic nodes in heterophilic graphs, remains rather limited. In the present study, we provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes within homophilic graphs and heterophilic nodes within heterophilic graphs while struggling on the opposite node set, exhibiting a performance disparity. We theoretically and empirically identify effects of GNNs on testing nodes exhibiting distinct structural patterns. We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity, namely the aggregated feature distance and homophily ratio difference between training and testing nodes. Furthermore, we demonstrate the practical implications of our new findings via (1) elucidating the effectiveness of deeper GNNs; and (2) revealing an over-looked distribution shift factor on graph out-of-distribution problem and proposing a new scenario accordingly.

Query understanding plays a key role in exploring users' search intents and facilitating users to locate their most desired information. However, it is inherently challenging since it needs to capture semantic information from short and ambiguous queries and often requires massive task-specific labeled data. In recent years, pre-trained language models (PLMs) have advanced various natural language processing tasks because they can extract general semantic information from large-scale corpora. However, directly applying them to query understanding is sub-optimal because existing strategies rarely consider to boost the search performance. On the other hand, search logs contain user clicks between queries and urls that provide rich users' search behavioral information on queries beyond their content. Therefore, in this paper, we aim to fill this gap by exploring search logs. In particular, we propose a novel graph-enhanced pre-training framework, GE-BERT, which leverages both query content and the query graph. The model is trained on a query graph where nodes are queries and two queries are connected if they lead to clicks on the same urls, to capture both semantic information and users' search behavioral information of queries. Extensive experiments on offline and online tasks have demonstrated the effectiveness of the proposed framework.

A fundamental task for knowledge graphs (KGs) is knowledge graph completion (KGC). It aims to predict unseen edges by learning representations for all the entities and relations in a KG. A common concern when learning representations on traditional graphs is degree bias. It can affect graph algorithms by learning poor representations for lower-degree nodes, often leading to low performance on such nodes. However, there has been limited research on whether there exists degree bias for embedding-based KGC and how such bias affects the performance of KGC. In this paper, we validate the existence of degree bias in embedding-based KGC and identify the key factor to degree bias. We then introduce a novel data augmentation method, KG-Mixup, to generate synthetic triples to mitigate such bias. Extensive experiments have demonstrated that our method can improve various embedding-based KGC methods and outperform other methods tackling the bias problem on multiple benchmark datasets. 1

In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone’s daily life and profoundly altering the course of human society. The intention behind developing AI was and is to benefit humans by reducing labor, increasing everyday conveniences, and promoting social good. However, recent research and AI applications indicate that AI can cause unintentional harm to humans by, for example, making unreliable decisions in safety-critical scenarios or undermining fairness by inadvertently discriminating against a group or groups. Consequently, trustworthy AI has recently garnered increased attention regarding the need to avoid the adverse effects that AI could bring to people, so people can fully trust and live in harmony with AI technologies. A tremendous amount of research on trustworthy AI has been conducted and witnessed in recent years. In this survey, we present a comprehensive appraisal of trustworthy AI from a computational perspective to help readers understand the latest technologies for achieving trustworthy AI. Trustworthy AI is a large and complex subject, involving various dimensions. In this work, we focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Nondiscrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems. We also discuss the accordant and conflicting interactions among different dimensions and discuss potential aspects for trustworthy AI to investigate in the future.

As widely used in data-driven decision-making, recommender systems have been recognized for their capabilities to provide users with personalized services in many user-oriented online services, such as E-commerce (e.g., Amazon, Taobao, etc.) and Social Media sites (e.g., Facebook and Twitter). Recent works have shown that deep neural networks-based recommender systems are highly vulnerable to adversarial attacks, where adversaries can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target recommender system to promote or demote a set of target items. Instead of generating users with fake profiles from scratch, in this article, we introduce a novel strategy to obtain “fake” user profiles via copying cross-domain user profiles, where a reinforcement learning based black-box attacking framework (CopyAttack+) is developed to effectively and efficiently select cross-domain user profiles from the source domain to attack the target system. Moreover, we propose to train a local surrogate system for mimicking adversarial black-box attacks in the source domain, so as to provide transferable signals with the purpose of enhancing the attacking strategy in the target black-box recommender system. Comprehensive experiments on three real-world datasets are conducted to demonstrate the effectiveness of the proposed attacking framework.

Graph neural networks (GNNs) have been widely applied in the recommendation tasks and have achieved very appealing performance. However, most GNN-based recommendation methods suffer from the problem of data sparsity in practice. Meanwhile, pre-training techniques have achieved great success in mitigating data sparsity in various domains such as natural language processing (NLP) and computer vision (CV) . Thus, graph pre-training has the great potential to alleviate data sparsity in GNN-based recommendations. However, pre-training GNNs for recommendations faces unique challenges. For example, user-item interaction graphs in different recommendation tasks have distinct sets of users and items, and they often present different properties. Therefore, the successful mechanisms commonly used in NLP and CV to transfer knowledge from pre-training tasks to downstream tasks such as sharing learned embeddings or feature extractors are not directly applicable to existing GNN-based recommendations models. To tackle these challenges, we delicately design an adaptive graph pre-training framework for localized collaborative filtering (ADAPT) . It does not require transferring user/item embeddings, and is able to capture both the common knowledge across different graphs and the uniqueness for each graph simultaneously. Extensive experimental results have demonstrated the effectiveness and superiority of ADAPT.

Crime prediction plays an impactful role in enhancing public security and sustainable development of urban. With recent advances in data collection and integration technologies, a large amount of urban data with rich crime-related information and fine-grained spatio-temporal logs have been recorded. Such helpful information can boost our understandings of the temporal evolution and spatial factors of urban crimes and can enhance accurate crime prediction. However, the vast majority of existing crime prediction algorithms either do not distinguish different types of crime or treat each crime type separately, which fails to capture the intrinsic correlations among different types of crime. In this paper, we perform crime prediction exploiting the cross-type and spatio-temporal correlations of urban crimes. In particular, we verify the existence of correlations among different types of crime from temporal and spatial perspectives, and propose a coherent framework to mathematically model these correlations for crime prediction. Extensive experiments on real-world datasets validate the effectiveness of our framework.

Haochen Liu, Joseph Thekinen, Sinem Mollaoglu, Da Tang, Ji Yang, Youlong Cheng, Hui Liu, Jiliang Tang. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Real-world recommender systems usually consist of two phases. Predictive models in Phase I provide accurate predictions of users' actions on items, and Phase II is to aggregate the predictions withstrategic parameters to make final recommendations, which aim to meet multiple business goals, such as maximizing users' like rate and average engagement time. Though it is important to generate accurate predictions in Phase I, it is also crucial to optimize the strategic parameters in Phase II. Conventional solutions include manually tunning, Bayesian optimization, contextual multi-armed bandit optimization, etc. However, these methods either produce universal strategic parameters for all the users or focus on a deterministic solution, which leads to an undesirable performance. In this paper, we propose a personalized probabilistic solution for strategic parameter optimization. We first formulate the personalized probabilistic optimizing problem and compare its solution with deterministic and context-free solutions theoretically to show its superiority. We then introduce a novel Personalized pRObabilistic strategic parameter optimizing Policy Network (PROPN) to solve the problem. PROPN follows reinforcement learning architecture where a neural network serves as an agent that dynamically adjusts the distributions of strategic parameters for each user. We evaluate our model under the streaming recommendation setting on two public real-world datasets. The results show that our framework outperforms representative baseline methods.

Recent studies show that NLP models trained on standard English texts tend to produce biased outcomes against underrepresented English varieties. In this work, we conduct a pioneering study of the English variety use of African American English (AAE) in NLI task. First, we propose CodeSwitch, a greedy unidirectional morphosyntactically-informed rule-based translation method for data augmentation. Next, we use CodeSwitch to present a preliminary study to determine if demographic language features do in fact influence models to produce false predictions. Then, we conduct experiments on two popular datasets and propose two simple, yet effective and generalizable debiasing methods. Our findings show that NLI models (e.g. BERT) trained under our proposed frameworks outperform traditional large language models while maintaining or even improving the prediction performance. In addition, we intend to release CodeSwitch, in hopes of promoting dialectal language diversity in training data to both reduce the discriminatory societal impacts and improve model robustness of downstream NLP tasks.

Adversarial training has been empirically proven to be one of the most effective and reliable defense methods against adversarial attacks. However, the majority of existing studies are focused on balanced datasets, where each class has a similar amount of training examples. Research on adversarial training with imbalanced training datasets is rather limited. As the initial effort to investigate this problem, we reveal the facts that adversarially trained models present two distinguished behaviors from naturally trained models in imbalanced datasets: (1) Compared to natural training, adversarially trained models can suffer much worse performance on under-represented classes, when the training dataset is extremely imbalanced. (2) Traditional reweighting strategies which assign large weights to underrepresented classes will drastically hurt the model’s performance on well-represented classes. In this paper, to further understand our observations, we theoretically show that the poor data separability is one key reason causing this strong tension between under-represented and well-represented classes. Motivated by this finding, we propose the Separable Reweighted Adversarial Training (SRAT) framework to facilitate adversarial training under imbalanced scenarios, by learning more separable features for different classes. Extensive experiments on various datasets verify the effectiveness of the proposed framework.

Although deep neural networks (DNNs) have been successfully deployed in various real-world application scenarios, recent studies demonstrated that DNNs are extremely vulnerable to adversarial attacks. By introducing visually imperceptible perturbations into benign inputs, the attacker can manipulate a DNN model into providing wrong predictions. For practitioners who are applying DNNs into real-world problems, understanding the characteristics of different kinds of attacks will not only help them improve the robustness of their models, but also can help them have deeper insights into the working mechanism of DNNs. In this tutorial, we provide a comprehensive overview of the recent advances of adversarial learning, including both attack methods and defense methods. Specifically, we first give a detailed introduction of various types of evasion attacks, followed by a series of representative defense methods against evasion attacks. We then discuss different poisoning attack methods, followed by several defense methods against poisoning attacks. In addition, besides introducing attack methods working in the digital setting, we also introduce attack methods designed for threatening physical world systems. Finally, we present DeepRobust, a PyTorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Via our tutorial, audience can grasp the main ideas of adversarial attacks and defenses and obtain a deep insight of the robustness of DNNs. The tutorial official website is available at https://sites.google.com/view/kdd22-tutorial-adv-learn/.

Machine learning on graph data has become a common area of interest across academia and industry. However, due to the size of real-world industry graphs (hundreds of millions of vertices and billions of edges) and the special architecture of graph neural net- works, it is still a challenge for practitioners and researchers to perform machine learning tasks on large-scale graph data. It typi- cally takes a powerful and expensive GPU machine to train a graph neural network on a million-vertex scale graph, let alone doing deep learning on real enterprise graphs. In this tutorial, we will cover how to develop and run performant graph algorithms and graph neural network models with TigerGraph [3], a massively parallel platform for graph analytics, and its Machine Learning Workbench with PyTorch Geometric [4] and DGL [8] support. Using an NFT transaction dataset [6], we will first investigate transactions using graph algorithms by themselves as methods of graph traversing, clustering, classification, and determining similarities between data. Secondly, we will show how to use those graph-derived features such as PageRank and embeddings to empower traditional machine learning models. Finally, we will demonstrate how to train common graph neural networks with TigerGraph and how to implement novel graph neural network models. Participants will use the Tiger- Graph ML Workbench Cloud to perform graph feature engineering and train their machine learning algorithms during the session.

Recent years have witnessed remarkable success achieved by graph neural networks (GNNs) in many real-world applications such as recommendation and drug discovery. Despite the success, oversmoothing has been identified as one of the key issues which limit the performance of deep GNNs. It indicates that the learned node representations are highly indistinguishable due to the stacked aggregators. In this paper, we propose a new perspective to look at the performance degradation of deep GNNs, i.e., feature overcorrelation. Through empirical and theoretical study on this matter, we demonstrate the existence of feature overcorrelation in deeper GNNs and reveal potential reasons leading to this issue. To reduce the feature correlation, we propose a general framework DeCorr which can encourage GNNs to encode less redundant information. Extensive experiments have demonstrated that DeCorr can help enable deeper GNNs and is complementary to existing techniques tackling the oversmoothing issue.

As training deep learning models on large dataset takes a lot of time and resources, it is desired to construct a small synthetic dataset with which we can train deep learning models sufficiently. There are recent works that have explored solutions on condensing image datasets through complex bi-level optimization. For instance, dataset condensation (DC) matches network gradients w.r.t. large-real data and small-synthetic data, where the network weights are optimized for multiple steps at each outer iteration. However, existing approaches have their inherent limitations: (1) they are not directly applicable to graphs where the data is discrete; and (2) the condensation process is computationally expensive due to the involved nested optimization. To bridge the gap, we investigate efficient dataset condensation tailored for graph datasets where we model the discrete graph structure as a probabilistic model. We further propose a one-step gradient matching scheme, which performs gradient matching for only one single step without training the network weights. Our theoretical analysis shows this strategy can generate synthetic graphs that lead to lower classification loss on real graphs. Extensive experiments on various graph datasets demonstrate the effectiveness and efficiency of the proposed method. In particular, we are able to reduce the dataset size by 90% while approximating up to 98% of the original performance and our method is significantly faster than multi-step gradient matching (e.g. $15$× in CIFAR10 for synthesizing 500 graphs).

Recent advances in multimodal single-cell technologies have enabled simultaneous acquisitions of multiple omics data from the same cell, providing deeper insights into cellular states and dynamics. However, it is challenging to learn the joint representations from the multimodal data, model the relationship between modalities, and, more importantly, incorporate the vast amount of single-modality datasets into the downstream analyses. To address these challenges and correspondingly facilitate multimodal single-cell data analyses, three key tasks have been introduced: Modality prediction, Modality matching andJoint embedding. In this work, we present a general Graph Neural Network framework scMoGNN to tackle these three tasks and show that scMoGNN demonstrates superior results in all three tasks compared with the state-of-the-art and conventional approaches. Our method is an official winner in the overall ranking ofModality prediction from NeurIPS 2021 Competition (https://openproblems.bio/neurips_2021/), and all implementations of our methods have been integrated into DANCE package (https://github.com/OmicsML/dance).

Deep Learning models are at the core of research in Artificial Intelligence research today. A tide in research for deep learning on graphs or graph neural networks. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, program synthesis and analysis, financial security, Drug Discovery and so on. However, there are still many challenges regarding a broad range of the topics in deep learning on graphs, from methodologies to applications, and from foundations to the new frontiers of GNNs. This international workshop on "Deep Learning on Graphs: Method and Applications (DLG-KDD'22)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to above challenges.

Knowledge tracing (KT) is the task of using students' historical learning interaction data to model their knowledge mastery over time so as to make predictions on their future interaction performance. Recently, remarkable progress has been made of using various deep learning techniques to solve the KT problem. However, the success behind deep learning based knowledge tracing (DLKT) approaches is still left somewhat unknown and proper measurement and analysis of these DLKT approaches remain a challenge. First, data preprocessing procedures in existing works are often private and custom, which limits experimental standardization. Furthermore, existing DLKT studies often differ in terms of the evaluation protocol and are far away real-world educational contexts. To address these problems, we introduce a comprehensive python based benchmark platform, \textsc{pyKT}, to guarantee valid comparisons across DLKT methods via thorough evaluations. The \textsc{pyKT} library consists of a standardized set of integrated data preprocessing procedures on 7 popular datasets across different domains, and 10 frequently compared DLKT model implementations for transparent experiments. Results from our fine-grained and rigorous empirical KT studies yield a set of observations and suggestions for effective DLKT, e.g., wrong evaluation setting may cause label leakage that generally leads to performance inflation; and the improvement of many DLKT approaches is minimal compared to the very first DLKT model proposed by Piech et al. \cite{piech2015deep}. We have open sourced \textsc{pyKT} and our experimental results at \url{https://pykt.org/}. We welcome contributions from other research groups and practitioners.

The unbiased learning to rank (ULTR) problem has been greatly advanced by recent deep learning techniques and well-designed debias algorithms. However, promising results on the existing benchmark datasets may not be extended to the practical scenario due to some limitations of existing datasets. First, their semantic feature extractions are outdated while state-of-the-art large-scale pre-trained language models like BERT cannot be utilized due to the lack of original text. Second, display features are incomplete; thus in-depth study on ULTR is impossible such as the displayed abstract for analyzing the click necessary bias. Third, synthetic user feedback has been adopted by most existing datasets and real-world user feedback is greatly missing. To overcome these disadvantages, we introduce the Baidu-ULTR dataset. It involves randomly sampled 1.2 billion searching sessions and 7,008 expert annotated queries(397,572 query document pairs). Baidu-ULTR is the first billion-level dataset for ULTR. Particularly, it offers: (1)the original semantic features and pre-trained language models of different sizes; (2)sufficient display information such as position, displayed height, and displayed abstract, enabling the comprehensive study of multiple displayed biases; and (3)rich user feedback on search result pages (SERPs) like dwelling time, allowing for user engagement optimization and promoting the exploration of multi-task learning in ULTR. Furthermore, we present the design principle of Baidu-ULTR and the performance of representative ULTR algorithms on Baidu-ULTR. The Baidu-ULTR dataset and corresponding baseline implementations are available at https://github.com/ChuXiaokai/baiduultrdataset. The dataset homepage is available at https://searchscience.baidu.com/dataset.html.

User-item interactions in recommendations can be naturally denoted as a user-item bipartite graph. Given the success of graph neural networks (GNNs) in graph representation learning, GNN-based Collaborative Filtering (CF) methods have been proposed to advance recommender systems. These methods often make recommendations based on the learned user and item embeddings. However, we found that they do not perform well with sparse user-item graphs which are quite common in real-world recommendations. Therefore, in this work, we introduce a novel perspective to build GNN-based CF methods for recommendations which leads to the proposed framework Localized Graph Collaborative Filtering (LGCF). One key advantage of LGCF is that it does not need to learn embeddings for each user and item, which is challenging in sparse scenarios. Alternatively, LGCF aims at encoding useful CF information into a localized graph and making recommendations based on such graph. Extensive experiments on various datasets validate the effectiveness of LGCF, especially in sparse scenarios. Furthermore, empirical results demonstrate that LGCF provides complementary information to the embedding-based CF model which can be utilized to boost recommendation performance.

