Educational question generation (EQG) is a crucial component of intelligent educational systems, significantly aiding self-assessment, active learning, and personalized education. While EQG systems have emerged, existing datasets typically rely on predefined, carefully edited texts, failing to represent real-world classroom content, including lecture speech with a set of complementary slides. To bridge this gap, we collect a dataset of educational questions based on videos from real-world lectures. On this realistic dataset, we find that current methods for EQG struggle to accurately generate questions from educational videos, particularly in aligning with specific timestamps and target answers. Common challenges include selecting informative contexts from extensive transcripts and ensuring generated questions meaningfully incorporate the target answer. To address the challenges, we introduce a novel framework utilizing large language models (LLMs) for dynamically selecting and rewriting contexts based on target timestamps and answers in lecture videos. First, our framework selects contexts from both lecture transcripts and video keyframes based on answer relevance and temporal proximity. Then, we integrate the contexts selected from both modalities and rewrite them into answer-containing knowledge statements, to enhance the logical connection between the contexts and the desired answer. Quantitative evaluation and human evaluation show that our approach improves the quality and relevance of the generated questions.

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Zhaoxuan Tan, Zixuan Zhang, Haoyang Wen, Zheng Li, Rongzhi Zhang, Pei Chen, Fengran Mo, Zheyuan Liu, Qingkai Zeng, Qingyu Yin, Meng Jiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Tengchao Yang, Sichen Guo, Mengzhao Jia, Jiaming Su, Yuanyang Liu, Zhihan Zhang, Meng Jiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Collecting mobile datasets remains challenging for academic researchers due to limited data access and technical barriers. Commercial organizations often possess exclusive access to mobile data, leading to a "data monopoly" that restricts the independence of academic research. Existing open-source mobile data collection frameworks primarily focus on mobile sensing data rather than screen content, which is crucial for various research studies. We present Crepe, a no-code Android app that enables researchers to collect information displayed on screen through simple demonstrations of target data. Crepe utilizes a novel Graph Query technique which augments the structures of mobile UI screens to support flexible identification, location, and collection of specific data pieces. The tool emphasizes participants' privacy and agency by providing full transparency over collected data and allowing easy opt-out. We designed and built Crepe for research purposes only and in scenarios where researchers obtain explicit consent from participants. Code for Crepe will be open-sourced to support future academic research data collection.

Multi-turn interactions between users and information-seeking systems have become a popular paradigm to satisfy complex information needs via a flexible interface and context understanding capacity. However, existing methods primarily adapt single-turn retrieval-augmented generation (RAG) pipelines to conversational settings without effectively incorporating historical information, such as previous search results, turn dependency, and historical evidence grounding. To effectively manage and utilize the information in conversations, we explore the feasibility of boosting response generation by leveraging historical information and propose several strategies to incorporate this information individually or in combination. We conduct experiments on three widely used conversational search benchmarks, each containing thousands of samples. Our method consistently outperforms previous strong baselines across different settings, achieving approximately a 10% absolute improvement over the second-best approach. Besides, our analyses help to understand the behind-the-scenes behavior of our methods. • We investigate the feasibility of leveraging abundant historical information to improve RAG performance in conversations. • We design several training-free strategies from different aspects, that can be used individually or in combination to boost RAG performance. • We conduct thorough experiments on three datasets to demonstrate the effectiveness of our methods, and analyze the potential paradigms behind the model.

Abstract Prior works in multi-objective reinforcement learning typically use linear reward scalarization with fixed weights, which provably fail to capture non-convex Pareto fronts and thus yield suboptimal results. This limitation becomes especially critical in online preference alignment for large language models. Here, stochastic trajectories generated by parameterized policies create highly non-linear and non-convex mappings from parameters to objectives that no single static weighting scheme can find optimal trade-offs. We address this limitation by introducing dynamic reward weighting, which adaptively adjusts reward weights during the online reinforcement learning process. Unlike existing approaches that rely on fixed-weight interpolation, our dynamic weighting continuously balances and prioritizes objectives in training, facilitating effective exploration of Pareto fronts in objective space. We introduce two approaches of increasing sophistication and generalizability: hypervolume-guided weight adaptation and gradient-based weight optimization, offering a versatile toolkit for online multi-objective alignment. Our extensive experiments demonstrate their compatibility with commonly used online reinforcement learning algorithms, effectiveness across multiple datasets, and applicability to different model families, consistently achieving Pareto dominant solutions with fewer training steps than fixed-weight linear scalarization baselines.