Crowdsourcing has proven to be a cost-effective way to meet the demands for labeled training data in supervised deep learning models. However, crowdsourced labels are often inconsistent and noisy due to cognitive and expertise differences among crowd workers. Existing approaches either infer latent true labels from noisy crowdsourced labels or learn a discriminative model directly from the crowdsourced labeled data, assuming the latent true label distribution is class-balanced. Unfortunately, in many real-world applications, the true label distribution typically is imbalanced across classes. Therefore, in this paper, we address the problem of learning from crowdsourced labeled data with an imbalanced true label distribution. We propose a new framework, named “Learning from Imbalanced Crowdsourced Labeled Data” (ICED), which simultaneously infers true labels from imbalanced crowdsourced labeled data and achieves high accuracy on downstream tasks such as classification. The ICED framework consists of two modules, i.e., a true label inference module and a synthetic data generation module, that augment each other iteratively. Extensive experiments conducted on both synthetic and real-world datasets demonstrate the effectiveness of the ICED framework. Our code is available at https://github.com/wentao-repo/ICED.

Recommender systems aim to provide personalized services to users and are playing an increasingly important role in our daily lives. The key of recommender systems is to predict how likely users will interact with items based on their historical online behaviors, e.g., clicks, add-to-cart, purchases, etc. To exploit these user-item interactions, there are increasing efforts on considering the user-item interactions as a user-item bipartite graph and then performing information propagation in the graph via Graph Neural Networks (GNNs). Given the power of GNNs in graph representation learning, these GNNs-based recommendation methods have remarkably boosted the recommendation performance. Despite their success, most existing GNNs-based recommender systems overlook the existence of interactions caused by unreliable behaviors (e.g., random/bait clicks) and uniformly treat all the interactions, which can lead to sub-optimal and unstable performance. In this paper, we investigate the drawbacks (e.g., non-adaptive propagation and non-robustness) of existing GNN-based recommendation methods. To address these drawbacks, we introduce a principled graph trend collaborative filtering method and propose the Graph Trend Filtering Networks for recommendations (GTN) that can capture the adaptive reliability of the interactions. Comprehensive experiments and ablation studies are presented to verify and understand the effectiveness of the proposed framework. Our implementation based on PyTorch is available: https://github.com/wenqifan03/GTN-SIGIR2022.

Real-world recommendation datasets have been shown to be subject to selection bias, which can challenge recommendation models to learn real preferences of users, so as to make accurate recommendations. Existing approaches to mitigate selection bias, such as data imputation and inverse propensity score, are sensitive to the quality of the additional imputation or propensity estimation models. To break these limitations, in this work, we propose a novel self-supervised learning (SSL) framework, i.e., Rating Distribution Calibration (RDC), to tackle selection bias without introducing additional models. In addition to the original training objective, we introduce a rating distribution calibration loss. It aims to correct the predicted rating distribution of biased users by taking advantage of that of their similar unbiased users. We empirically evaluate RDC on two real-world datasets and one synthetic dataset. The experimental results show that RDC outperforms the original model as well as the state-of-the-art debiasing approaches by a significant margin.

Graph neural networks (GNNs) have emerged as a successful method on graph structured data. Limited by expensive labeled data, contrastive learning has been adopted to the graph domain. In most existing node-level graph contrastive learning methods, when applying contrastive learning to a certain unlabeled node (the center node), its corresponding “similar” node (positive sample) is usually generated by data augmentation. Other nodes in the graph are served as the “dissimilar” nodes (negative samples), which leads to two major problems. First, the computational cost can be prohibitively expensive, especially when the graph is large. Second, utilizing some nodes which share the same label with the center node as the negative samples will damage the learning process. Hence, to address these issues, we explore the feasibility of only sampling a part of nodes for graph contrastive learning process. And unlike the previous self-supervised contrastive methods, we use joint training to exploit supervised signals as much as possible in contrastive learning. Hence, we propose a Negative Samples Selecting Strategy to utilize the classification prediction to guide the selection of the negative samples for sampled nodes. Then, we further incorporate this strategy for performing contrastive learning on graphs and propose a framework named Graph Contrastive Learning with Negative Samples Selecting Strategy (GCNSS). We demonstrate that GCNSS can be trained much faster with much less computation memory than graph contrastive learning baselines, and GCNSS can effectively boost the performance of existing GNN models on semi-supervised node classification tasks across many different datasets. The code is in: https://github.com/MR9812/GCNSS.

Data in many real-world applications such as social networks, users shopping behaviors, and inter-item relationships can be represented as graphs. Graph Neural Networks (GNNs) have shown great success in learning meaningful representations for graphs by inherently integrating node information and topological structure. Data in social recommendations can also be denotes as graph data in the form of user-user social graphs and user-item graphs. In addition, the relationships between items can be denoted as item-item graphs. GNNs provide an unprecedented opportunity to advance social recommendations. However, there are tremendous challenges in building GNNs-based social recommendations where (1) users (items) are simultaneously involved in the user-item graph and user-user social graph (item-item graph); (2) user-item graphs not only contain user-item interactions but also include users’ opinions on items; and (3) the nature of social relations are heterogeneous among users. In this paper, we propose a novel graph neural network framework (GraphRec+) for social recommendations, which is able to coherently model graph data in order to learn better user and item representations. Specifically, we introduce a principled approach for jointly capturing interactions and opinions in the user-item graph and also propose an attention mechanism to differentiate the heterogeneous strengths of social relations. Comprehensive experiments on three real-world datasets show the effectiveness of the proposed framework.

Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing representation learning approaches often require a large number of consistent and noise-free labels. However, due to various reasons such as budget constraints and privacy concerns, labels are very limited in many real-world scenarios. Directly applying standard representation learning approaches on small labeled data sets will easily run into over-fitting problems and lead to sub-optimal solutions. Even worse, in some domains such as education, the limited labels are usually annotated by multiple workers with diverse expertise, which yields noises and inconsistency in such crowdsourcing settings. In this paper, we propose a novel framework which aims to learn effective representations from limited data with crowdsourced labels. Specifically, we design a grouping based deep neural network to learn embeddings from a limited number of training samples and present a Bayesian confidence estimator to capture the inconsistency among crowdsourced labels. Furthermore, to expedite the training process, we develop a hard example selection procedure to adaptively pick up training examples that are misclassified by the model. Extensive experiments conducted on three real-world data sets demonstrate the superiority of our framework on learning representations from limited data with crowdsourced labels, comparing with various state-of-the-art baselines. In addition, we provide a comprehensive analysis on each of the main components of our proposed framework and also introduce the promising results it achieved in our real production to fully understand the proposed framework. To encourage reproducible results, we make our code available online athttps://github.com/tal-ai/RECLE.

DeepRobust is a PyTorch platform for generating adversarial examples and building robust machine learning models for different data domains. Users can easily evaluate the attack performance against different defense methods with DeepRobust and get performance analyzing visualization. In this paper, we introduce the functions of DeepRobust with detailed instructions. We believe that DeepRobust is a useful tool to measure deep learning model robustness and to find the suitable countermeasures against adversarial attacks. The platform is kept updated and can be found at https://github.com/DSE-MSU/DeepRobust. More details of instruction can be found in the documentation at https://deeprobust.readthedocs.io/en/latest/.

With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in utilizing RL for online advertising in recommendation platforms (e.g., e-commerce and news feed sites). However, most RL-based advertising algorithms focus on optimizing ads' revenue while ignoring the possible negative influence of ads on user experience of recommended items (products, articles and videos). Developing an optimal advertising algorithm in recommendations faces immense challenges because interpolating ads improperly or too frequently may decrease user experience, while interpolating fewer ads will reduce the advertising revenue. Thus, in this paper, we propose a novel advertising strategy for the rec/ads trade-off. To be specific, we develop an RL-based framework that can continuously update its advertising strategies and maximize reward in the long run. Given a recommendation list, we design a novel Deep Q-network architecture that can determine three internally related tasks jointly, i.e., (i) whether to interpolate an ad or not in the recommendation list, and if yes, (ii) the optimal ad and (iii) the optimal location to interpolate. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework.

With the emergence of online social media platforms, there has been a surge of teachers/educators turning to these platforms for professional purposes, e.g., supplementing their students’ educational needs. Consequently, teachers in social media have been the subject of many educational studies. Despite the progress in this line of research, one of the major obstacles is the limited number of teachers being investigated. Current studies usually suffice to at most a few hundreds of surveyed teachers while there are thousands of other teachers online. To better understand teachers in online social media and enable modern machine learning approaches to process teacher-related data, we need to identify more teachers. Thus, this paper proposes a framework to automatically identify teachers on Pinterest– an image-based social media platform popular among teachers. We formulate the teacher identification problem as a positive unlabeled learning task where positive samples are a small set of surveyed teachers, and unlabeled samples are their connected users on Pinterest. We perform extensive experiments on a real dataset of teachers on Pinterest and show the effectiveness of our framework. We believe the proposed framework can potentially improve the quality of many research endeavors concerned with studying teachers in social media.

Graph Neural Networks (GNNs) have risen to prominence in learning representations for graph structured data. A single GNN layer typically consists of a feature transformation and a feature aggregation operation. The former normally uses feed-forward networks to transform features, while the latter aggregates the transformed features over the graph. Numerous recent works have proposed GNN models with different designs in the aggregation operation. In this work, we establish mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as (approximately) solving a graph denoising problem with a smoothness assumption. Such a unified view across GNNs not only provides a new perspective to understand a variety of aggregation operations but also enables us to develop a unified graph neural network framework UGNN. To demonstrate its promising potential, we instantiate a novel GNN model, ADA-UGNN, derived from UGNN, to handle graphs with adaptive smoothness across nodes. Comprehensive experiments show the effectiveness of ADA-UGNN.

Network alignment, in general, seeks to discover the hidden underlying correspondence between nodes across two (or more) networks when given their network structure. However, most existing network alignment methods have added assumptions of additional constraints to guide the alignment, such as having a set of seed node-node correspondences across the networks or the existence of side-information. Instead, we seek to develop a general unsupervised network alignment algorithm that makes no additional assumptions. Recently, network embedding has proven effective in many network analysis tasks, but embeddings of different networks are not aligned. Thus, we present our Deep Adversarial Network Alignment (DANA) framework that first uses deep adversarial learning to discover complex mappings for aligning the embedding distributions of the two networks. Then, using our learned mapping functions, DANA performs an efficient nearest neighbor node alignment. Furthermore, we present an unsupervised heuristic to perform model selection for DANA. We perform experiments on real world datasets to show the effectiveness of our framework for first aligning the graph embedding distributions and then discovering node alignments that outperform existing methods.

Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and transforming the information from the neighborhood. Meanwhile, they adopt the same strategy in aggregating the information from different feature dimensions. However, suggested by social dimension theory and spectral embedding, there are potential benefits to treat the dimensions differently during the aggregation process. In this work, we investigate to enable heterogeneous contributions of feature dimensions in GNNs. In particular, we propose a general graph feature gating network (GFGN) based on the graph signal denoising problem and then correspondingly introduce three graph filters under GFGN to allow different levels of contributions from feature dimensions. Extensive experiments on various real-world datasets demonstrate the effectiveness and robustness of the proposed frameworks.

Recommender systems, which aim to suggest personalized lists of items for users, have drawn a lot of attention. In fact, many of these state-of-the-art recommender systems have been built on deep neural networks (DNNs). Recent studies have shown that these deep neural networks are vulnerable to attacks, such as data poisoning, which generate fake users to promote a selected set of items. Correspondingly, effective defense strategies have been developed to detect these generated users with fake profiles. Thus, new strategies of creating more `realistic' user profiles to promote a set of items should be investigated to further understand the vulnerability of DNNs based recommender systems. In this work, we present a novel framework CopyAttack. It is a reinforcement learning based black-box attacking method that harnesses real users from a source domain by copying their profiles into the target domain with the goal of promoting a subset of items. CopyAttack is constructed to both efficiently and effectively learn policy gradient networks that first select, then further refine/craft user profiles from the source domain, and ultimately copy them into the target domain. CopyAttack's goal is to maximize the hit ratio of the targeted items in the Top-k recommendation list of the users in the target domain. We conducted experiments on two real-world datasets and empirically verified the effectiveness of the proposed framework. The implementation of CopyAttack is available at https://github.com/wenqifan03/CopyAttack.

Deep learning-based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimension of categorical variables (e.g., user/item identifiers) and meaningfully transform them in the low-dimensional space. The majority of existing DLRSs empirically pre-define a fixed and unified dimension for all user/item embeddings. It is evident from recent researches that different embedding sizes are highly desired for different users/items according to their frequency. However, manually selecting embedding sizes in recommender systems can be very challenging due to a large number of users/items and the dynamic nature of their frequency. Thus, in this paper, we propose an AutoML based end-to-end framework (AutoEmb), enabling various embedding dimensions according to the frequency in an automated and dynamic manner. To be specific, we first enhance a typical DLRS to allow various embedding dimensions; then, we propose an end-to-end differentiable framework that can automatically select different embedding dimensions according to user/item frequency; finally, we propose an AutoML based optimization algorithm in a streaming recommendation setting. The experimental results based on widely used benchmark datasets demonstrate the effectiveness of the AutoEmb framework.

While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $\ell_1$ and $\ell_2$-based graph smoothing. In particular, we propose a novel and general message passing scheme into GNNs. This message passing algorithm is not only friendly to back-propagation training but also achieves the desired smoothing properties with a theoretical convergence guarantee. Experiments on semi-supervised learning tasks demonstrate that the proposed Elastic GNNs obtain better adaptivity on benchmark datasets and are significantly robust to graph adversarial attacks. The implementation of Elastic GNNs is available at \url{https://github.com/lxiaorui/ElasticGNN}.

Adversarial training algorithms have been proved to be reliable to improve machine learning models’ robustness against adversarial examples. However, we find that adversarial training algorithms tend to introduce severe disparity of accuracy and robustness between different groups of data. For instance, PGD adversarially trained ResNet18 model on CIFAR-10 has 93% clean accuracy and 67% PGD l_infty-8 adversarial accuracy on the class ”automobile” but only 65% and 17% on class ”cat”. This phenomenon happens in balanced datasets and does not exist in naturally trained models when only using clean samples. In this work, we empirically and theoretically show that this phenomenon can generally happen under adversarial training algorithms which minimize DNN models’ robust errors. Motivated by these findings, we propose a Fair-Robust-Learning (FRL) framework to mitigate this unfairness problem when doing adversarial defenses and experimental results validate the effectiveness of FRL.

Graph Neural Networks (GNNs) have demonstrated their powerful capability in learning representations for graph-structured data. Consequently, they have enhanced the performance of many graph-related tasks such as node classification and graph classification. However, it is evident from recent studies that GNNs are vulnerable to adversarial attacks. Their performance can be largely impaired by deliberately adding carefully created unnoticeable perturbations to the graph. Existing attacking methods often produce perturbation by adding/deleting a few edges, which might be noticeable even when the number of modified edges is small. In this paper, we propose a graph rewiring operation to perform the attack. It can affect the graph in a less noticeable way compared to existing operations such as adding/deleting edges. We then utilize deep reinforcement learning to learn the strategy to effectively perform the rewiring operations. Experiments on real-world graphs demonstrate the effectiveness of the proposed framework. To understand the proposed framework, we further analyze how its generated perturbation impacts the target model and the advantages of the rewiring operations. The implementation of the proposed framework is available at https://github.com/alge24/ReWatt.

Graphs such as social networks and molecular graphs are ubiquitous data structures in the real world. Due to their prevalence, it is of great research importance to extract meaningful patterns from graph structured data so that downstream tasks can be facilitated. Instead of designing hand-engineered features, graph representation learning has emerged to learn representations that can encode the abundant information about the graph. It has achieved tremendous success in various tasks such as node classification, link prediction, and graph classification and has attracted increasing attention in recent years.

Discrete event sequences are ubiquitous, such as an ordered event series of process interactions in Information and Communication Technology systems. Recent years have witnessed increasing efforts in detecting anomalies with discrete event sequences. However, it remains an extremely difficult task due to several intrinsic challenges including data imbalance issues, discrete property of the events, and sequential nature of the data. To address these challenges, in this paper, we propose OC4Seq, a multi-scale one-class recurrent neural network for detecting anomalies in discrete event sequences. Specifically, OC4Seq integrates the anomaly detection objective with recurrent neural networks (RNNs) to embed the discrete event sequences into latent spaces, where anomalies can be easily detected. In addition, given that an anomalous sequence could be caused by either individual events, subsequences of events, or the whole sequence, we design a multi-scale RNN framework to capture different levels of sequential patterns simultaneously. We fully implement and evaluate OC4Seq on three real-world system log datasets. The results show that OC4Seq consistently outperforms various representative baselines by a large margin. Moreover, through both quantitative and qualitative analysis, the importance of capturing multi-scale sequential patterns for event anomaly detection is verified. To encourage reproducibility, we make the code and data publicly available.

Deep Learning models are at the core of research in Artificial Intelligence research today. A tide in research for deep learning on graphs or graph neural networks. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including computer vision, natural language processing, program synthesis and analysis, financial security, Drug Discovery, and so on. However, there are still many challenges regarding a broad range of the topics in deep learning on graphs, from methodologies to applications, and from foundations to the new frontiers of GNNs. This international workshop on "Deep Learning on Graphs: Method and Applications (DLG-KDD'21)" aims to bring together both academic researchers and industrial practitioners from different backgrounds and perspectives to the above challenges.

Deep neural networks (DNNs) have achieved unprecedented accomplishments in various machine learning tasks. However, recent studies demonstrate that DNNs are extremely vulnerable to adversarial examples. They are manually synthesized input samples which look benign but can severely fool the prediction of DNN models. For machine learning practitioners who are applying DNNs, understanding the behavior of adversarial examples will not only help them improve the safety of their models, but also can help them have deeper insights into the working mechanism of the DNNs. In this tutorial, we provide a comprehensive overview on the recent advances of adversarial examples and their countermeasures, from both practical and theoretical perspectives. From the practical aspect, we give a detailed introduction of the popular algorithms to generate adversarial examples under different adversary's goals. We also discuss how the defending strategies are developed to resist these attacks, and how new attacks come out to break these defenses. From the theoretical aspect, we discuss a series of intrinsic behaviors of robust DNNs which are different from traditional DNNs, especially about their optimization and generalization properties. Finally, we introduce DeepRobust, a Pytorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Via our tutorial, the audience can grip the main ideas of adversarial attacks and defenses and gain a deep insight of DNN's robustness. The tutorial official website is at https://sites.google.com/view/kdd21-tutorial-adv-robust.

Designing an effective loss function plays a crucial role in training deep recommender systems. Most existing works often leverage a predefined and fixed loss function that could lead to suboptimal recommendation quality and training efficiency. Some recent efforts rely on exhaustively or manually searched weights to fuse a group of candidate loss functions, which is exceptionally costly in computation and time. They also neglect the various convergence behaviors of different data examples. In this work, we propose an AutoLoss framework that can automatically and adaptively search for the appropriate loss function from a set of candidates. To be specific, we develop a novel controller network, which can dynamically adjust the loss probabilities in a differentiable manner. Unlike existing algorithms, the proposed controller can adaptively generate the loss probabilities for different data examples according to their varied convergence behaviors. Such design improves the model's generalizability and transferability between deep recommender systems and datasets. We evaluate the proposed framework on two benchmark datasets. The results show that AutoLoss outperforms representative baselines. Further experiments have been conducted to deepen our understandings of AutoLoss, including its transferability, components and training efficiency.

Graph neural networks (GNNs) have shown the power in graph representation learning for numerous tasks. In this work, we discover an interesting phenomenon that although residual connections in the message passing of GNNs help improve the performance, they immensely amplify GNNs' vulnerability against abnormal node features. This is undesirable because in real-world applications, node features in graphs could often be abnormal such as being naturally noisy or adversarially manipulated. We analyze possible reasons to understand this phenomenon and aim to design GNNs with stronger resilience to abnormal features. Our understandings motivate us to propose and derive a simple, efficient, interpretable, and adaptive message passing scheme, leading to a novel GNN with Adaptive Residual, AirGNN. Extensive experiments under various abnormal feature scenarios demonstrate the effectiveness of the proposed algorithm.

Meta learning algorithms have been widely applied in many tasks for efficient learning, such as few-shot image classification and fast reinforcement learning. During meta training, the meta learner develops a common learning strategy, or experience, from a variety of learning tasks. Therefore, during meta test, the meta learner can use the learned strategy to quickly adapt to new tasks even with a few training samples. However, there is still a dark side about meta learning in terms of reliability and robustness. In particular, is meta learning vulnerable to adversarial attacks? In other words, would a well-trained meta learner utilize its learned experience to build wrong or likely useless knowledge, if an adversary unnoticeably manipulates the given training set? Without the understanding of this problem, it is extremely risky to apply meta learning in safety-critical applications. Thus, in this paper, we perform the initial study about adversarial attacks on meta learning under the few-shot classification problem. In particular, we formally define key elements of adversarial attacks unique to meta learning and propose the first attacking algorithm against meta learning under various settings. We evaluate the effectiveness of the proposed attacking strategy as well as the robustness of several representative meta learning algorithms. Experimental results demonstrate that the proposed attacking strategy can easily break the meta learner and meta learning is vulnerable to adversarial attacks.

Graph Neural Networks (GNNs) have achieved tremendous success in various real-world applications due to their strong ability in graph representation learning. GNNs explore the graph structure and node features by aggregating and transforming information within node neighborhoods. However, through theoretical and empirical analysis, we reveal that the aggregation process of GNNs tends to destroy node similarity in the original feature space. There are many scenarios where node similarity plays a crucial role. Thus, it has motivated the proposed framework SimP-GCN that can effectively and efficiently preserve node similarity while exploiting graph structure. Specifically, to balance information from graph structure and node features, we propose a feature similarity preserving aggregation which adaptively integrates graph structure and node features. Furthermore, we employ self-supervised learning to explicitly capture the complex feature similarity and dissimilarity relations between nodes. We validate the effectiveness of SimP-GCN on seven benchmark datasets including three assortative and four disassorative graphs. The results demonstrate that SimP-GCN outperforms representative baselines. Further probe shows various advantages of the proposed framework. The implementation of SimP-GCN is available at https://github.com/ChandlerBang/SimP-GCN.

Practical large-scale recommender systems usually contain thousands of feature fields from users, items, contextual information, and their interactions. Most of them empirically allocate a unified dimension to all feature fields, which is memory inefficient. Thus it is highly desired to assign various embedding dimensions to different feature fields according to their importance and predictability. Due to the large amounts of feature fields and the nuanced relationship between embedding dimensions with feature distributions and neural network architectures, manually allocating embedding dimensions in practical recommender systems can be challenging. To this end, we propose an AutoML-based framework (AutoDim) in this paper, which can automatically select dimensions for different feature fields in a data-driven fashion. Specifically, we first proposed an end-to-end differentiable framework that can calculate the weights over various dimensions in a soft and continuous manner for feature fields, and an AutoML-based optimization algorithm; then, we derive a hard and discrete embedding component architecture according to the maximal weights and retrain the whole recommender framework. We conduct extensive experiments on benchmark datasets to validate the effectiveness of AutoDim.

With the recent advances in Reinforcement Learning (RL), there have been tremendous interests in employing RL for recommender systems. However, directly training and evaluating a new RL-based recommendation algorithm needs to collect users’ real-time feedback in the real system, which is time/effort consuming and could negatively impact users’ experiences. Thus, it calls for a user simulator that can mimic real users’ behaviors to pre-train and evaluate new recommendation algorithms. Simulating users’ behaviors in a dynamic system faces immense challenges – (i) the underlying item distribution is complex, and (ii) historical logs for each user are limited. In this paper, we develop a user simulator based on a Generative Adversarial Network (GAN). To be specific, the generator captures the underlying distribution of users’ historical logs and generates realistic logs that can be considered as augmentations of real logs; while the discriminator not only distinguishes real and fake logs but also predicts users’ behaviors. The experimental results based on benchmark datasets demonstrate the effectiveness of the proposed simulator.

The failure of landing a job for college students could cause serious social consequences such as drunkenness and suicide. In addition to academic performance, unconscious biases can become one key obstacle for hunting jobs for graduating students. Thus, it is necessary to understand these unconscious biases so that we can help these students at an early stage with more personalized intervention. In this paper, we develop a framework, i.e., MAYA (Multi-mAjor emploYment stAtus) to predict students' employment status while considering biases. The framework consists of four major components. Firstly, we solve the heterogeneity of student courses by embedding academic performance into a unified space. Then, we apply a generative adversarial network (GAN) to overcome the class imbalance problem. Thirdly, we adopt Long Short-Term Memory (LSTM) with a novel dropout mechanism to comprehensively capture sequential information among semesters. Finally, we design a bias-based regularization to capture the job market biases. We conduct extensive experiments on a large-scale educational dataset and the results demonstrate the effectiveness of our prediction framework.

Robust language processing systems are becoming increasingly important given the recent awareness of dangerous situations where brittle machine learning models can be easily broken with the presence of noises. In this paper, we introduce a robust word recognition framework that captures multi-level sequential dependencies in noised sentences. The proposed framework employs a sequence-to-sequence model over characters of each word, whose output is given to a word-level bi-directional recurrent neural network. We conduct extensive experiments to verify the effectiveness of the framework. The results show that the proposed framework outperforms state-of-the-art methods by a large margin and they also suggest that character-level dependencies can play an important role in word recognition. The code of the proposed framework and the major experiments are publicly available1.

Large-scale machine learning models are often trained by parallel stochastic gradient descent algorithms. However, the communication cost of gradient aggregation and model synchronization between the master and worker nodes becomes the major obstacle for efficient learning as the number of workers and the dimension of the model increase. In this paper, we propose DORE, a DOuble REsidual compression stochastic gradient descent algorithm, to reduce over $95%$ of the overall communication such that the obstacle can be immensely mitigated. Our theoretical analyses demonstrate that the proposed strategy has superior convergence properties for both strongly convex and nonconvex objective functions. The experimental results validate that DORE achieves the best communication efficiency while maintaining similar model accuracy and convergence speed in comparison with start-of-the-art baselines.

Graph Convolutional Networks (GCNs) show promising results for semi-supervised learning tasks on graphs, thus become favorable comparing with other approaches. Despite the remarkable success of GCNs, it is difficult to train GCNs with insufficient supervision. When labeled data are limited, the performance of GCNs becomes unsatisfying for low-degree nodes. While some prior work analyze successes and failures of GCNs on the entire model level, profiling GCNs on individual node level is still underexplored.

With the recent prevalence of Reinforcement Learning (RL), there have been tremendous interests in developing RL-based recommender systems. In practical recommendation sessions, users will sequentially access multiple scenarios, such as the entrance pages and the item detail pages, and each scenario has its specific characteristics. However, the majority of existing RL-based recommender systems focus on optimizing one strategy for all scenarios or separately optimizing each strategy, which could lead to sub-optimal overall performance. In this paper, we study the recommendation problem with multiple (consecutive) scenarios, i.e., whole-chain recommendations. We propose a multi-agent RL-based approach (DeepChain), which can capture the sequential correlation among different scenarios and jointly optimize multiple recommendation strategies. To be specific, all recommender agents (RAs) share the same memory of users' historical behaviors, and they work collaboratively to maximize the overall reward of a session. Note that optimizing multiple recommendation strategies jointly faces two challenges in the existing model-free RL model - (i) it requires huge amounts of user behavior data, and (ii) the distribution of reward (users' feedback) are extremely unbalanced. In this paper, we introduce model-based RL techniques to reduce the training data requirement and execute more accurate strategy updates. The experimental results based on a real e-commerce platform demonstrate the effectiveness of the proposed framework.

Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in realworld applications such as computer vision and recommendations.For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as "gorillas".As one crucial application of AI, dialogue systems have been extensively applied in our society.They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world.However, the fairness of dialogue systems has not been well investigated.In this paper, we perform a pioneering study about the fairness issues in dialogue systems.In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models.Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races.Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods.Experiments show that our methods can reduce the bias in dialogue systems significantly.The dataset and the implementation are released to foster fairness research in dialogue systems 1 .

The automatic feedback of school assignments is an important application of AI in education.In this work, we focus on the task of personalized multimodal feedback generation, which aims to generate personalized feedback for teachers to evaluate students' assignments involving multimodal inputs such as images, audios, and texts.This task involves the representation and fusion of multimodal information and natural language generation, which presents the challenges from three aspects: (1) how to encode and integrate multimodal inputs; (2) how to generate feedback specific to each modality; and (3) how to fulfill personalized feedback generation.In this paper, we propose a novel Personalized Multimodal Feedback Generation Network (PMFGN) armed with a modality gate mechanism and a personalized bias mechanism to address these challenges.Extensive experiments on real-world K-12 education data show that our model significantly outperforms baselines by generating more accurate and diverse feedback.In addition, detailed ablation experiments are conducted to deepen our understanding of the proposed framework.

Dialogue systems play an increasingly important role in various aspects of our daily life.It is evident from recent research that dialogue systems trained on human conversation data are biased.In particular, they can produce responses that reflect people's gender prejudice.Many debiasing methods have been developed for various NLP tasks, such as word embedding.However, they are not directly applicable to dialogue systems because they are likely to force dialogue models to generate similar responses for different genders.This greatly degrades the diversity of the generated responses and immensely hurts the performance of the dialogue models.In this paper, we propose a novel adversarial learning framework Debiased-Chat to train dialogue models free from gender bias while keeping their performance.Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.The implementation of the proposed framework is released 1 .

Graph Neural Networks (GNNs), which extend deep neural networks to graph-structured data, have attracted increasing attention. They have been proven to be powerful for numerous graph related tasks such as graph classification, link prediction, and node classification. To adapt GNNs to graph classification, recent works aim to learn graph-level representation through a hierarchical pooling procedure. One major direction is to select important nodes to hierarchically coarsen the input graph and gradually reduce the information into the graph representation. However, most of the existing methods only select important nodes, which can be redundant and cannot represent the original graph well. Meanwhile, the information of non-selected nodes is often overlooked when generating a new coarser graph, which may lead to the tremendous loss of important structural and node feature information. In this paper, we propose a novel pooling operator RepPool to learn hierarchical graph representations. Specifically, we introduce the concept of representativeness that is combined with the importance for node selection and we provide a learnable way to integrate non-selected nodes. By combining the RepPool operator with conventional GCN convolutional layers, a hierarchical graph classification architecture is developed. Extensive experiments on various public benchmarks have demonstrated the effectiveness of the proposed method. The implementation of the proposed framework is available.

Positive and unlabeled (PU) learning aims to obtain a well-performed classifier via an incomplete binary training set, in which only a part of labels of one category is known while the rest are unknown. However, in many real-world applications such as image recognition, the collected data samples often involve more than two categories. Moreover, only a small portion of the collected samples might have associated labels due to some practical reasons, and these labeled samples cannot always cover all the categories. We refer to this type of data as incomplete labeled data. In this paper, we first formally define the incomplete labeled data learning problem and then aim to tackle it via adversarial data generation. Specifically, we propose a novel generative framework LILA, which can produce synthetic labeled samples for both partially labeled categories and unlabeled categories. To enforce that the generated samples for unlabeled categories can associate with correct labels, we integrate two active learning processes into the LILA framework for selecting unlabeled samples in the collected sample set to query their labels effectively. After LILA has been well trained, a classifier can be trained on the balanced augmented data set consisting of both generated and original labeled samples. Extensive experiments on real image data demonstrate the effectiveness of our proposed framework. We release the implementation of the proposed framework via https://github.com/wentao-repo/LILA.

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. However, recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. Adversarial attacks can easily fool GNNs in making predictions for downstream tasks. The vulnerability to adversarial attacks has raised increasing concerns for applying GNNs in safety-critical applications. Therefore, developing robust algorithms to defend adversarial attacks is of great significance. A natural idea to defend adversarial attacks is to clean the perturbed graph. It is evident that real-world graphs share some intrinsic properties. For example, many real-world graphs are low-rank and sparse, and the features of two adjacent nodes tend to be similar. In fact, we find that adversarial attacks are likely to violate these graph properties. Therefore, in this paper, we explore these properties to defend adversarial attacks on graphs. In particular, we propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model from the perturbed graph guided by these properties. Extensive experiments on real-world graphs demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art defense methods, even when the graph is heavily perturbed. We release the implementation of Pro-GNN to our DeepRobust repository for adversarial attacks and defenses. The specific experimental settings to reproduce our results can be found in https://github.com/ChandlerBang/Pro-GNN.

Recently we have seen a rapid rise in the amount of education data available through the digitization of education. This huge amount of education data usually exhibits in a mixture form of images, videos, speech, texts, etc. It is crucial to consider data from different modalities to build successful applications in AI in education (AIED). This tutorial targets AI researchers and practitioners who are interested in applying state-of-the-art multimodal machine learning techniques to tackle some of the hard-core AIED tasks. These include tasks such as automatic short answer grading, student assessment, class quality assurance, knowledge tracing, etc.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples leaves us a big hesitation when applying DNN models on safety-critical tasks such as autonomous vehicles and malware detection. These adversarial examples are intentionally crafted instances, either appearing in the train or test phase, which can fool the DNN models to make severe mistakes. Therefore, people are dedicated to devising more robust models to resist adversarial examples, but usually they are broken by new stronger attacks. This arms-race between adversarial attacks and defenses has been drawn increasing attention in recent years. In this tutorial, we provide a comprehensive overview on the frontiers and advances of adversarial attacks and their countermeasures. In particular, we give a detailed introduction of different types of attacks under different scenarios, including evasion and poisoning attacks, white-box and black box attacks. We will also discuss how the defending strategies develop to compete against these attacks, and how new attacks come out to break these defenses. Moreover, we will discuss the story of adversarial attacks and defenses in other data domains, especially in graph structured data. Then, we introduce DeepRobust, a Pytorch adversarial learning library which aims to build a comprehensive and easy-to-use platform to foster this research field. Finally, we summarize the tutorial with discussions on open issues and challenges about adversarial attacks and defenses. Via our tutorial, our audience can grip the main idea and key approaches of the game between adversarial attacks and defenses.

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack human intelligible explanations. Thus, they cannot be fully trusted and used in certain application domains if GNN models cannot be explained. In this work, we propose a novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach can provide high-level insights and generic understanding of how GNNs work. In particular, we propose to explain GNNs by training a graph generator so that the generated graph patterns maximize a certain prediction of the model. We formulate the graph generation as a reinforcement learning task, where for each step, the graph generator predicts how to add an edge into the current graph. The graph generator is trained via a policy gradient method based on information from the trained GNNs. In addition, we incorporate several graph rules to encourage the generated graphs to be valid. Experimental results on both synthetic and real-world datasets show that our proposed methods help understand and verify the trained GNNs. Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.

Online recommendation and advertising are two major income channels for online recommendation platforms (e.g. e-commerce and news feed site). However, most platforms optimize recommending and advertising strategies by different teams separately via different techniques, which may lead to suboptimal overall performances. To this end, in this paper, we propose a novel two-level reinforcement learning framework to jointly optimize the recommending and advertising strategies, where the first level generates a list of recommendations to optimize user experience in the long run; then the second level inserts ads into the recommendation list that can balance the immediate advertising revenue from advertisers and the negative influence of ads on long-term user experience. To be specific, the first level tackles high combinatorial action space problem that selects a subset items from the large item space; while the second level determines three internally related tasks, i.e., (i) whether to insert an ad, and if yes, (ii) the optimal ad and (iii) the optimal location to insert. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework. We have released the implementation code to ease reproductivity.

Increasingly many teachers are turning to online social media to supplement educational resources and meet students' needs in the classrooms. The diffusion of information from online social media to the classroom is significantly faster than traditional curriculum-based approaches. However, this is contingent upon how well teachers across an online social media network are connected. To understand this, we perform a thorough and large-scale investigation of teacher connections in online social media, which is lacking in the literature. To make this feasible, we construct a large dataset of teachers on Pinterest, an image-based popular online social media. Our dataset includes 540 teachers across 5 states and 48 districts, thousands of connections they have established (either with their peers or some other Pinterest users), and all the resources they have shared in their accounts. Then, taking into account some crucial teacher-related attributes (e.g., their districts, grade levels, etc), we characterize direct and indirect teacher connections. Moreover, we compare the physical (face to face) and virtual (Pinterest) network of our surveyed teachers using several graph-related metrics. The finding in this study can serve as a basis to investigate teachers on social media in a deeper manner.

Canonical Correlation Analysis (CCA) aims to learn the linear projections of two sets of variables where they are correlated maximally, which is not optimal for variables with non-linear relations. Recent years have witnessed great efforts in developing deep neural networks based CCA models, which are able to learn flexible non-linear and highly correlated representations between two variables. In addition to learning representations, generating realistic multi-view samples is also becoming highly desired in many real-world applications. However, the majority of existing CCA models do not provide mechanisms for realistic samples generation. Meanwhile, adversarial learning techniques such as generative adversarial networks have been proven to be effective in generating realistic samples similar to real data distribution. Thus, incorporating adversarial learning techniques has a great potential to advance Canonical Correlation Analysis. In this paper, we harness the power of adversarial learning techniques to equip Canonical Correlation Analysis with the ability of realistic data generation. In particular, we propose a Deep Adversarial Canonical Correlation Analysis model (DACCA), which can simultaneously learn representation of multi-view data but also generate realistic multi-view samples. Comprehensive experiments have been conducted on three real-world datasets and the results demonstrate the effectiveness of the proposed model. Our code is available at https://github.com/wenqifan03/DACCA.