Best-of-N decoding methods instruct large language models (LLMs) to generate multiple solutions, score each using a scoring function, and select the highest scored as the final answer to mathematical reasoning problems.However, this repeated independent process often leads to the same mistakes, making the selected solution still incorrect.We propose a novel prompting method named Stepwise Correction (STEPCO) that helps LLMs identify and revise incorrect steps in their generated reasoning paths.It iterates verification and revision phases that employ a process-supervised verifier.The verifythen-revise process not only improves answer correctness but also reduces token consumption with fewer paths needed to generate.With STEPCO, a series of LLMs demonstrate exceptional performance.Notably, using GPT-4o as the backend LLM, STEPCO achieves an average accuracy of 94.1 across eight datasets, significantly outperforming the state-of-the-art Best-of-N method by +2.4, while reducing token consumption by 77.8%.Our implementation is made publicly available at https: //wzy6642.github.io/stepco.github.io.

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang, Zhaoxuan Tan, Meng Jiang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The rapid development of Large Language Models (LLMs) has led to their widespread adoption across various domains, leveraging vast pre-training knowledge and impressive generalization capabilities. However, these models often inherit biased knowledge, resulting in unfair decisions in sensitive applications. It is challenging to remove this biased knowledge without compromising reasoning abilities due to the entangled nature of the learned knowledge within LLMs. To solve this problem, existing approaches have attempted to mitigate the bias using techniques such as fine-tuning with unbiased datasets, model merging, and gradient ascent. While these methods have experimentally proven effective, they can still be sub-optimum in fully disentangling biases from reasoning. To address this gap, we propose Selective Disentanglement Unlearning (SDU), a novel unlearning framework that selectively removes biased knowledge while preserving reasoning capabilities. SDU operates in three stages: identifying biased parameters using a shadow LLM, fine-tuning with unbiased data, and performing selective parameter updates based on weight saliency. Experimental results across multiple LLMs show that SDU improves fairness accuracy by 14.7% and enhances reasoning performance by 62.6% compared to existing baselines.

Current research on the Decompose-Then-Verify paradigm for evaluating the factuality of long-form text typically treats decomposition and verification in isolation, overlooking their interactions and potential misalignment.We find that existing decomposition policies, typically hand-crafted demonstrations, do not align well with downstream verifiers in terms of atomicity-a novel metric quantifying information density-leading to suboptimal verification results.We formulate finding the optimal decomposition policy for optimal verification as a bilevel optimization problem.To approximate a solution for this strongly NP-hard problem, we propose dynamic decomposition, a reinforcement learning framework that leverages verifier feedback to learn a policy for dynamically decomposing claims to verifier-preferred atomicity.Experimental results show that dynamic decomposition outperforms existing decomposition policies, improving verification confidence by 0.07 and accuracy by 0.12 (on a 0-1 scale) on average across varying verifiers, datasets, and atomcities of input claims.1

Fengran Mo, Yifan Gao, Chuan Meng, Xin Liu, Zhuofeng Wu, Kelong Mao, Zhengyang Wang, Pei Chen, Zheng Li, Xian Li, Bing Yin, Meng Jiang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

While the Question Generation (QG) task has been increasingly adopted in educational assessments, its evaluation remains limited by approaches that lack a clear connection to the educational values of test items.In this work, we introduce test item analysis, a method frequently used by educators to assess test question quality, into QG evaluation.Specifically, we construct pairs of candidate questions that differ in quality across dimensions such as topic coverage, item difficulty, item discrimination, and distractor efficiency.We then examine whether existing QG evaluation approaches can effectively distinguish these differences.Our findings reveal significant shortcomings in these approaches with respect to accurately assessing test item quality in relation to student performance.To address this gap, we propose a novel QG evaluation framework, QG-SMS, which leverages Large Language Model for Student Modeling and Simulation to perform test item analysis.As demonstrated in our extensive experiments and human evaluation study, the additional perspectives introduced by the simulated student profiles lead to a more effective and robust assessment of test items.