In many real-world classification applications such as fake news detection, the training data can be extremely imbalanced, which brings challenges to existing classifiers as the majority classes dominate the loss functions of classifiers. Oversampling techniques such as SMOTE are effective approaches to tackle the class imbalance problem by producing more synthetic minority samples. Despite their success, the majority of existing oversampling methods only consider local data distributions when generating minority samples, which can result in noisy minority samples that do not fit global data distributions or interleave with majority classes. Hence, in this paper, we study the class imbalance problem by simultaneously exploring local and global data information since: (i) the local data distribution could give detailed information for generating minority samples; and (ii) the global data distribution could provide guidance to avoid generating outliers or samples that interleave with majority classes. Specifically, we propose a novel framework GL-GAN, which leverages the SMOTE method to explore local distribution in a learned latent space and employs GAN to capture the global information, so that synthetic minority samples can be generated under even extremely imbalanced scenarios. Experimental results on diverse real data sets demonstrate the effectiveness of our GL-GAN framework in producing realistic and discriminative minority samples for improving the classification performance of various classifiers on imbalanced training data. Our code is available at https://github.com/wentao-repo/GL-GAN.

Graphs are used to model pairwise relations between entities in many real-world scenarios such as social networks. Graph Neural Networks(GNNs) have shown their superior ability in learning representations for graph structured data, which leads to performance improvements in many graph related tasks such as link prediction, node classification and graph classification. Most of the existing graph neural networks models are designed for static graphs while many real-world graphs are inherently dynamic with new nodes and edges constantly emerging. Existing graph neural network models cannot utilize the dynamic information, which has been shown to enhance the performance of many graph analytic tasks such as community detection. Hence, in this paper, we propose DyGNN, a Dynamic Graph Neural Network model, which can model the dynamic information as the graph evolving. In particular, the proposed framework keeps updating node information by capturing the sequential information of edges (interactions), the time intervals between edges and information propagation coherently. Experimental results on various dynamic graphs demonstrate the effectiveness of the proposed framework.

Deep recommender systems have achieved promising performance on real-world recommendation tasks. They typically represent users and items in a low-dimensional embedding space and then feed the embeddings into the following deep network structures for prediction. Traditional deep recommender models often adopt uniform and fixed embedding sizes for all the users and items. However, such design is not optimal in terms of not only the recommendation performance and but also the space complexity. In this paper, we propose to dynamically search the embedding sizes for different users and items and introduce a novel embedding size adjustment policy network (ESAPN). ESAPN serves as an automated reinforcement learning agent to adaptively search appropriate embedding sizes for users and items. Different from existing works, our model performs hard selection on different embedding sizes, which leads to a more accurate selection and decreases the storage space. We evaluate our model under the streaming setting on two real-world benchmark datasets. The results show that our proposed framework outperforms representative baselines. Moreover, our framework is demonstrated to be robust to the cold-start problem and reduce memory consumption by around 40%-90%. The implementation of the model is released.

A growing trend recently is to harness the structure of today's big data, where much of the data can be represented as graphs. Simultaneously, graph convolutional networks (GCNs) have been proposed and since seen rapid development. More recently, due to the scalability issues that arise when attempting to utilize these powerful models on real-world data, methodologies have sought the use of sampling techniques. More specifically, minibatches of nodes are formed and then sets of nodes are sampled to aggregate from in one or more layers. Among these methods, the two prominent ways are based on sampling nodes from either a local or global perspective. In this work, we first observe the similarities in the two sampling strategies to that of epidemic and diffusion network models. Then we harness this understanding to fuse together the benefits of sampling from both a local and global perspective while alleviating some of the inherent issues found in both through the use of a low-dimensional approximation for the path-based Katz similarity measure. Our proposed framework, Epidemic Graph Convolutional Network (EGCN), is thus able to achieve improved performance over sampling from just one of the two perspectives alone. Empirical experiments are performed on several public benchmark datasets to verify the effectiveness over existing methodologies for the node classification task and we furthermore present some empirical parameter analysis of EGCN.

One crucial aspect that yet remains fairly unknown while can inform us about the behavior of deep neural networks is their decision boundaries. Trust can be improved once we understand how and why deep models carve out a particular form of decision boundary and thus make particular decisions. Robustness against adversarial examples is directly related to the decision boundary as adversarial examples are basically 'missed out' by the decision boundary between two classes. Investigating the decision boundary of deep neural networks, nevertheless, faces tremendous challenges. First, how we can generate instances near the decision boundary that are similar to real samples? Second, how we can leverage near decision boundary instances to characterize the behaviour of deep neural networks? Motivated to solve these challenges, we focus on investigating the decision boundary of deep neural network classifiers. In particular, we propose a novel approach to generate instances near decision boundary of pre-trained DNNs and then leverage these instances to characterize the behaviour of deep models.

In real-world networks, nodes might have more than one type of relationship. Signed networks are an important class of such networks consisting of two types of relations: positive and negative. Recently, embedding signed networks has attracted increasing attention and is more challenging than classic networks since nodes are connected by paths with multi-types of links. Existing works capture the complex relationships by relying on social theories. However, this approach has major drawbacks, including the incompleteness/inaccurateness of such theories. Thus, we propose network transformation based embedding to address these shortcomings. The core idea is that rather than directly finding the similarities of two nodes from the complex paths connecting them, we can obtain their similarities through simple paths connecting their different roles. We employ this idea to build our proposed embedding technique that can be described in three steps: (1) the input directed signed network is transformed into an unsigned bipartite network with each node mapped to a set of nodes we denote as role-nodes. Each role-node captures a certain role that a node in the original network plays; (2) the network of role-nodes is embedded; and (3) the original network is encoded by aggregating the embedding vectors of role-nodes. Our experiments show the novel proposed technique substantially outperforms existing models.

Traffic flow analysis, prediction and management are keystones for building smart cities in the new era. With the help of deep neural networks and big traffic data, we can better understand the latent patterns hidden in the complex transportation networks. The dynamic of the traffic flow on one road not only depends on the sequential patterns in the temporal dimension but also relies on other roads in the spatial dimension. Although there are existing works on predicting the future traffic flow, the majority of them have certain limitations on modeling spatial and temporal dependencies. In this paper, we propose a novel spatial temporal graph neural network for traffic flow prediction, which can comprehensively capture spatial and temporal patterns. In particular, the framework offers a learnable positional attention mechanism to effectively aggregate information from adjacent roads. Meanwhile, it provides a sequential component to model the traffic flow dynamics which can exploit both local and global temporal dependencies. Experimental results on various real traffic datasets demonstrate the effectiveness of the proposed framework.

Many real-world relations can be represented by signed networks with positive links (e.g., friendships and trust) and negative links (e.g., foes and distrust). Link prediction helps advance tasks in social network analysis such as recommendation systems. Most existing work on link analysis focuses on unsigned social networks. The existence of negative links piques research interests in investigating whether properties and principles of signed networks differ from those of unsigned networks and mandates dedicated efforts on link analysis for signed social networks. Recent findings suggest that properties of signed networks substantially differ from those of unsigned networks and negative links can be of significant help in signed link analysis in complementary ways. In this article, we center our discussion on a challenging problem ofsigned link analysis. Signed link analysis faces the problem of data sparsity, i.e., only a small percentage of signed links are given. This problem can even get worse when negative links are much sparser than positive ones as users are inclined more toward positive disposition rather than negative. We investigate how we can take advantage of other sources of information for signed link analysis. This research is mainly guided by three social science theories,Emotional Information,Diffusion of Innovations, andIndividual Personality. Guided by these, we extract three categories of related features and leverage them for signed link analysis. Experiments show the significance of the features gleaned from social theories for signed link prediction and addressing the data sparsity challenge.

In recent times we have seen a trend of having the ideologies of the two dominant political parties in the U.S. growing further and further apart. Simultaneously we have entered the age of big data raising enormous interest in computational approaches to solve problems in many domains such as political elections. However, an overlooked problem lies in predicting what happens once our elected officials take office, more specifically, predicting the congressional votes, which are perhaps the most influential decisions being made in the U.S. This, nevertheless, is far from a trivial task, since the congressional system is highly complex and heavily influenced by both ideological and social factors. Thus, dedicated efforts are required to first effectively identify and represent these factors, then furthermore capture the interactions between them. To this end, we proposed a robust end-to-end framework Multi-Factor Congressional Vote Prediction (MFCVP) that defines and encodes features from indicative ideological factors while also extracting novel social features. This allows for a principled expressive representation of the complex system, which ultimately leads to MFCVP making accurate vote predictions. Experimental results on a dataset from the U.S. House of Representatives shows the superiority of MFCVP to several representatives approaches when predicting votes for individual representatives and also the overall outcome of the bill voted on. Finally, we perform a factor analysis to understand the effectiveness and interplay between the different factors.

A large portion of today's big data can be represented as networks. However, not all networks are the same, and in fact, for many that have additional complexities to their structure, traditional general network analysis methods are no longer applicable. For example, signed networks contain both positive and negative links, and thus dedicated theories and algorithms have been developed. However, previous work mainly focuses on the unipartite setting where signed links connect any pair of nodes. Signed bipartite networks on the one hand, are commonly found, but have primarily been overlooked. Their complexities of having two node types where signed links can only form across the two sets introduce challenges that prevent most existing literature on unipartite signed and unsigned bipartite networks from being applied. On the other hand, balance theory, a key signed social theory, has been generally defined for cycles of any length and is being used in the form of triangles for numerous unipartite signed network tasks. However, in bipartite networks there are no triangles and furthermore there exist two types of nodes. Therefore, in this work, we conduct the first comprehensive analysis and validation of balance theory using the smallest cycle in signed bipartite networks - signed butterflies (i.e., cycles of length 4 containing the two node types). Then, to investigate the applicability of balance theory aiding signed bipartite network tasks, we develop multiple sign prediction methods that utilize balance theory in the form of signed butterflies. Our sign prediction experiment on three real-world signed bipartite networks demonstrates the effectiveness of using these signed butterflies for not only sign prediction, but paves the way for improvements in other signed bipartite network analysis tasks.

Learning representation has been proven to be helpful in numerous machine learning tasks. The success of the majority of existing representation learning approaches often requires a large amount of consistent and noise-free labels. However, labels are not accessible in many real-world scenarios and they are usually annotated by the crowds. In practice, the crowdsourced labels are usually inconsistent among crowd workers given their diverse expertise and the number of crowdsourced labels is very limited. Thus, directly adopting crowdsourced labels for existing representation learning algorithms is inappropriate and suboptimal. In this paper, we investigate the above problem and propose a novel framework of Representation Learning with crowdsourced Labels, i.e., "RLL", which learns representation of data with crowdsourced labels by jointly and coherently solving the challenges introduced by limited and inconsistent labels. The proposed representation learning framework is evaluated in two real-world education applications. The experimental results demonstrate the benefits of our approach on learning representation from limited labeled data from the crowds, and show RLL is able to outperform state-of-the-art baselines. Moreover, detailed experiments are conducted on RLL to fully understand its key components and the corresponding performance.

Recent years have witnessed rapid developments on social recommendation techniques for improving the performance of recommender systems due to the growing influence of social networks to our daily life. The majority of existing social recommendation methods unify user representation for the user-item interactions (item domain) and user-user connections (social domain). However, it may restrain user representation learning in each respective domain, since users behave and interact differently in the two domains, which makes their representations to be heterogeneous. In addition, most of traditional recommender systems can not efficiently optimize these objectives, since they utilize negative sampling technique which is unable to provide enough informative guidance towards the training during the optimization process. In this paper, to address the aforementioned challenges, we propose a novel deep adversarial social recommendation framework DASO. It adopts a bidirectional mapping method to transfer users' information between social domain and item domain using adversarial learning. Comprehensive experiments on two real-world datasets show the effectiveness of the proposed framework.

Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks such as node classification and link prediction. To apply graph neural networks for the graph classification task, approaches to generate thegraph representation from node representations are demanded. A common way is to globally combine the node representations. However, rich structural information is overlooked. Thus a hierarchical pooling procedure is desired to preserve the graph structure during the graph representation learning. There are some recent works on hierarchically learning graph representation analogous to the pooling step in conventional convolutional neural (CNN) networks. However, the local structural information is still largely neglected during the pooling process. In this paper, we introduce a pooling operator $\pooling$ based on graph Fourier transform, which can utilize the node features and local structures during the pooling process. We then design pooling layers based on the pooling operator, which are further combined with traditional GCN convolutional layers to form a graph neural network framework $\m$ for graph classification. Theoretical analysis is provided to understand $\pooling$ from both local and global perspectives. Experimental results of the graph classification task on $6$ commonly used benchmarks demonstrate the effectiveness of the proposed framework.

Recommender systems are crucial to alleviate the information overload problem in online worlds. Most of the modern recommender systems capture users' preference towards items via their interactions based on collaborative filtering techniques. In addition to the user-item interactions, social networks can also provide useful information to understand users' preference as suggested by the social theories such as homophily and influence. Recently, deep neural networks have been utilized for social recommendations, which facilitate both the user-item interactions and the social network information. However, most of these models cannot take full advantage of the social network information. They only use information from direct neighbors, but distant neighbors can also provide helpful information. Meanwhile, most of these models treat neighbors' information equally without considering the specific recommendations. However, for a specific recommendation case, the information relevant to the specific item would be helpful. Besides, most of these models do not explicitly capture the neighbor's opinions to items for social recommendations, while different opinions could affect the user differently. In this paper, to address the aforementioned challenges, we propose DSCF, a Deep Social Collaborative Filtering framework, which can exploit the social relations with various aspects for recommender systems. Comprehensive experiments on two-real world datasets show the effectiveness of the proposed framework.

Convolutional neural networks (CNNs) leverage the great power in representation learning on regular grid data such as image and video. Recently, increasing attention has been paid on generalizing CNNs to graph or network data which is highly irregular. Some focus on graph-level representation learning while others aim to learn node-level representations. These methods have been shown to boost the performance of many graph-level tasks such as graph classification and node-level tasks such as node classification. Most of these methods have been designed for single-dimensional graphs where a pair of nodes can only be connected by one type of relation. However, many real-world graphs have multiple types of relations and they can be naturally modeled as multi-dimensional graphs with each type of relation as a dimension. Multi-dimensional graphs bring about richer interactions between dimensions, which poses tremendous challenges to the graph convolutional neural networks designed for single-dimensional graphs. In this paper, we study the problem of graph convolutional networks for multidimensional graphs and propose a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations for multi-dimensional graphs. Comprehensive experiments on real-world multi-dimensional graphs demonstrate the effectiveness of the proposed framework.

To employ millimeter wave technology in the 5G standard, two inherent challenges need to be addressed in dynamic outdoor environments. Firstly, different types of obstacles can easily block the links. Secondly, the link quality can drop significantly in a mobile environment. It is critical to discriminate between the two different situations to take appropriate actions. The existing work to make the distinction is based on RSSI variation measured in a time window, which is very time-consuming leading to large volume of data loss in order to achieve high accuracy. In this paper, we propose a learning-based prediction framework to classify link blockage and link movement efficiently and quickly. A classifier is trained with data blockage instances using different learning methods and is used to make a prediction based on diffraction values on different multipath components formed around a receiver. The simulations show that the prediction framework can predict blockage with close to 90% accuracy. The prediction framework will eliminate the need for having time-consuming methods to discriminate between link movement and link blockage. Experiments show that our framework does not need large amount of training data to get to the desired prediction accuracy.

In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information and topological structure, have been demonstrated to be powerful in learning on graph data. These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key. However, building social recommender systems based on GNNs faces challenges. For example, the user-item graph encodes both interactions and their associated opinions; social relations have heterogeneous strengths; users involve in two graphs (e.g., the user-user social graph and the user-item graph). To address the three aforementioned challenges simultaneously, in this paper, we present a novel graph neural network framework (GraphRec) for social recommendations. In particular, we provide a principled approach to jointly capture interactions and opinions in the user-item graph and propose the framework GraphRec, which coherently models two graphs and heterogeneous strengths. Extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed framework GraphRec.

In modern recommender systems, both users and items are associated with rich side information, which can help understand users and items. Such information is typically heterogeneous and can be roughly categorized into flat and hierarchical side information. While side information has been proved to be valuable, the majority of existing systems have exploited either only flat side information or only hierarchical side information due to the challenges brought by the heterogeneity. In this paper, we investigate the problem of exploiting heterogeneous side information for recommendations. Specifically, we propose a novel framework jointly captures flat and hierarchical side information with mathematical coherence. We demonstrate the effectiveness of the proposed framework via extensive experiments on various real-world datasets. Empirical results show that our approach is able to lead a significant performance gain over the state-of-the-art methods.

Networks such as social networks, airplane networks, and citation networks are ubiquitous. To apply advanced machine learning algorithms to network data, low-dimensional and continuous representations are desired. To achieve this goal, many network embedding methods have been proposed recently. The majority of existing methods facilitate the local information i.e. local connections between nodes, to learn the representations, while neglecting global information (or node status), which has been proven to boost numerous network mining tasks such as link prediction and social recommendation. In this paper, we study the problem of preserving local and global information for network embedding. In particular, we introduce an approach to capture global information and propose a network embedding framework LOG, which can coherently model LOcal and Global information. Experiments demonstrate the effectiveness of the proposed framework.

Social media has been widely adopted by online users to share their opinions. Among users in signed networks, two types of opinions can be expressed. They can directly specify opinions to others via establishing positive or negative links; and they also can give opinions to content generated by others via a variety of social interactions such as commenting and rating. Intuitively these two types of opinions should be related. For example, users are likely to give positive (or negative) opinions to content from those with positive (or negative) links; and users tend to create positive (or negative) links with those that they frequently positively (or negatively) interact with. Therefore we can leverage one type of opinions to power the other. Meanwhile, they can enrich each other that can help mitigate the data sparsity and cold-start problems in the corresponding predictive tasks - link and interaction polarity predictions, respectively. In this paper, we investigate the problem of joint link and interaction polarity predictions in signed networks. We first understand the correlation between these two types of opinions; and then propose a framework that can predict signed links and the polarities of interactions simultaneously. The experimental results on a real-world signed network demonstrate the effectiveness of the proposed framework.