Learning from preference feedback is essential for aligning large language models (LLMs) with human values and improving the quality of generated responses. However, existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale. In this work, we present PUGC, a novel framework that leverages implicit human Preferences in unlabeled User-Generated Content (UGC) to generate preference data. Although UGC is not explicitly created to guide LLMs in generating human-preferred responses, it often reflects valuable insights and implicit preferences from its creators that has the potential to address readers’ questions. PUGC transforms UGC into user queries and generates responses from the policy model. The UGC is then leveraged as a reference text for response scoring, aligning the model with these implicit preferences. This approach improves the quality of preference data while enabling scalable, domain-specific alignment. Experimental results on Alpaca Eval 2 show that models trained with DPO and PUGC achieve a 9.37% performance improvement over traditional methods, setting a 35.93% state-of-the-art length-controlled win rate using Mistral-7B-Instruct. Further studies highlight gains in reward quality, domain-specific alignment effectiveness, robustness against UGC quality, and theory of mind capabilities. Our code and dataset are available at https://zhaoxuan.info/PUGC.github.io/.

Zixiang Xu, Yanbo Wang, Yue Huang, Xiuying Chen, Jieyu Zhao, Meng Jiang, Xiangliang Zhang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Hy Dang, Tianyi Liu, Zhuofeng Wu, Jingfeng Yang, Haoming Jiang, Tao Yang, Pei Chen, Zhengyang Wang, Helen Wang, Huasheng Li, Bing Yin, Meng Jiang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Predicting drug efficacy and safety in vivo requires information on biological responses (e.g., cell morphology and gene expression) to small molecule perturbations. However, current molecular representation learning methods do not provide a comprehensive view of cell states under these perturbations and struggle to remove noise, hindering model generalization. We introduce the Information Alignment (InfoAlign) approach to learn molecular representations through the information bottleneck method in cells. We integrate molecules and cellular response data as nodes into a context graph, connecting them with weighted edges based on chemical, biological, and computational criteria. For each molecule in a training batch, InfoAlign optimizes the encoder's latent representation with a minimality objective to discard redundant structural information. A sufficiency objective decodes the representation to align with different feature spaces from the molecule's neighborhood in the context graph. We demonstrate that the proposed sufficiency objective for alignment is tighter than existing encoder-based contrastive methods. Empirically, we validate representations from InfoAlign in two downstream applications: molecular property prediction against up to 27 baseline methods across four datasets, plus zero-shot molecule-morphology matching. The code and model are available at https://github.com/liugangcode/InfoAlign.

The data on user behaviors is sparse given the vast array of user-item combinations. Attributes related to users (e.g., age), items (e.g., brand), and behaviors (e.g., co-purchase) serve as crucial input sources for item-item transitions of user's behavior prediction. While recent Transformer-based sequential recommender systems learn the attention matrix for each attribute to update item representations, the attention of a specific attribute is optimized by gradients from all input sources, leading to potential information mixture. Besides, Transformers mainly focus on intra-sequence attention for item attributes, neglecting cross-sequence relations and user attributes. Addressing these challenges, we propose the Attribute Transformer (AttrFormer) to learn attributes as explicit relations. This model transforms each type of attribute into an explicit relation defined in the feature space, and it ensures no information mixing among different input sources. Explicit relations introduce cross-sequence and intra-sequence relations. AttrFormer has novel relation-augmented heads to handle them at both the item and behavioral levels, seamlessly integrating the augmented heads into the multi-head attention mechanism. Furthermore, we employ position-to-position aggregation to refine behavior representation for users with similar patterns at the sequence level. To capture the subjective nature of user preferences, AttrFormer is trained using posterior targets where upcoming user behaviors follow a multinomial distribution with a Dirichlet prior. Our evaluations on four popular datasets, including Amazon (Toys & Games and Beauty) and MovieLens (1M and 25M versions), reveal that AttrFormer outperforms leading Transformer baselines, achieving around 20% improvement in NDCG@20 scores. Extensive ablation studies also demonstrate the efficiency of AttrFormer in managing long behavior sequences and inter-sequence relations.

Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, Meng Jiang. 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.

Yining Lu, Dixuan Wang, Tianjian Li, Dongwei Jiang, Sanjeev Khudanpur, Meng Jiang, Daniel Khashabi. 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.

Zhihan Zhang, Shiyang Li, Zixuan Zhang, Xin Liu, Haoming Jiang, Xianfeng Tang, Yifan Gao, Zheng Li, Haodong Wang, Zhaoxuan Tan, Yichuan Li, Qingyu Yin, Bing Yin, Meng Jiang. 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.

Zifeng Zhu, Mengzhao Jia, Zhihan Zhang, Lang Li, Meng Jiang. 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.

Polymers are large macromolecules composed of repeating structural units known as monomers and are widely applied in fields such as energy storage, construction, medicine, and aerospace. However, existing graph neural network methods, though effective for small molecules, only model the single unit of polymers and fail to produce consistent vector representations for the true polymer structure with varying numbers of units. To address this challenge, we introduce Graph Repetition Invariance (GRIN), a novel method to learn polymer representations that are invariant to the number of repeating units in their graph representations. GRIN integrates a graph-based maximum spanning tree alignment with repeat-unit augmentation to ensure structural consistency. We provide theoretical guarantees for repetition‐invariance from both model and data perspectives, demonstrating that three repeating units are the minimal augmentation required for optimal invariant representation learning. GRIN outperforms state-of-the-art baselines on both homopolymer and copolymer benchmarks, learning stable, repetition-invariant representations that generalize effectively to polymer chains of unseen sizes.

ABSTRACT In recent years, intelligent control methods based on surface electromyographic signals (sEMG) have received extensive attention in the fields of bionic prosthetics and human‐computer interaction. Compared with high‐density sampling, sparse sampling sEMG has significant advantages due to its convenient collection, strong non‐intrusiveness and high equipment flexibility. However, it has deficiencies in spatial resolution and muscle activity information acquisition, which can easily lead to a decline in the recognition accuracy of complex gestures. In view of the limitations of sparse sEMG in feature extraction and channel information utilization, this paper proposes a hybrid neural network SERes‐L based on the attention mechanism. This model introduces the squeeze‐and‐excitation (SE) attention module in the residual unit to construct a residual attention structure to enhance the channel modeling of key information. At the same time, it combines the long short‐term memory network (LSTM) to capture the long‐term temporal dependencies in gesture actions, achieving a deep integration of spatial and temporal features. Experiments on the self‐built dataset show that SERes‐L achieves an average recognition accuracy rate of 93.90%. To verify its generalization ability, further tests were conducted on three public datasets, NinaPro DB1, DB4, and DB5. The average classification accuracy rates of the model reached 90.28%, 84.72%, and 91.87% respectively, significantly outperforming many existing mainstream methods. The above results indicate that the proposed SERes‐L architecture can effectively alleviate the challenges of insufficient utilization of channel information and inadequate feature extraction in sparse sEMG, demonstrating excellent generalization performance and practical application potential.

The scaling laws have become the de facto guidelines for designing large language models (LLMs), but they were studied under the assumption of unlimited computing resources for both training and inference. As LLMs are increasingly used as personalized intelligent assistants, their customization (i.e., learning through fine-tuning) and deployment onto resource-constrained edge devices will become more and more prevalent. An urgent but open question is how a resource-constrained computing environment would affect the design choices for a personalized LLM. We study this problem empirically in this work. In particular, we consider the tradeoffs among a number of key design factors and their intertwined impacts on learning efficiency and accuracy. The factors include the learning methods for LLM customization, the amount of personalized data used for learning customization, the types and sizes of LLMs, the compression methods of LLMs, the amount of time afforded to learn, and the difficulty levels of the target use cases. Through extensive experimentation and benchmarking, we draw a number of surprisingly insightful guidelines for deploying LLMs onto resource-constrained devices. For example, an optimal choice between parameter learning and RAG may vary depending on the difficulty of the downstream task, the longer fine-tuning time does not necessarily help the model, and a compressed LLM may be a better choice than an uncompressed LLM to learn from limited personalized data.