Social media, e.g. Twitter, has become a widely used medium for the exchange of information, but it has also become a valuable tool for hackers to spread misinformation through compromised accounts. Hence, detecting compromised accounts is a necessary step toward a safe and secure social media environment. Nevertheless, detecting compromised accounts faces several challenges. First, social media activities of users are temporally correlated which plays an important role in compromised account detection. Second, data associated with social media accounts is inherently sparse. Finally, social contagions where multiple accounts become compromised, take advantage of the user connectivity to propagate their attack. Thus how to represent each user's network features for compromised account detection is an additional challenge. To address these challenges, we propose an End-to-End Compromised Account Detection framework (E2ECAD). E2ECAD effectively captures temporal correlations via an LSTM (Long Short-Term Memory) network. Further, it addresses the sparsity problem by defining and employing a user context representation. Meanwhile, informative network-related features are modeled efficiently. To verify the working of the framework, we construct a real-world dataset of compromised accounts on Twitter and conduct extensive experiments. The results of experiments show that E2ECAD outperforms the state of the art compromised account detection algorithms.

Mobile Applications (or Apps) are becoming more and more popular in recent years, which has attracted increasing attention on mobile App recommendations. The majority of existing App recommendation algorithms focus on mining App functionality or user usage data for discovering user preferences; while actions taken by a user when he/she decides to download an App or not are ignored. In realistic scenarios, a user will first view the description of the App and then decide if he/she wants to download it or not. The actions such as viewing or downloading provide rich information about users' preferences and tastes for Apps, which have great potentials to advance App recommendations. However, the work on exploring action data for App recommendations is rather limited. Therefore, in this paper we study the novel problem of exploiting user actions for App recommendations. We propose a new framework ActionRank, which simultaneously captures various signals from user actions for App recommendations. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework.

Social media has become a valuable tool for hackers to disseminate misleading content through compromised accounts. Detecting compromised accounts, however, is challenging due to the noisy nature of social media posts and the difficulty in acquiring sufficient labeled data that can effectively capture a wide variety of compromised tweets from different types of hackers (spammers, vandals, cybercriminals, revenge hackers, etc). To address these challenges, this proposal presents a multiview learning framework that employs nonlinear autoencoders to learn the feature embedding from multiple views, such as the tweets' content, source, location, and timing information and then projects the embedded features into a common lower-rank feature representation. Suspicious user accounts are detected based on their reconstruction errors in the shared subspace. Our empirical results show the superiority of CADET compared to several existing representative approaches when applied to a realworld Twitter dataset.

There are various real-world applications such as video ads, airport screenings, courtroom trials, and job interviews where deception detection can play a crucial role. Hence, there are immense demands on deception detection in videos. However, videos are inherently complex; moreover, they lack detective labels in many real-world applications, which poses tremendous challenges to traditional deception detection methods. In this paper, we study the problem of deception detection in videos. In particular, we provide a principled way to capture rich information into a coherent model and propose an end-to-end framework DEV to detect DEceptive Videos automatically, which is robust to the small number of training data. Experimental results on real-world videos demonstrate the effectiveness of the proposed framework and further experiments are conducted to understand important factors of deception detection in videos.

The modeling of networks, specifically generative models, has been shown to provide a plethora of information about the underlying network structures, as well as many other benefits behind their construction. There has been a considerable increase in interest for the better understanding and modeling of networks, and the vast majority of existing work has been for unsigned networks. However, many networks can have positive and negative links (or signed networks), especially in online social media. It is evident from recent work that signed networks present unique properties and principles from unsigned networks due to the added complexity, which pose tremendous challenges on existing unsigned network models. Hence, in this paper, we investigate the problem of modeling signed networks. In particular, we provide a principled approach to capture important properties and principles of signed networks and propose a novel signed network model guided by Structural Balance Theory. Empirical experiments on three real-world signed networks demonstrate the effectiveness of the proposed model.

Fake news spreading through media outlets poses a real threat to the trustworthiness of information and detecting fake news has attracted increasing attention in recent years. Fake news is typically written intentionally to mislead readers, which determines that fake news detection merely based on news content is tremendously challenging. Meanwhile, fake news could contain true evidence to mock true news and presents different degrees of fakeness, which further exacerbates the detection difficulty. On the other hand, the spread of fake news produces various types of data from different perspectives. These multiple sources provide rich contextual information about fake news and offer unprecedented opportunities for advanced fake news detection. In this paper, we study fake news detection with different degrees of fakeness by integrating multiple sources. In particular, we introduce approaches to combine information from multiple sources and to discriminate between different degrees of fakeness, and propose a Multi-source Multi-class Fake news Detection framework MMFD, which combines automated feature extraction, multi-source fusion and automated degrees of fakeness detection into a coherent and interpretable model. Experimental results on the real-world data demonstrate the effectiveness of the proposed framework and extensive experiments are further conducted to understand the working of the proposed framework.

LTE networks are rolling out cellular Internet-of- Things (IoT) services. Cellular-connected IoT devices are becoming increasingly popular and the number is forecasted to grow almost fourfold from 2015 to 2021. Since they share the same infrastructure with non-IoT devices such as smartphones, we may expect no big differences between them in terms of voice/data service accounting/charging (e.g., paying for what you get) and security risks. However, our study shows that cellular IoT users may pay more than what they get, as well as are vulnerable to voice signaling spams and thus suffer from an overcharging attack which leads to financial loss or denial of service. We validate our proof-of- concept attack in a major U.S. cellular network operator which takes higher than 35% market share. We finally propose a solution to address the identified security vulnerabilities.

Due to the fact much of today's data can be represented as graphs, there has been a demand for generalizing neural network models for graph data. One recent direction that has shown fruitful results, and therefore growing interest, is the usage of graph convolutional neural networks (GCNs). They have been shown to provide a significant improvement on a wide range of tasks in network analysis, one of which being node representation learning. The task of learning low-dimensional node representations has shown to increase performance on a plethora of other tasks from link prediction and node classification, to community detection and visualization. Simultaneously, signed networks (or graphs having both positive and negative links) have become ubiquitous with the growing popularity of social media. However, since previous GCN models have primarily focused on unsigned networks (or graphs consisting of only positive links), it is unclear how they could be applied to signed networks due to the challenges presented by negative links. The primary challenges are based on negative links having not only a different semantic meaning as compared to positive links, but their principles are inherently different and they form complex relations with positive links. Therefore we propose a dedicated and principled effort that utilizes balance theory to correctly aggregate and propagate the information across layers of a signed GCN model. We perform empirical experiments comparing our proposed signed GCN against state-of-the-art baselines for learning node representations in signed networks. More specifically, our experiments are performed on four real-world datasets for the classical link sign prediction problem that is commonly used as the benchmark for signed network embeddings algorithms.

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedback. Users' feedback can be positive and negative and both types of feedback have great potentials to boost recommendations. However, the number of negative feedback is much larger than that of positive one; thus incorporating them simultaneously is challenging since positive feedback could be buried by negative one. In this paper, we develop a novel approach to incorporate them into the proposed deep recommender system (DEERS) framework. The experimental results based on real-world e-commerce data demonstrate the effectiveness of the proposed framework. Further experiments have been conducted to understand the importance of both positive and negative feedback in recommendations.

Recommender systems can mitigate the information overload problem by suggesting users' personalized items. In real-world recommendations such as e-commerce, a typical interaction between the system and its users is - users are recommended a page of items and provide feedback; and then the system recommends a new page of items. To effectively capture such interaction for recommendations, we need to solve two key problems - (1) how to update recommending strategy according to user's real-time feedback, and 2) how to generate a page of items with proper display, which pose tremendous challenges to traditional recommender systems. In this paper, we study the problem of page-wise recommendations aiming to address aforementioned two challenges simultaneously. In particular, we propose a principled approach to jointly generate a set of complementary items and the corresponding strategy to display them in a 2-D page; and propose a novel page-wise recommendation framework based on deep reinforcement learning, DeepPage, which can optimize a page of items with proper display based on real-time feedback from users. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.

Automatically manipulating facial attributes is challenging because it needs to modify the facial appearances, while keeping not only the person's identity but also the realism of the resultant images. Unlike the prior works on the facial attribute parsing, we aim at an inverse and more challenging problem called attribute manipulation by modifying a facial image in line with a reference facial attribute. Given a source input image and reference images with a target attribute, our goal is to generate a new image (i.e., target image) that not only possesses the new attribute but also keeps the same or similar content with the source image. In order to generate new facial attributes, we train a deep neural network with a combination of a perceptual content loss and two adversarial losses, which ensure the global consistency of the visual content while implementing the desired attributes often impacting on local pixels. The model automatically adjusts the visual attributes on facial appearances and keeps the edited images as realistic as possible. The evaluation shows that the proposed model can provide a unified solution to both local and global facial attribute manipulation such as expression change and hair style transfer. Moreover, we further demonstrate that the learned attribute discriminator can be used for attribute localization.

Information networks are ubiquitous in many applications. A popular way to facilitate the information in a network is to embed the network structure into low-dimension spaces where each node is represented as a vector. The learned representations have been proven to advance various network analysis tasks such as link prediction and node classification. The majority of existing embedding algorithms are designed for the networks with one type of nodes and one dimension of relations among nodes. However, many networks in the real-world complex systems have multiple types of nodes and multiple dimensions of relations. For example, an e-commerce network can have users and items, and items can be viewed or purchased by users, corresponding to two dimensions of relations. In addition, some types of nodes can present hierarchical structure. For example, authors in publication networks are associated to affiliations; and items in e-commerce networks belong to categories. Most of existing methods cannot be naturally applicable to these networks. In this paper, we aim to learn representations for networks with multiple dimensions and hierarchical structure. In particular, we provide an approach to capture independent information from each dimension and dependent information across dimensions and propose a framework MINES, which performs Multi-dImension Network Embedding with hierarchical Structure. Experimental results on a network from a real-world e-commerce website demonstrate the effectiveness of the proposed framework.

Friend and item recommendation on a social media site is an important task, which not only brings conveniences to users but also benefits platform providers. However, recommendation for newly launched social media sites is challenging because they often lack user historical data and encounter data sparsity and cold-start problem. Thus, it is important to exploit auxiliary information to help improve recommendation performances on these sites. Existing approaches try to utilize the knowledge transferred from other mature sites, which often require overlapped users or similar items to ensure an effective knowledge transfer. However, these assumptions may not hold in practice because 1) Overlapped user set is often unavailable and costly to identify due to the heterogeneous user profile, content and network data, and 2) Different schemes to show item attributes across sites cause the attribute values inconsistent, incomplete, and noisy. Thus, how to transfer knowledge when no direct bridge is given between two social media sites remains a challenge. In addition, another auxiliary information we can exploit is the mutual benefit between social relationships and rating preferences within the platform. User-user relationships are widely used as side information to improve item recommendation, whereas how to exploit user-item interactions for friend recommendation is rather limited. To tackle these challenges, we propose aCross media jointF riend andI temRe commendation framework (CrossFire ), which can capture both 1) cross-platform knowledge transfer, and 2) within-platform correlations among user-user relations and user-item interactions. Empirical results on real-world datasets demonstrate the effectiveness of the proposed framework.

In personalized recommendation, candidate generation plays an infrastructural role by retrieving candidates out of billions of items. During this process, substitutes and complements constitute two main classes of retrieved candidates: substitutable products are interchangeable, whereas complementary products might be purchased together by users. Discriminating substitutable and complementary products is playing an increasingly important role in e-commerce portals by affecting the performance of candidate generation, e.g., when a user has browsed a t-shirt, it is reasonable to retrieve similar t-shirts, i.e., substitutes; whereas if the user has already purchased one, it would be better to retrieve trousers, hats or shoes, as complements of t-shirts. In this paper, we propose a path-constrained framework (PMSC) for discriminating substitutes and complements. Specifically, for each product, we first learn its embedding representations in a general semantic space. Thereafter, we project the embedding vectors into two separate spaces via a novel mapping function. In the end, we incorporate each embedding with path-constraints to further boost the discriminative ability of the model. Extensive experiments conducted on two e-commerce datasets show the effectiveness of our proposed method.

The explosive popularity of e-commerce sites has reshaped users» shopping habits and an increasing number of users prefer to spend more time shopping online. This evolution allows e-commerce sites to observe rich data about users. The majority of traditional recommender systems have focused on the macro interactions between users and items, i.e., the purchase history of a customer. However, within each macro interaction between a user and an item, the user actually performs a sequence of micro behaviors, which indicate how the user locates the item, what activities the user conducts on the item (e.g., reading the comments, carting, and ordering) and how long the user stays with the item. Such micro behaviors offer fine-grained and deep understandings about users and provide tremendous opportunities to advance recommender systems in e-commerce. However, exploiting micro behaviors for recommendations is rather limited, which motivates us to investigate e-commerce recommendations from a micro-behavior perspective in this paper. Particularly, we uncover the effects of micro behaviors on recommendations and propose an interpretable Recommendation framework RIB, which models inherently the sequence of mIcro Behaviors and their effects. Experimental results on datasets from a real e-commence site demonstrate the effectiveness of the proposed framework and the importance of micro behaviors for recommendations.

Dialogue systems help various real applications interact with humans in an intelligent natural way. In dialogue systems, the task of dialogue generation aims to generate utterances given previous utterances as contexts. Among various spectrums of dialogue generation approaches, end-to-end neural generation models have received an increase of attention. These end-to-end neural generation models are capable of generating natural-sounding sentences with a unified neural encoder-decoder network structure. The end-to-end structure sequentially encodes each word in an input context and generates the response word-by-word deterministically during decoding. However, lack of variation and limited ability in capturing long-term dependencies between utterances still challenge existing approaches. In this paper, we propose a novel hierarchical variational memory network (HVMN), by adding the hierarchical structure and the variational memory network into a neural encoder-decoder network. By emulating human-to-human dialogues, our proposed method can capture both the high-level abstract variations and long-term memories during dialogue tracking, which enables the random access of relevant dialogue histories. Extensive experiments conducted on three large real-world datasets verify a significant improvement of our proposed model against state-of-the-art baselines for dialogue generation.

Reciprocity in directed networks points to user»s willingness to return favors in building mutual interactions. High reciprocity has been widely observed in many directed social media networks such as following relations in Twitter and Tumblr. Therefore, reciprocal relations between users are often regarded as a basic mechanism to create stable social ties and play a crucial role in the formation and evolution of networks. Each reciprocity relation is formed by two parasocial links in a back-and-forth manner with a time delay. Hence, understanding the delay can help us gain better insights into the underlying mechanisms of network dynamics. Meanwhile, the accurate prediction of delay has practical implications in advancing a variety of real-world applications such as friend recommendation and marketing campaign. For example, by knowing when will users follow back, service providers can focus on the users with a potential long reciprocal delay for effective targeted marketing. This paper presents the initial investigation of the time delay in reciprocal relations. Our study is based on a large-scale directed network from Tumblr that consists of 62.8 million users and 3.1 billion user following relations with a timespan of multiple years (from 31 Oct 2007 to 24 Jul 2013). We reveal a number of interesting patterns about the delay that motivate the development of a principled learning model to predict the delay in reciprocal relations. Experimental results on the above mentioned dynamic networks corroborate the effectiveness of the proposed delay prediction model.

Social media provides a platform for seeking information from a large user base. Information seeking in social media, however, occurs simultaneously with users expressing their viewpoints by making statements. Rhetorical questions have the form of a question but serve the function of a statement and are an important tool employed by users to express their viewpoints. Therefore, rhetorical questions might mislead platforms assisting information seeking in social media. It becomes difficult to identify rhetorical questions as they are not syntactically different from other questions. In this article, we develop a framework to identify rhetorical questions by modeling some motivations of the users to post them. We focus on two motivations of the users drawing from linguistic theories to implicitly convey a message and to modify the strength of a statement previously made. We develop a quantitative framework from these motivations to identify rhetorical questions in social media. We evaluate the framework using two datasets of questions posted on a social media platform Twitter and demonstrate its effectiveness in identifying rhetorical questions. This is the first framework, to the best of our knowledge, to model the possible motivations for posting rhetorical questions to identify them on social media platforms.

Items in real-world recommender systems exhibit certain hierarchical structures. Similarly, user preferences also present hierarchical structures. Recent studies show that incorporating the hierarchy of items or user preferences can improve the performance of recommender systems. However, hierarchical structures are often not explicitly available, especially those of user preferences. Thus, there's a gap between the importance of hierarchies and their availability. In this paper, we investigate the problem of exploring the implicit hierarchical structures for recommender systems when they are not explicitly available. We propose a novel recommendation framework to bridge the gap, which enables us to explore the implicit hierarchies of users and items simultaneously. We then extend the framework to integrate explicit hierarchies when they are available, which gives a unified framework for both explicit and implicit hierarchical structures. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework by incorporating implicit and explicit structures.

Machine learning methods are used to discover complex nonlinear relationships in biological and medical data. However, sophisticated learning models are computationally unfeasible for data with millions of features. Here, we introduce the first feature selection method for nonlinear learning problems that can scale up to large, ultra-high dimensional biological data. More specifically, we scale up the novel Hilbert-Schmidt Independence Criterion Lasso (HSIC Lasso) to handle millions of features with tens of thousand samples. The proposed method is guaranteed to find an optimal subset of maximally predictive features with minimal redundancy, yielding higher predictive power and improved interpretability. Its effectiveness is demonstrated through applications to classify phenotypes based on module expression in human prostate cancer patients and to detect enzymes among protein structures. We achieve high accuracy with as few as 20 out of one million features-a dimensionality reduction of 99.998 percent. Our algorithm can be implemented on commodity cloud computing platforms. The dramatic reduction of features may lead to the ubiquitous deployment of sophisticated prediction models in mobile health care applications.

Huge volumes of opinion-rich data is user-generated in social media at an unprecedented rate, easing the analysis of individual and public sentiments. Sentiment analysis has shown to be useful in probing and understanding emotions, expressions and attitudes in the text. However, the distinct characteristics of social media data present challenges to traditional sentiment analysis. First, social media data is often noisy, incomplete and fast-evolved which necessitates the design of a sophisticated learning model. Second, sentiment labels are hard to collect which further exacerbates the problem by not being able to discriminate sentiment polarities. Meanwhile, opportunities are also unequivocally presented. Social media contains rich sources of sentiment signals in textual terms and user interactions, which could be helpful in sentiment analysis. While there are some attempts to leverage implicit sentiment signals in positive user interactions, little attention is paid on signed social networks with both positive and negative links. The availability of signed social networks motivates us to investigate if negative links also contain useful sentiment signals. In this paper, we study a novel problem of unsupervised sentiment analysis with signed social networks. In particular, we incorporate explicit sentiment signals in textual terms and implicit sentiment signals from signed social networks into a coherent model SignedSenti for unsupervised sentiment analysis. Empirical experiments on two real-world datasets corroborate its effectiveness.