Chain-of-Thought (CoT) prompting methods have enabled large language models (LLMs) to generate reasoning paths and solve math word problems (MWPs). However, they are sensitive to mistakes in the paths, as any mistake can result in an incorrect answer. We propose a novel method named Progressive Rectification Prompting (PRP) to improve average accuracy on eight MWP datasets from 77.3 to 90.5. Given an initial answer from CoT, PRP iterates a verify-then-rectify process to progressively identify incorrect answers and rectify the reasoning paths. With the most likely correct answer, the LLM predicts a masked numerical value in the question; if the prediction does not match the masked value, the answer is likely incorrect. Then the LLM is prompted to re-generate the reasoning path hinted with a set of incorrect answers to prevent itself from repeating previous mistakes. PRP achieves the best performance compared against the CoT methods. Our implementation is made publicly available at https://wzy6642.github.io/prp.github.io/.

Zhihan Zhang, Dong-Ho Lee, Yuwei Fang, Wenhao Yu, Mengzhao Jia, Meng Jiang, Francesco Barbieri. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Automatic taxonomy induction is crucial for web search, recommendation systems, and question answering. Manual curation of taxonomies is expensive in terms of human effort, making automatic taxonomy construction highly desirable. In this work, we introduce Chain-of-Layer which is an in-context learning framework designed to induct taxonomies from a given set of entities. Chain-of-Layer breaks down the task into selecting relevant candidate entities in each layer and gradually building the taxonomy from top to bottom. To minimize errors, we introduce the Ensemble-based Ranking Filter to reduce the hallucinated content generated at each iteration. Through extensive experiments, we demonstrate that Chain-of-Layer achieves state-of-the-art performance on four real-world benchmarks. Source code available at: https://github.com/qingkaizeng/chain-of-layer.

Current face recognition (FR) algorithms frequently encounter discrimination issues in terms of various attributes (e.g., gender, age) due to the biased demographic distribution of the training datasets towards specific groups. In this paper, we study an identity protected fair FR problem where the goal is to augment the datasets with external face images while ensuring the anonymity of the corresponding face identities. Our problem is motivated by the limitation of current fairness driven data augmentation approaches that directly utilize the external face images accessed by FR algorithm developers while ignoring the protection on the face identities of the image owners. To address the problem, we develop FaDE, a face segment driven identity anonymization framework that augments biased face image datasets by identifying specific face segments with diversified demographic characteristics from external face images but with least identity disclosure, and then reconstructing the segments to full face images with new identities. As a result, the augmented dataset is under a more balanced demographic distribution and improves the fairness performance of the optimized FR algorithms. We evaluate FaDE on two public face datasets, CelebA and LFW that suffer from various demographic imbalance. The results show that FaDE significantly enhances both fairness and accuracy performance of the optimized FR algorithms, while keeping effective anonymity for the identities of external face images.

After a large language model (LLM) is deployed on edge devices, it is desirable for these devices to learn from user-generated conversation data to generate user-specific and personalized responses in real-time. However, user-generated data usually contains sensitive and private information, and uploading such data to the cloud for annotation is not preferred if not prohibited. While it is possible to obtain annotation locally by directly asking users to provide preferred responses, such annotations have to be sparse to not affect user experience. In addition, the storage of edge devices is usually too limited to enable large-scale fine-tuning with full user-generated data. It remains an open question how to enable on-device LLM personalization, considering sparse annotation and limited on-device storage. In this paper, we propose a novel framework to select and store the most representative data online in a self-supervised way. Such data has a small memory footprint and allows infrequent requests of user annotations for further fine-tuning. To enhance fine-tuning quality, multiple semantically similar pairs of question texts and expected responses are generated using the LLM. Our experiments show that the proposed framework achieves the best user-specific content-generating capability (accuracy) and fine-tuning speed (performance) compared with vanilla baselines. To the best of our knowledge, this is the very first on-device LLM personalization framework.