Data classification and tag recommendation are both important and challenging tasks in social media. These two tasks are often considered independently and most efforts have been made to tackle them separately. However, labels in data classification and tags in tag recommendation are inherently related. For example, a Youtube video annotated with NCAA, stadium, pac12 is likely to be labeled as football, while a video/image with the class label of coast is likely to be tagged with beach, sea, water and sand. The existence of relations between labels and tags motivates us to jointly perform classification and tag recommendation for social media data in this paper. In particular, we provide a principled way to capture the relations between labels and tags, and propose a novel framework CLARE, which fuses data CLAssification and tag REcommendation into a coherent model. With experiments on three social media datasets, we demonstrate that the proposed framework CLARE achieves superior performance on both tasks compared to the state-of-the-art methods.

Network embedding leverages the node proximity manifested to learn a low-dimensional node vector representation for each node in the network. The learned embeddings could advance various learning tasks such as node classification, network clustering, and link prediction. Most, if not all, of the existing works, are overwhelmingly performed in the context of plain and static networks. Nonetheless, in reality, network structure often evolves over time with addition/deletion of links and nodes. Also, a vast majority of real-world networks are associated with a rich set of node attributes, and their attribute values are also naturally changing, with the emerging of new content patterns and the fading of old content patterns. These changing characteristics motivate us to seek an effective embedding representation to capture network and attribute evolving patterns, which is of fundamental importance for learning in a dynamic environment. To our best knowledge, we are the first to tackle this problem with the following two challenges: (1) the inherently correlated network and node attributes could be noisy and incomplete, it necessitates a robust consensus representation to capture their individual properties and correlations; (2) the embedding learning needs to be performed in an online fashion to adapt to the changes accordingly. In this paper, we tackle this problem by proposing a novel dynamic attributed network embedding framework - DANE. In particular, DANE first provides an offline method for a consensus embedding and then leverages matrix perturbation theory to maintain the freshness of the end embedding results in an online manner. We perform extensive experiments on both synthetic and real attributed networks to corroborate the effectiveness and efficiency of the proposed framework.

The major task of network embedding is to learn low-dimensional vector representations of social-network nodes. It facilitates many analytical tasks such as link prediction and node clustering and thus has attracted increasing attention. The majority of existing embedding algorithms are designed for unsigned social networks. However, many social media networks have both positive and negative links, for which unsigned algorithms have little utility. Recent findings in signed network analysis suggest that negative links have distinct properties and added value over positive links. This brings about both challenges and opportunities for signed network embedding. In addition, user attributes, which encode properties and interests of users, provide complementary information to network structures and have the potential to improve signed network embedding. Therefore, in this paper, we study the novel problem of signed social network embedding with attributes. We propose a novel framework SNEA, which exploits the network structure and user attributes simultaneously for network representation learning. Experimental results on link prediction and node clustering with real-world datasets demonstrate the effectiveness of SNEA.

It has become increasingly popular to use mobile social networking applications for weight loss and management. Users can not only create profiles and maintain their records but also perform a variety of social activities that shatter the barrier to share or seek information. Due to the open and connected nature, these applications produce massive data that consists of rich weight-related information which offers immense opportunities for us to enable advanced research on weight loss. In this paper, we conduct the initial investigation to understand weight loss with a large-scale mobile social networking dataset with near 10 million users. In particular, we study individual and social factors related to weight loss and reveal a number of interesting findings that help us build a meaningful model to predict weight loss automatically. The experimental results demonstrate the effectiveness of the proposed model and the significance of social factors in weight loss.

Crime prediction plays a crucial role in improving public security and reducing the financial loss of crimes. The vast majority of traditional algorithms performed the prediction by leveraging demographic data, which could fail to capture the dynamics of crimes in urban. In the era of big data, we have witnessed advanced ways to collect and integrate fine-grained urban, mobile, and public service data that contains various crime-related sources and rich temporal-spatial information. Such information provides better understandings about the dynamics of crimes and has potentials to advance crime prediction. In this paper, we exploit temporal-spatial correlations in urban data for crime prediction. In particular, we validate the existence of temporal-spatial correlations in crime and develop a principled approach to model these correlations into the coherent framework TCP for crime prediction. The experimental results on real-world data demonstrate the effectiveness of the proposed framework. Further experiments have been conducted to understand the importance of temporal-spatial correlations in crime prediction.

Feature selection has been proven to be effective and efficient in preparing high-dimensional data for data mining and machine learning problems. Since real-world data is usually unlabeled, unsupervised feature selection has received increasing attention in recent years. Without label information, unsupervised feature selection needs alternative criteria to define feature relevance. Recently, data reconstruction error emerged as a new criterion for unsupervised feature selection, which defines feature relevance as the capability of features to approximate original data via a reconstruction function. Most existing algorithms in this family assume predefined, linear reconstruction functions. However, the reconstruction function should be data dependent and may not always be linear especially when the original data is high-dimensional. In this paper, we investigate how to learn the reconstruction function from the data automatically for unsupervised feature selection, and propose a novel reconstruction-based unsupervised feature selection framework REFS, which embeds the reconstruction function learning process into feature selection. Experiments on various types of real-world datasets demonstrate the effectiveness of the proposed framework REFS.

Forecasting the future observations of time-series data can be performed by modeling the trend and fluctuations from the observed data. Many classical time-series analysis models like Autoregressive model (AR) and its variants have been developed to achieve such forecasting ability. While they are often based on the white noise assumption to model the data fluctuations, a more general Brownian motion has been adopted that results in Ornstein-Uhlenbeck (OU) process. The OU process has gained huge successes in predicting the future observations over many genres of time series, however, it is still limited in modeling simple diffusion dynamics driven by a single persistent factor that never evolves over time. However, in many real problems, a mixture of hidden factors are usually present, and when and how frequently they appear or disappear are unknown ahead of time. This imposes a challenge that inspires us to develop a Mixture Factorized OU process (MFOUP) to model evolving factors. The new model is able to capture the changing states of multiple mixed hidden factors, from which we can infer their roles in driving the movements of time series. We conduct experiments on three forecasting problems, covering sensor and market data streams. The results show its competitive performance on predicting future observations and capturing evolution patterns of hidden factors as compared with the other algorithms.

Supervised multi-class learning arises in many application domains such as biology, computer vision, social network analysis, and information retrieval. These applications often involve high-dimensional data, which not only significantly increase the time and space requirement of the underlying algorithms but also degrade their performance due to the curse of dimensionality. Feature selection has been proven effective and efficient for preparing high-dimensional data for many learning tasks. Traditional feature selection algorithms for multi-class data assume the independence of label categories and select features with the capability to distinguish samples from different classes. However, class labels in multi-class data may be correlated and little work exists for exploiting label correlation in multi-class feature selection. In this paper, we investigate label correlation in feature selection for multi-class data. In particular, we provide a principled approach for capturing label correlation and propose an Embedded Supervised Feature Selection (ESFS) framework, which embeds label correlation modeling in supervised feature selection for multi-class data. Experiments on both synthetic data and various types of public benchmark datasets show that the proposed framework effectively captures the multi-class label correlation and significantly outperforms existing state-of-the-art baseline methods.

Vacation rental websites such as Airbnb have become increasingly popular where rentals are typically short-term and travels or vacations related. Reasonable rental prices play a crucial role in improving user experiences and engagements in these websites. However, the unique properties of their rentals challenge traditional house rentals that are often long-term and study or work related. Therefore, in this paper we investigate the novel problem of price recommendation in vacation rental websites. We identify some important factors that affect the rental prices and propose a framework that consists of Multi-Scale Affinity Propagation (MSAP) to cluster houses, Nash Equilibrium filter to remove unreasonable price and Linear Regression model with Normal Noise (LRNN) to predict the reasonable prices. Experimental results demonstrate the effectiveness of the proposed framework. We conduct further experiments to understand the important factors in rental price recommendation.

Network embedding is to learn low-dimensional vector representations for nodes of a given social network, facilitating many tasks in social network analysis such as link prediction. The vast majority of existing embedding algorithms are designed for unsigned social networks or social networks with only positive links. However, networks in social media could have both positive and negative links, and little work exists for signed social networks. From recent findings of signed network analysis, it is evident that negative links have distinct properties and added value besides positive links, which brings about both challenges and opportunities for signed network embedding. In this paper, we propose a deep learning framework SiNE for signed network embedding. The framework optimizes an objective function guided by social theories that provide a fundamental understanding of signed social networks. Experimental results on two real-world datasets of social media demonstrate the effectiveness of the proposed framework SiNE.

Feature selection has been proven to be effective and efficient in preparing high-dimensional data for many mining and learning tasks. Features of real-world high-dimensional data such as words of documents, pixels of images and genes of microarray data, usually present inherent hierarchical structures. In a hierarchical structure, features could share certain properties. Such information has been exploited to help supervised feature selection but it is rarely investigated for unsupervised feature selection, which is challenging due to the lack of labels. Since real world data is often unlabeled, it is of practical importance to study the problem of feature selection with hierarchical structures in an unsupervised setting. In particular, we provide a principled method to exploit hierarchical structures of features and propose a novel framework HUFS, which utilizes the given hierarchical structures to help select features without labels. Experimental study on real-world datasets is conducted to assess the effectiveness of the proposed framework.

Social media has become a valuable tool for hackers to disseminate misinformation through compromised accounts. A compromised account is an account accessed by a third party without the user's knowledge. Previous studies have found 13% of online adults experienced their social media accounts compromised. Since compromised accounts can have a significant adverse impact on the social media sites, this has led to the growing research on detecting compromised accounts. However, previous works are limited as they either focus on the detection of hacked accounts for spamming and phishing activities or utilize only twitter content information. In this paper, we performed a systematic study on compromised accounts in Twitter by identifying who compromise the accounts; what information they share, and what patterns their tweets present. Our findings suggest that the accounts can be compromised by two different types of hackers and the content they post tend to follow several common themes. We also showed that, in addition to the text content of the tweets, there are other meta-information that can be exploited to help improve the detection of compromised accounts.

The ubiquity of mobile devices and cloud services has led to an unprecedented growth of online personal photo and video collections. Due to the scarcity of personal media search log data, research to date has mainly focused on searching images and videos on the web. However, in order to manage the exploding amount of personal photos and videos, we raise a fundamental question: what are the differences and similarities when users search their own photos versus the photos on the web? To the best of our knowledge, this paper is the first to study personal media search using large-scale real-world search logs. We analyze different types of search sessions mined from Flickr search logs and discover a number of interesting characteristics of personal media search in terms of information needs and click behaviors. The insightful observations will not only be instrumental in guiding future personal media search methods, but also benefit related tasks such as personal photo browsing and recommendation. Our findings suggest there is a significant gap between personal queries and automatically detected concepts, which is responsible for the low accuracy of many personal media search queries. To bridge the gap, we propose the deep query understanding model to learn a mapping from the personal queries to the concepts in the clicked photos. Experimental results verify the efficacy of the proposed method in improving personal media search, where the proposed method consistently outperforms baseline methods.

The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios. Data streams present distinct properties such as temporally ordered, continuous and high-velocity, which poses tremendous challenges to traditional recommender systems. In this paper, we investigate the problem of recommendation with stream inputs. In particular, we provide a principled framework termed sRec, which provides explicit continuous-time random process models of the creation of users and topics, and of the evolution of their interests. A variational Bayesian approach called recursive meanfield approximation is proposed, which permits computationally efficient instantaneous on-line inference. Experimental results on several real-world datasets demonstrate the advantages of our sRec over other state-of-the-arts.

Studies suggest that self-harm users found it easier to discuss self-harm-related thoughts and behaviors using social media than in the physical world. Given the enormous and increasing volume of social media data, on-line self-harm content is likely to be buried rapidly by other normal content. To enable voices of self-harm users to be heard, it is important to distinguish self-harm content from other types of content. In this paper, we aim to understand self-harm content and provide automatic approaches to its detection. We first perform a comprehensive analysis on self-harm social media using different input cues. Our analysis, the first of its kind in large scale, reveals a number of important findings. Then we propose frameworks that incorporate the findings to discover self-harm content under both supervised and unsupervised settings. Our experimental results on a large social media dataset from Flickr demonstrate the effectiveness of the proposed frameworks and the importance of our findings in discovering self-harm content.

The rapid growth of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which facilitates the study of point-of-interest (POI) recommendation. The majority of the existing POI recommendation methods focus on four aspects, i.e., temporal patterns, geographical influence, social correlations and textual content indications. For example, user's visits to locations have temporal patterns and users are likely to visit POIs near them. In real-world LBSNs such as Instagram, users can upload photos associating with locations. Photos not only reflect users' interests but also provide informative descriptions about locations. For example, a user who posts many architecture photos is more likely to visit famous landmarks; while a user posts lots of images about food has more incentive to visit restaurants. Thus, images have potentials to improve the performance of POI recommendation. However, little work exists for POI recommendation by exploiting images. In this paper, we study the problem of enhancing POI recommendation with visual contents. In particular, we propose a new framework Visual Content Enhanced POI recommendation (VPOI), which incorporates visual contents for POI recommendations. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework.

Location information of Web pages plays an important role in location-sensitive tasks such as Web search ranking for location-sensitive queries. However, such information is usually ambiguous, incomplete, or even missing, which raises the problem of location prediction for Web pages. Meanwhile, Web pages are massive and often noisy, which pose challenges to the majority of existing algorithms for location prediction. In this paper, we propose a novel and scalable location prediction framework for Web pages based on the query-URL click graph. In particular, we introduce a concept of term location vectors to capture location distributions for all terms and develop an automatic approach to learn the importance of each term location vector for location prediction. Empirical results on a large URL set demonstrate that the proposed framework significantly improves the location prediction accuracy comparing with various representative baselines. We further provide a principled way to incorporate the proposed framework into the search ranking task and experimental results on a commercial search engine show that the proposed method remarkably boosts the ranking performance for location-sensitive queries.

Social media plays a major role in helping people affected by natural calamities. These people use social media to request information and help in situations where time is a critical commodity. However, generic social media platforms like Twitter and Facebook are not conducive for obtaining answers promptly. Algorithms to ensure prompt responders for questions in social media have to understand and model the factors affecting their response time. In this paper, we draw from sociological studies on information seeking and organizational behavior to identify users who can provide timely and relevant responses to questions posted on social media. We first draw from these theories to model the future availability and past response behavior of the candidate responders and integrate these criteria with user relevance. We propose a learning algorithm from these criteria to derive optimal rankings of responders for a given question. We present questions posted on Twitter as a form of information seeking activity in social media and use them to evaluate our framework. Our experiments demonstrate that the proposed framework is useful in identifying timely and relevant responders for questions in social media.

Social media has emerged to be a popular platform for people to express their viewpoints on political protests like the Arab Spring. Millions of people use social media to communicate and mobilize their viewpoints on protests. Hence, it is a valuable tool for organizing social movements. However, the mechanisms by which protest affects the population is not known, making it difficult to estimate the number of protestors. In this paper, we are inspired by sociological theories of protest participation and propose a framework to predict from the user's past status messages and interactions whether the next post of the user will be a declaration of protest. Drawing concepts from these theories, we model the interplay between the user's status messages and messages interacting with him over time and predict whether the next post of the user will be a declaration of protest. We evaluate the framework using data from the social media platform Twitter on protests during the recent Nigerian elections and demonstrate that it can effectively predict whether the next post of a user is a declaration of protest.

The pervasive presence of social media greatly enriches online users' social activities, resulting in abundant social relations. Social relations provide an independent source for recommendation, bringing about new opportunities for recommender systems. Exploiting social relations to improve recommendation performance attracts a great amount of attention in recent years. Most existing social recommender systems treat social relations homogeneously and make use of direct connections (or strong dependency connections). However, connections in online social networks are intrinsically heterogeneous and are a composite of various relations. While connected users in online social networks form groups, and users in a group share similar interests, weak dependency connections are established among these users when they are not directly connected. In this paper, we investigate how to exploit the heterogeneity of social relations and weak dependency connections for recommendation. In particular, we employ social dimensions to simultaneously capture heterogeneity of social relations and weak dependency connections, and provide principled ways to model social dimensions, and propose a recommendation framework SoDimRec which incorporates heterogeneity of social relations and weak dependency connections based on social dimensions. Experimental results on real-world data sets demonstrate the effectiveness of the proposed framework. We conduct further experiments to understand the important role of social dimensions in the proposed framework.

It is widely known that there exists a semantic gap between web documents and user queries and bridging this gap is crucial to advance information retrieval systems. The task of query rewriting, aiming to alter a given query to a rewrite query that can close the gap and improve information retrieval performance, has attracted increasing attention in recent years. However, the majority of existing query rewriters are not designed to boost search performance and consequently their rewrite queries could be sub-optimal. In this paper, we propose a learning to rewrite framework that consists of a candidate generating phase and a candidate ranking phase. The candidate generating phase provides us the flexibility to reuse most of existing query rewriters; while the candidate ranking phase allows us to explicitly optimize search relevance. Experimental results on a commercial search engine demonstrate the effectiveness of the proposed framework. Further experiments are conducted to understand the important components of the proposed framework.

Word and document embedding algorithms such as Skip-gram and Paragraph Vector have been proven to help various text analysis tasks such as document classification, document clustering and information retrieval. The vast majority of these algorithms are designed to work with independent and identically distributed documents. However, in many real-world applications, documents are inherently linked. For example, web documents such as blogs and online news often have hyperlinks to other web documents, and scientific articles usually cite other articles. Linked documents present new challenges to traditional document embedding algorithms. In addition, most existing document embedding algorithms are unsupervised and their learned representations may not be optimal for classification when labeling information is available. In this paper, we study the problem of linked document embedding for classification and propose a linked document embedding framework LDE, which combines link and label information with content information to learn document representations for classification. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework. Further experiments are conducted to understand the importance of link and label information in the proposed framework LDE.

Restricted Boltzmann Machines (RBMs) are widely adopted unsupervised representation learning methods and have powered many data mining tasks such as collaborative filtering and document representation. Recently, linked data that contains both attribute and link information has become ubiquitous in various domains. For example, social media data is inherently linked via social relations and web data is networked via hyperlinks. It is evident from recent work that link information can enhance a number of real-world applications such as clustering and recommendations. Therefore, link information has the potential to advance RBMs for better representation learning. However, the majority of existing RBMs have been designed for independent and identically distributed data and are unequipped for linked data. In this paper, we aim to design a new type of Restricted Boltzmann Machines that takes advantage of linked data. In particular, we propose a paired Restricted Boltzmann Machine (pRBM), which is able to leverage the attribute and link information of linked data for representation learning. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework pRBM.

Pointwise label and pairwise label are both widely used in computer vision tasks. For example, supervised image classification and annotation approaches use pointwise label, while attribute-based image relative learning often adopts pairwise labels. These two types of labels are often considered independently and most existing efforts utilize them separately. However, pointwise labels in image classification and tag annotation are inherently related to the pairwise labels. For example, an image labeled with "coast" and annotated with "beach, sea, sand, sky" is more likely to have a higher ranking score in terms of the attribute "open", while "men shoes" ranked highly on the attribute "formal" are likely to be annotated with "leather, lace up" than "buckle, fabric". The existence of potential relations between pointwise labels and pairwise labels motivates us to fuse them together for jointly addressing related vision tasks. In particular, we provide a principled way to capture the relations between class labels, tags and attributes, and propose a novel framework PPP(Pointwise and Pairwise image label Prediction), which is based on overlapped group structure extracted from the pointwise-pairwise-label bipartite graph. With experiments on benchmark datasets, we demonstrate that the proposed framework achieves superior performance on three vision tasks compared to the state-of-the-art methods.

Data of many problems in real-world systems such as link prediction and one-class recommendation share common characteristics. First, data are in the form of positive unlabeled (PU) measurements (e.g. Twitter "following", Facebook "like", etc.) that do not provide negative information, which can be naturally represented as networks. Second, in the era of big data, such data are generated temporally-ordered, continuously and rapidly, which determines its streaming nature. These common characteristics allow us to unify many problems into a novel framework -- PU learning in streaming networks. In this paper, a principled probabilistic approach SPU is proposed to leverage the characteristics of the streaming PU inputs. In particular, SPU captures temporal dynamics and provides real-time adaptations and predictions by identifying the potential negative signals concealed in unlabeled data. Our empirical results on various real-world datasets demonstrate the effectiveness of the proposed framework over other state-of-the-art methods in both link prediction and recommendation.

Search engines play a crucial role in our daily lives. Relevance is the core problem of a commercial search engine. It has attracted thousands of researchers from both academia and industry and has been studied for decades. Relevance in a modern search engine has gone far beyond text matching, and now involves tremendous challenges. The semantic gap between queries and URLs is the main barrier for improving base relevance. Clicks help provide hints to improve relevance, but unfortunately for most tail queries, the click information is too sparse, noisy, or missing entirely. For comprehensive relevance, the recency and location sensitivity of results is also critical. In this paper, we give an overview of the solutions for relevance in the Yahoo search engine. We introduce three key techniques for base relevance -- ranking functions, semantic matching features and query rewriting. We also describe solutions for recency sensitive relevance and location sensitive relevance. This work builds upon 20 years of existing efforts on Yahoo search, summarizes the most recent advances and provides a series of practical relevance solutions. The performance reported is based on Yahoo's commercial search engine, where tens of billions of urls are indexed and served by the ranking system.

Trust and distrust networks are usually extremely sparse and the vast majority of the existing algorithms for trust/distrust prediction suffer from the data sparsity problem. In this paper, following the research from psychology and sociology, we envision that users' emotions such as happiness and anger are strong indicators of trust/distrust relations. Meanwhile the popularity of social media encourages the increasing number of users to freely express their emotions; hence emotional information is pervasively available and usually denser than the trust and distrust relations. Therefore incorporating emotional information could have the potentials to alleviate the data sparsity in the problem of trust/distrust prediction. In this study, we investigate how to exploit emotional information for trust/distrust prediction. In particular, we provide a principled way to capture emotional information mathematically and propose a novel trust/distrust prediction framework ETD. Experimental results on the real-world social media dataset demonstrate the effectiveness of the proposed framework and the importance of emotional information in trust/distrust prediction.

Node classification in social networks has been proven to be useful in many real-world applications. The vast majority of existing algorithms focus on unsigned social networks (or social networks with only positive links), while little work exists for signed social networks. It is evident from recent developments in signed social network analysis that negative links have added value over positive links. Therefore, the incorporation of negative links has the potential to benefit various analytical tasks. In this paper, we study the novel problem of node classification in signed social networks. We provide a principled way to mathematically model positive and negative links simultaneously and propose a novel framework NCSSN for node classification in signed social networks. Experimental results on real-world signed social network datasets demonstrate the effectiveness of the proposed framework NCSSN. Further experiments are conducted to gain a deeper understanding of the importance of negative links for NCSSN.

Social media is increasingly being used to access and disseminate information on sociopolitical issues like gun rights and general elections. The popularity and openness of social media makes it conducive for some individuals, known as advocates, who use social media to push their agendas on these issues strategically. Identifying these advocates will caution social media users before reading their information and also enable campaign managers to identify advocates for their digital political campaigns. A significant challenge in identifying advocates is that they employ nuanced strategies to shape user opinion and increase the spread of their messages, making it difficult to distinguish them from random users posting on the campaign. In this paper, we draw from social movement theories and design a quantitative framework to study the nuanced message strategies, propagation strategies, and community structure adopted by advocates for political campaigns in social media. Based on observations of their social media activities manifesting from these strategies, we investigate how to model these strategies for identifying them. We evaluate the framework using two datasets from Twitter, and our experiments demonstrate its effectiveness in identifying advocates for political campaigns with ramifications of this work directed towards assisting users as they navigate through social media spaces.

Recommender systems play a crucial role in mitigating the information overload problem in social media by suggesting relevant information to users. The popularity of pervasively available social activities for social media users has encouraged a large body of literature on exploiting social networks for recommendation. The vast majority of these systems focus on unsigned social networks (or social networks with only positive links), while little work exists for signed social networks (or social networks with positive and negative links). The availability of negative links in signed social networks presents both challenges and opportunities in the recommendation process. We provide a principled and mathematical approach to exploit signed social networks for recommendation, and propose a model, RecSSN, to leverage positive and negative links in signed social networks. Empirical results on real-world datasets demonstrate the effectiveness of the proposed framework. We also perform further experiments to explicitly understand the effect of signed networks in RecSSN.

The rapid urban expansion has greatly extended the physical boundary of users' living area and developed a large number of POIs (points of interest). POI recommendation is a task that facilitates users' urban exploration and helps them filter uninteresting POIs for decision making. While existing work of POI recommendation on location-based social networks (LBSNs) discovers the spatial, temporal, and social patterns of user check-in behavior, the use of content information has not been systematically studied. The various types of content information available on LBSNs could be related to different aspects of a user's check-in action, providing a unique opportunity for POI recommendation. In this work, we study the content information on LBSNs w.r.t. POI properties, user interests, and sentiment indications. We model the three types of information under a unified POI recommendation framework with the consideration of their relationship to check-in actions. The experimental results exhibit the significance of content information in explaining user behavior, and demonstrate its power to improve POI recommendation performance on LBSNs.

The rise of social media provides a great opportunity for people to reach out to their social connections to satisfy their information needs. However, generic social media platforms are not explicitly designed to assist information seeking of users. In this paper, we propose a novel framework to identify the social connections of a user able to satisfy his information needs. The information need of a social media user is subjective and personal, and we investigate the utility of his social context to identify people able to satisfy it. We present questions users post on Twitter as instances of information seeking activities in social media. We infer soft community memberships of the asker and his social connections by integrating network and content information. Drawing concepts from the social foci theory, we identify answerers whose community memberships in the question domain overlap with that of the asker. Our experiments demonstrate that the framework is effective in identifying answerers to social media questions.

Sparse learning has been proven to be a powerful techniquein supervised feature selection, which allows toembed feature selection into the classification (or regression)problem. In recent years, increasing attentionhas been on applying spare learning in unsupervisedfeature selection. Due to the lack of label information,the vast majority of these algorithms usually generatecluster labels via clustering algorithms and then formulateunsupervised feature selection as sparse learningbased supervised feature selection with these generatedcluster labels. In this paper, we propose a novel unsupervisedfeature selection algorithm EUFS, which directlyembeds feature selection into a clustering algorithm viasparse learning without the transformation. The AlternatingDirection Method of Multipliers is used to addressthe optimization problem of EUFS. Experimentalresults on various benchmark datasets demonstrate theeffectiveness of the proposed framework EUFS.

With the pervasion of social media, trust has been playing more of an important role in helping online users collect reliable information. In reality, user-specified trust relations are often very sparse; hence, inferring unknown trust relations has attracted increasing attention in recent years. Social status is one of the most important concepts in trust, and status theory is developed to help us understand the important role of social status in the formation of trust relations. In this paper, we investigate how to exploit social status in trust prediction by modeling status theory. We first vertify status theory in trust relations, then provide a principled way to model it mathematically, and propose a novel framework sTrust which incorporates status theory for trust prediction. Experimental results on real-world datasets demonstrate the effectiveness of the proposed framework. Futher experiments are conducted to understand the importance of status theory in trust prediction.

The explosive growth of social media sites brings about massive amounts of high-dimensional data. Feature selection is effective in preparing high-dimensional data for data analytics. The characteristics of social media present novel challenges for feature selection. First, social media data is not fully structured and its features are usually not predefined, but are generated dynamically. For example, in Twitter, slang words (features) are created everyday and quickly become popular within a short period of time. It is hard to directly apply traditional batch-mode feature selection methods to find such features. Second, given the nature of social media, label information is costly to collect. It exacerbates the problem of feature selection without knowing feature relevance. On the other hand, opportunities are also unequivocally present with additional data sources; for example, link information is ubiquitous in social media and could be helpful in selecting relevant features. In this paper, we study a novel problem to conduct unsupervised streaming feature selection for social media data. We investigate how to exploit link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework USFS. Experimental results on two real-world social media datasets show the effectiveness and efficiency of the proposed framework comparing with the state-of-the-art unsupervised feature selection algorithms.

Users usually play dual roles in real-world recommender systems. One is as a reviewer who writes reviews for items with rating scores, and the other is as a rater who rates the helpfulness scores of reviews. Traditional recommender systems mainly consider the reviewer role while not taking into account the rater role. However, the rater role allows users to express their opinions toward reviews about items; hence it may indirectly indicate their opinions about items, which could be complementary to the reviewer role. Since most real-world recommender systems provide convenient mechanisms for the rater role, recent studies show that typically there are much more helpfulness ratings from the rater role than item ratings from the reviewer role. Therefore, incorporating the rater role of users may have the potentials to mitigate the data sparsity and cold-start problems in traditional recommender systems. In this paper, we investigate how to exploit dual roles of users in recommender systems. In particular, we provide a principled way to exploit the rater role mathematically and propose a novel recommender system DualRec, which captures both the reviewer role and the rater role of users simultaneously for recommendation. Experimental results on two real world datasets demonstrate the effectiveness of the proposed framework, and further experiments are conducted to understand the importance of the rater role of users in recommendation.

Social media is being increasingly used to request information and help in situations like natural disasters, where time is a critical commodity. However, generic social media platforms are not explicitly designed for timely information seeking, making it difficult for users to obtain prompt responses. Algorithms to ensure prompt responders for questions in social media have to understand the factors affecting their response time. In this paper, we draw from sociological studies on information seeking and organizational behavior to model the future availability and past response behavior of the candidate responders. We integrate these criteria with their interests to identify users who can provide timely and relevant responses to questions posted in social media. We propose a learning algorithm to derive optimal rankings of responders for a given question. We present questions posted on Twitter as a form of information seeking activity in social media. Our experiments demonstrate that the proposed framework is useful in identifying timely and relevant responders for questions in social media.

Data embedding is used in many machine learning applications to create low-dimensional feature representations, which preserves the structure of data points in their original space. In this paper, we examine the scenario of a heterogeneous network with nodes and content of various types. Such networks are notoriously difficult to mine because of the bewildering combination of heterogeneous contents and structures. The creation of a multidimensional embedding of such data opens the door to the use of a wide variety of off-the-shelf mining techniques for multidimensional data. Despite the importance of this problem, limited efforts have been made on embedding a network of scalable, dynamic and heterogeneous data. In such cases, both the content and linkage structure provide important cues for creating a unified feature representation of the underlying network. In this paper, we design a deep embedding algorithm for networked data. A highly nonlinear multi-layered embedding function is used to capture the complex interactions between the heterogeneous data in a network. Our goal is to create a multi-resolution deep embedding function, that reflects both the local and global network structures, and makes the resulting embedding useful for a variety of data mining tasks. In particular, we demonstrate that the rich content and linkage information in a heterogeneous network can be captured by such an approach, so that similarities among cross-modal data can be measured directly in a common embedding space. Once this goal has been achieved, a wide variety of data mining problems can be solved by applying off-the-shelf algorithms designed for handling vector representations. Our experiments on real-world network datasets show the effectiveness and scalability of the proposed algorithm as compared to the state-of-the-art embedding methods.

The explosive popularity of microblogging services encourages more and more online users to share their opinions, and sentiment analysis on such opinion-rich resources has been proven to be an effective way to understand public opinions. On the one hand, the brevity and informality of microblogging data plus its wide variety and rapid evolution of language in microblogging pose new challenges to the vast majority of existing methods. On the other hand, microblogging texts contain various types of emotional signals strongly associated with their sentiment polarity, which brings about new opportunities for sentiment analysis. In this paper, we investigate propagation-based sentiment analysis for microblogging data. In particular, we provide a propagating process to incorporate various types of emotional signals in microblogging data into a coherent model, and propose a novel sentiment analysis framework PSA which learns from both labeled and unlabeled data by iteratively alternating a propagating process and a fitting process. We conduct experiments on real-world microblogging datasets, and the results demonstrate the effectiveness of the proposed framework. Further experiments are conducted to probe the working of the key components of the proposed framework.

Signed network analysis has attracted increasing attention in recent years. This is in part because research on signed network analysis suggests that negative links have added value in the analytical process. A major impediment in their effective use is that most social media sites do not enable users to specify them explicitly. In other words, a gap exists between the importance of negative links and their availability in real data sets. Therefore, it is natural to explore whether one can predict negative links automatically from the commonly available social network data. In this paper, we investigate the novel problem of negative link prediction with only positive links and content-centric interactions in social media. We make a number of important observations about negative links, and propose a principled framework NeLP, which can exploit positive links and content-centric interactions to predict negative links. Our experimental results on real-world social networks demonstrate that the proposed NeLP framework can accurately predict negative links with positive links and content-centric interactions. Our detailed experiments also illustrate the relative importance of various factors to the effectiveness of the proposed framework.

Trust plays a crucial role in helping online users collect reliable information and it has gained increasing attention from the computer science community in recent years. Traditionally, research about online trust assumes static trust relations between users. However, trust, as a social concept, evolves as people interact. Most existing studies about trust evolution are from sociologists in the physical world while little work exists in an online world. Studying online trust evolution faces unique challenges because more often than not, available data is from passive observation. In this work, we leverage social science theories to develop a methodology that enables the study of online trust evolution. In particular, we identify the differences of trust evolution study in physical and online worlds and propose a framework, eTrust, to study trust evolution using online data from passive observation in the context of product review sites by exploiting the dynamics of user preferences. We present technical details about modeling trust evolution, and perform experiments to show how the exploitation of trust evolution can help improve the performance of online applications such as trust prediction, rating prediction and ranking evolution.

The explosive use of social media also makes it a popular platform for malicious users, known as social spammers, to overwhelm normal users with unwanted content. One effective way for social spammer detection is to build a classifier based on content and social network information. However, social spammers are sophisticated and adaptable to game the system with fast evolving content and network patterns. First, social spammers continually change their spamming content patterns to avoid being detected. Second, reflexive reciprocity makes it easier for social spammers to establish social influence and pretend to be normal users by quickly accumulating a large number of "human" friends. It is challenging for existing anti-spamming systems based on batch-mode learning to quickly respond to newly emerging patterns for effective social spammer detection. In this paper, we present a general optimization framework to collectively use content and network information for social spammer detection, and provide the solution for efficient online processing. Experimental results on Twitter datasets confirm the effectiveness and efficiency of the proposed framework.

Trust plays a crucial role in helping users collect reliable information in an online world, and has attracted more and more attention in research communities lately. As a conceptual counterpart of trust, distrust can be as important as trust. However, distrust is rarely studied in social media because distrust information is usually unavailable. The value of distrust has been widely recognized in social sciences and recent work shows that distrust can benefit various online applications in social media. In this work, we investigate whether we can obtain distrust information via learning when it is not directly available, and propose to study a novel problem - predicting distrust using pervasively available interaction data in an online world. In particular, we analyze interaction data, provide a principled way to mathematically incorporate interaction data in a novel framework dTrust to predict distrust information. Experimental results using real-world data show that distrust information is predictable with interaction data by the proposed framework dTrust. Further experiments are conducted to gain a deep understand on which factors contribute to the effectiveness of the proposed framework.

Social media is a popular platform for spammers to unfairly overwhelm normal users with unwanted or fake content via social networking. The spammers significantly hinder the use of social media systems for effective information dissemination and sharing. Different from the spammers in traditional platforms such as email and the Web, spammers in social media can easily connect with each other, sometimes without mutual consent. They collude with each other to imitate normal users by quickly accumulating a large number of "human" friends. In addition, content information in social media is noisy and unstructured. It is infeasible to directly apply traditional spammer detection methods in social media. Understanding and detecting deception has been extensively studied in traditional sociology and social sciences. Motivated by psychological findings in physical world, we investigate whether sentiment analysis can help spammer detection in online social media. In particular, we first conduct an exploratory study to analyze the sentiment differences between spammers and normal users, and then present an optimization formulation that incorporates sentiment information into a novel social spammer detection framework. Experimental results on real-world social media datasets show the superior performance of the proposed framework by harnessing sentiment analysis for social spammer detection.

The pervasive use of social media generates massive data in an unprecedented rate and the information overload problem becomes increasingly severe for social media users. Recommendation has been proven to be effective in mitigating the information overload problem, demonstrated its strength in improving the quality of user experience, and positively impacted the success of social media. New types of data introduced by social media not only provide more information to advance traditional recommender systems but also manifest new research possibilities for recommendation. In this tutorial, we aim to provide a comprehensive overview of various recommendation tasks in social media, especially their recent advances and new frontiers. We introduce basic concepts, review state-of-the-art algorithms, and deliberate the emerging challenges and opportunities. Finally we summarize the tutorial with discussions on open issues and challenges about recommendation in social media. Updated information about the tutorial can be found at \url{http://www.public.asu.edu/~jtang20/Recommendation.htm}.

Personalized location recommendation is a special topic of recommendation. It is related to human mobile behavior in the real world regarding various contexts including spatial, temporal, social, and content. The development of this topic is subject to the availability of human mobile data. The recent rapid growth of location-based social networks has alleviated such limitation, which promotes the development of various location recommendation techniques. This tutorial offers an overview, in a data mining perspective, of personalized location recommendation on location-based social networks. It introduces basic concepts, summarizes unique LBSN characteristics and research opportunities, elaborates associated challenges, reviews state-of-the-art algorithms with illustrative examples and real-world LBSN datasets, and discusses effective evaluation methods.

Feature selection has been proven to be efficient in preparing high dimensional data for data mining and machine learning. As most data is unlabeled, unsupervised feature selection has attracted more and more attention in recent years. Discriminant analysis has been proven to be a powerful technique to select discriminative features for supervised feature selection. To apply discriminant analysis, we usually need label information which is absent for unlabeled data. This gap makes it challenging to apply discriminant analysis for unsupervised feature selection. In this paper, we investigate how to exploit discriminant analysis in unsupervised scenarios to select discriminative features. We introduce the concept of pseudo labels, which enable discriminant analysis on unlabeled data, propose a novel unsupervised feature selection framework DisUFS which incorporates learning discriminative features with generating pseudo labels, and develop an effective algorithm for DisUFS. Experimental results on different types of real-world data demonstrate the effectiveness of the proposed framework DisUFS.

While microblogging has emerged as an important information sharing and communication platform, it has also become a convenient venue for spammers to overwhelm other users with unwanted content. Currently, spammer detection in microblogging focuses on using social networking information, but little on content analysis due to the distinct nature of microblogging messages. First, label information is hard to obtain. Second, the texts in microblogging are short and noisy. As we know, spammer detection has been extensively studied for years in various media, e.g., emails, SMS and the web. Motivated by abundant resources available in the other media, we investigate whether we can take advantage of the existing resources for spammer detection in microblogging. While people accept that texts in microblogging are different from those in other media, there is no quantitative analysis to show how different they are. In this paper, we first perform a comprehensive linguistic study to compare spam across different media. Inspired by the findings, we present an optimization formulation that enables the design of spammer detection in microblogging using knowledge from external media. We conduct experiments on real-world Twitter datasets to verify (1) whether email, SMS and web spam resources help and (2) how different media help for spammer detection in microblogging.

Privacy and security are major concerns for many users of social media. When users share information (e.g., data and photos) with friends, they can make their friends vulnerable to security and privacy breaches with dire consequences. With the continuous expansion of a user’s social network, privacy settings alone are often inadequate to protect a user’s profile. In this research, we aim to address some critical issues related to privacy protection: (1) How can we measure and assess individual users’ vulnerability? (2) With the diversity of one’s social network friends, how can one figure out an effective approach to maintaining balance between vulnerability and social utility? In this work, first we present a novel way to define vulnerable friends from an individual user’s perspective. User vulnerability is dependent on whether or not the user’s friends’ privacy settings protect the friend and the individual’s network of friends (which includes the user). We show that it is feasible to measure and assess user vulnerability and reduce one’s vulnerability without changing the structure of a social networking site. The approach is to unfriend one’s most vulnerable friends. However, when such a vulnerable friend is also socially important, unfriending him or her would significantly reduce one’s own social status. We formulate this novel problem as vulnerability minimization with social utility constraints. We formally define the optimization problem and provide an approximation algorithm with a proven bound. Finally, we conduct a large-scale evaluation of a new framework using a Facebook dataset. We resort to experiments and observe how much vulnerability an individual user can be decreased by unfriending a vulnerable friend. We compare performance of different unfriending strategies and discuss the security risk of new friend requests. Additionally, by employing different forms of social utility, we confirm that the balance between user vulnerability and social utility can be practically achieved.

Feature selection is widely used in preparing high-dimensional data for effective data mining. The explosive popularity of social media produces massive and high-dimensional data at an unprecedented rate, presenting new challenges to feature selection. Social media data consists of (1) traditional high-dimensional, attribute-value data such as posts, tweets, comments, and images, and (2) linked data that provides social context for posts and describes the relationships between social media users as well as who generates the posts, and so on. The nature of social media also determines that its data is massive, noisy, and incomplete, which exacerbates the already challenging problem of feature selection. In this article, we study a novel feature selection problem of selecting features for social media data with its social context. In detail, we illustrate the differences between attribute-value data and social media data, investigate if linked data can be exploited in a new feature selection framework by taking advantage of social science theories. We design and conduct experiments on datasets from real-world social media Web sites, and the empirical results demonstrate that the proposed framework can significantly improve the performance of feature selection. Further experiments are conducted to evaluate the effects of user--user and user--post relationships manifested in linked data on feature selection, and research issues for future work will be discussed.

The explosive usage of social media produces massive amount of unlabeled and high-dimensional data. Feature selection has been proven to be effective in dealing with high-dimensional data for efficient learning and data mining. Unsupervised feature selection remains a challenging task due to the absence of label information based on which feature relevance is often assessed. The unique characteristics of social media data further complicate the already challenging problem of unsupervised feature selection, e.g., social media data is inherently linked, which makes invalid the independent and identically distributed assumption, bringing about new challenges to unsupervised feature selection algorithms. In this paper, we investigate a novel problem of feature selection for social media data in an unsupervised scenario. In particular, we analyze the differences between social media data and traditional attribute-value data, investigate how the relations extracted from linked data can be exploited to help select relevant features, and propose a novel unsupervised feature selection framework, LUFS, for linked social media data. We systematically design and conduct systemic experiments to evaluate the proposed framework on data sets from real-world social media Web sites. The empirical study demonstrates the effectiveness and potential of our proposed framework.

Social media expands the ways people communicate with each other. On a popular social media website, a user typically has hundreds of contacts (or friends) on average. As a person's social network grows, friend management is increasingly important for effective communications. Often, one can only afford to maintain close friendship in a small scale due to limited time and other resources. In other words, the majority of one's connections are so-so friends and do not hold strong influence on the user. One approach resorts to network denoising, by which unimportant connections are removed as noise. We study the challenges of network denoising in social media and how we can leverage a variety of social media information to denoise the links. We formulate the network denoising task as an optimization problem, and show the efficacy of our network denoising approach and its scalability experimentally in the domain of behavior inference.

The rapid growth of location-based social networks (LBSNs) invigorates an increasing number of LBSN users, providing an unprecedented opportunity to study human mobile behavior from spatial, temporal, and social aspects. Among these aspects, temporal effects offer an essential contextual cue for inferring a user's movement. Strong temporal cyclic patterns have been observed in user movement in LBSNs with their correlated spatial and social effects (i.e., temporal correlations). It is a propitious time to model these temporal effects (patterns and correlations) on a user's mobile behavior. In this paper, we present the first comprehensive study of temporal effects on LBSNs. We propose a general framework to exploit and model temporal cyclic patterns and their relationships with spatial and social data. The experimental results on two real-world LBSN datasets validate the power of temporal effects in capturing user mobile behavior, and demonstrate the ability of our framework to select the most effective location prediction algorithm under various combinations of prediction models.

Location-based social networks (LBSNs) have attracted an inordinate number of users and greatly enriched the urban experience in recent years. The availability of spatial, temporal and social information in online LBSNs offers an unprecedented opportunity to study various aspects of human behavior, and enable a variety of location-based services such as location recommendation. Previous work studied spatial and social influences on location recommendation in LBSNs. Due to the strong correlations between a user's check-in time and the corresponding check-in location, recommender systems designed for location recommendation inevitably need to consider temporal effects. In this paper, we introduce a novel location recommendation framework, based on the temporal properties of user movement observed from a real-world LBSN dataset. The experimental results exhibit the significance of temporal patterns in explaining user behavior, and demonstrate their power to improve location recommendation performance.

Online reviews play a vital role in the decision-making process for online users. Helpful reviews are usually buried in a large number of unhelpful reviews, and with the consistently increasing number of reviews, it becomes more and more difficult for online users to find helpful reviews. Therefore most online review websites allow online users to rate the helpfulness of a review and a global helpfulness score is computed for the review based on its available ratings. However, in reality, user-specified helpfulness ratings for reviews are very sparse - a few reviews attract large numbers of helpfulness ratings while most reviews obtain few or even no helpfulness ratings. The available helpfulness ratings are too sparse for online users to assess the helpfulness of reviews. Also the helpfulness of a review is not necessarily equally useful for all users and users with different background may treat the helpfulness of a review very differently. The user idiosyncracy of review helpfulness motivates us to study the problem of review helpfulness rating prediction in this paper. We first identify various types of context information, model them mathematically, and propose a context-aware review helpfulness rating prediction framework CAP. Experimental results demonstrate the effectiveness of the proposed framework and the importance of context awareness in solving the review helpfulness rating prediction problem.

The explosive popularity of social media produces mountains of high-dimensional data and the nature of social media also determines that its data is often unla-belled, noisy and partial, presenting new challenges to feature selection. Social media data can be represented by heterogeneous feature spaces in the form of multiple views. In general, multiple views can be complementary and, when used together, can help handle noisy and partial data for any single-view feature selection. These unique challenges and properties motivate us to develop a novel feature selection framework to handle multi-view social media data. In this paper, we investigate how to exploit relations among views to help each other select relevant features, and propose a novel unsupervised feature selection framework, MVFS, for multiview social media data. We systematically evaluate the proposed framework in multi-view datasets from social media websites and the results demonstrate the effectiveness and potential of MVFS.

Supervised learning, e.g., classification, plays an important role in processing and organizing microblogging data. In microblogging, it is easy to mass vast quantities of unlabeled data, but would be costly to obtain labels, which are essential for supervised learning algorithms. In order to reduce the labeling cost, active learning is an effective way to select representative and informative instances to query for labels for improving the learned model. Different from traditional data in which the instances are assumed to be independent and identically distributed (i.i.d.), instances in microblogging are networked with each other. This presents both opportunities and challenges for applying active learning to microblogging data. Inspired by social correlation theories, we investigate whether social relations can help perform effective active learning on networked data. In this paper, we propose a novel Active learning framework for the classification of Networked Texts in microblogging (ActNeT). In particular, we study how to incorporate network information into text content modeling, and design strategies to select the most representative and informative instances from microblogging for labeling by taking advantage of social network structure. Experimental results on Twitter datasets show the benefit of incorporating network information in active learning and that the proposed framework outperforms existing state-of-the-art methods.

Feature selection is widely used in preparing high-dimensional data for effective data mining. Attribute-value data in traditional feature selection differs from social media data, although both can be large-scale. Social media data is inherently not independent and identically distributed (i.i.d.), but linked. Furthermore, there is a lot of noise. The quality of social media data can vary drastically. These unique properties present challenges as well as opportunities for feature selection. Motivated by these differences, we propose a novel feature selection framework, CoSelect, for social media data. In particular, CoSelect can exploit link information by applying social correlation theories, incorporate instance selection with feature selection, and select relevant instances and features simultaneously. Experimental results on real-world social media datasets demonstrate the effectiveness of our proposed framework and its potential in mining social media data.

Microblogging, like Twitter and Sina Weibo, has become a popular platform of human expressions, through which users can easily produce content on breaking news, public events, or products. The massive amount of microblogging data is a useful and timely source that carries mass sentiment and opinions on various topics. Existing sentiment analysis approaches often assume that texts are independent and identically distributed (i.i.d.), usually focusing on building a sophisticated feature space to handle noisy and short texts, without taking advantage of the fact that the microblogs are networked data. Inspired by the social sciences findings that sentiment consistency and emotional contagion are observed in social networks, we investigate whether social relations can help sentiment analysis by proposing a Sociological Approach to handling Noisy and short Texts (SANT) for sentiment classification. In particular, we present a mathematical optimization formulation that incorporates the sentiment consistency and emotional contagion theories into the supervised learning process; and utilize sparse learning to tackle noisy texts in microblogging. An empirical study of two real-world Twitter datasets shows the superior performance of our framework in handling noisy and short tweets.

Trust plays a crucial role for online users who seek reliable information. However, in reality, user-specified trust relations are very sparse, i.e., a tiny number of pairs of users with trust relations are buried in a disproportionately large number of pairs without trust relations, making trust prediction a daunting task. As an important social concept, however, trust has received growing attention and interest. Social theories are developed for understanding trust. Homophily is one of the most important theories that explain why trust relations are established. Exploiting the homophily effect for trust prediction provides challenges and opportunities. In this paper, we embark on the challenges to investigate the trust prediction problem with the homophily effect. First, we delineate how it differs from existing approaches to trust prediction in an unsupervised setting. Next, we formulate the new trust prediction problem into an optimization problem integrated with homophily, empirically evaluate our approach on two datasets from real-world product review sites, and compare with representative algorithms to gain a deep understanding of the role of homophily in trust prediction.

The explosion of social media services presents a great opportunity to understand the sentiment of the public via analyzing its large-scale and opinion-rich data. In social media, it is easy to amass vast quantities of unlabeled data, but very costly to obtain sentiment labels, which makes unsupervised sentiment analysis essential for various applications. It is challenging for traditional lexicon-based unsupervised methods due to the fact that expressions in social media are unstructured, informal, and fast-evolving. Emoticons and product ratings are examples of emotional signals that are associated with sentiments expressed in posts or words. Inspired by the wide availability of emotional signals in social media, we propose to study the problem of unsupervised sentiment analysis with emotional signals. In particular, we investigate whether the signals can potentially help sentiment analysis by providing a unified way to model two main categories of emotional signals, i.e., emotion indication and emotion correlation. We further incorporate the signals into an unsupervised learning framework for sentiment analysis. In the experiment, we compare the proposed framework with the state-of-the-art methods on two Twitter datasets and empirically evaluate our proposed framework to gain a deep understanding of the effects of emotional signals.

Location-based social networks (LBSNs) have attracted an increasing number of users in recent years. The availability of geographical and social information of online LBSNs provides an unprecedented opportunity to study the human movement from their socio-spatial behavior, enabling a variety of location-based services. Previous work on LBSNs reported limited improvements from using the social network information for location prediction; as users can check-in at new places, traditional work on location prediction that relies on mining a user's historical trajectories is not designed for this "cold start" problem of predicting new check-ins. In this paper, we propose to utilize the social network information for solving the "cold start" location prediction problem, with a geo-social correlation model to capture social correlations on LBSNs considering social networks and geographical distance. The experimental results on a real-world LBSN demonstrate that our approach properly models the social correlations of a user's new check-ins by considering various correlation strengths and correlation measures.

The prevalent use of social media produces mountains of unlabeled, high-dimensional data. Feature selection has been shown effective in dealing with high-dimensional data for efficient data mining. Feature selection for unlabeled data remains a challenging task due to the absence of label information by which the feature relevance can be assessed. The unique characteristics of social media data further complicate the already challenging problem of unsupervised feature selection, (e.g., part of social media data is linked, which makes invalid the independent and identically distributed assumption), bringing about new challenges to traditional unsupervised feature selection algorithms. In this paper, we study the differences between social media data and traditional attribute-value data, investigate if the relations revealed in linked data can be used to help select relevant features, and propose a novel unsupervised feature selection framework, LUFS, for linked social media data. We perform experiments with real-world social media datasets to evaluate the effectiveness of the proposed framework and probe the working of its key components.

Most existing research about online trust assumes static trust relations between users. As we are informed by social sciences, trust evolves as humans interact. Little work exists studying trust evolution in an online world. Researching online trust evolution faces unique challenges because more often than not, available data is from passive observation. In this paper, we leverage social science theories to develop a methodology that enables the study of online trust evolution. In particular, we propose a framework of evolution trust, eTrust, which exploits the dynamics of user preferences in the context of online product review. We present technical details about modeling trust evolution, and perform experiments to show how the exploitation of trust evolution can help improve the performance of online applications such as rating and trust prediction.

Feature selection is widely used in preparing high-dimensional data for effective data mining. Increasingly popular social media data presents new challenges to feature selection. Social media data consists of (1) traditional high-dimensional, attribute-value data such as posts, tweets, comments, and images, and (2) linked data that describes the relationships between social media users as well as who post the posts, etc. The nature of social media also determines that its data is massive, noisy, and incomplete, which exacerbates the already challenging problem of feature selection. In this paper, we illustrate the differences between attribute-value data and social media data, investigate if linked data can be exploited in a new feature selection framework by taking advantage of social science theories, extensively evaluate the effects of user-user and user-post relationships manifested in linked data on feature selection, and discuss some research issues for future work.

Traditionally, research about trust assumes a single type of trust between users. However, trust, as a social concept, inherently has many facets indicating multiple and heterogeneous trust relationships between users. Due to the presence of a large trust network for an online user, it is necessary to discern multi-faceted trust as there are naturally experts of different types. Our study in product review sites reveals that people place trust differently to different people. Since the widely used adjacency matrix cannot capture multi-faceted trust relationships between users, we propose a novel approach by incorporating these relationships into traditional rating prediction algorithms to reliably estimate their strengths. Our work results in interesting findings such as heterogeneous pairs of reciprocal links. Experimental results on real-world data from Epinions and Ciao show that our work of discerning multi-faceted trust can be applied to improve the performance of tasks such as rating prediction, facet-sensitive ranking, and status theory.

Vector Space Model (VSM) is widely used to represent documents and web pages. It is simple and easy to deal computationally, but it also oversimplifies a document into a vector, susceptible to noise, and cannot explicitly represent underlying topics of a document. A matrix representation of document is proposed in this paper: rows represent distinct terms and columns represent cohesive segments. The matrix model views a document as a set of segments, and each segment is a probability distribution over a limited number of latent topics which can be mapped to clustering structures. The latent topic extraction based on the matrix representation of documents is formulated as a constraint optimization problem in which each matrix (i.e., a document) Aiis factorized into a common base determined by non-negative matrices L and RT, and a non-negative weight matrix Misuch that the sum of reconstruction error on all documents is minimized. Empirical evaluation demonstrates that it is feasible to use the matrix model for document clustering: (1) compared with vector representation, using matrix representation improves clustering quality consistently, and the proposed approach achieves a relative accuracy improvement up to 66% on the studied datasets, and (2) the proposed method outperforms baseline methods such as k-means and NMF, and complements the state-of-the-art methods like LDA and PLSI. Furthermore, the proposed matrix model allows more refined information retrieval at a segment level instead of at a document level, which enables the return of more relevant documents in information retrieval tasks.