Intrinsic self-correct was a method that instructed large language models (LLMs) to verify and correct their responses without external feedback.Unfortunately, the study concluded that the LLMs could not self-correct reasoning yet.We find that a simple yet effective prompting method enhances LLM performance in identifying and correcting inaccurate answers without external feedback.That is to mask a key condition in the question, add the current response to construct a verification question, and predict the condition to verify the response.The condition can be an entity in an open-domain question or a numerical value in an arithmetic question, which requires minimal effort (via prompting) to identify.We propose an iterative verify-then-correct framework to progressively identify and correct (probably) false responses, named PROCO.We conduct experiments on three reasoning tasks.On average, PROCO, with GPT-3.5-Turbo-1106 as the backend LLM, yields +6.8 exact match on four open-domain question answering datasets, +14.1 accuracy on three arithmetic reasoning datasets, and +9.6 accuracy on a commonsense reasoning dataset, compared to Self-Correct.Our implementation is made publicly avail

Text-to-image prompt refinement (T2I-Refine) aims to rephrase or extend an input prompt with more descriptive details that can be leveraged to generate images with higher quality.In this paper, we study an adversarial prompt attacking problem for T2I-Refine, where to goal is to implicitly inject specific concept bias to the input prompts during the refinement process so that the generated images, still with higher quality, are explicitly biased to the target group.Our study is motivated by the limitation of current T2I-Refine research that lacks of explorations on the potential capacity of T2I-Refine models to provide prompt refinement service in a biased or advertising manner.To address the limitations, we develop RAt, a prompt refinement and attacking framework that attacks input prompts with intentionally selected adversarial replacements by optimizing a token distribution matrix based on the text-to-image finetuning strategy with a tokenlevel bias obfuscation loss as regularization.We evaluate RAt on a large-scale text-to-image dataset with various concepts as target in both in-domain and transfer-domain scenarios.The evaluation results demonstrate that, compared to other T2I-Refine schemes, RAt is well capable of implicitly attacking input prompts to generate images with higher quality and explicit visual bias towards specific concept group.

Personalization in large language models (LLMs) is increasingly important, aiming to align the LLMs' interactions, content, and recommendations with individual user preferences.Recent advances have highlighted effective prompt design by enriching user queries with non-parametric knowledge through behavior history retrieval and textual profiles.However, these methods faced limitations due to a lack of model ownership, resulting in constrained customization and privacy issues, and often failed to capture complex, dynamic user behavior patterns.To address these shortcomings, we introduce One PEFT Per User (OPPU) 1 , employing personalized parameter-efficient finetuning (PEFT) modules to store user-specific behavior patterns and preferences.By plugging in personal PEFT parameters, users can own and use their LLMs individually.OPPU integrates parametric user knowledge in the personal PEFT parameters with non-parametric knowledge from retrieval and profiles, adapting LLMs to user behavior shifts.Experimental results demonstrate that OPPU significantly outperforms existing prompt-based methods across seven diverse tasks in the LaMP benchmark.Further studies reveal OPPU's enhanced capabilities in handling user behavior shifts, modeling users at different activity levels, maintaining robustness across various user history formats, and displaying versatility with different PEFT methods.

Personalized large language models (LLMs) aim to tailor interactions, content, and recommendations to individual user preferences.While parameter-efficient fine-tuning (PEFT) methods excel in performance and generalization, they are costly and limit communal benefits when used individually.To this end, we introduce PERSONALIZED PIECES (PER-PCS) 1 , a framework that allows users to safely share and assemble personalized PEFT efficiently with collaborative efforts.PER-PCS involves selecting sharers, breaking their PEFT into pieces, and training gates for each piece.These pieces are added to a pool, from which target users can select and assemble personalized PEFT using their history data.This approach preserves privacy and enables fine-grained user modeling without excessive storage and computation demands.Experimental results show PER-PCS outperforms non-personalized and PEFT retrieval baselines, offering performance comparable to OPPU with significantly lower resource use across six tasks.Further analysis highlights PER-PCS's robustness concerning sharer count and selection strategy, pieces sharing ratio, and scalability in computation time and storage space.PER-PCS's modularity promotes safe sharing, making LLM personalization more efficient, effective, and widely accessible through collaborative efforts.

Supervised fine-tuning enhances the problemsolving abilities of language models across various mathematical reasoning tasks.To maximize such benefits, existing research focuses on broadening the training set with various data augmentation techniques, which is effective for standard single-round question-answering settings.Our work introduces a novel technique aimed at cultivating a deeper understanding of the training problems at hand, enhancing performance not only in standard settings but also in more complex scenarios that require reflective thinking.Specifically, we propose reflective augmentation, a method that embeds problem reflection into each training instance.It trains the model to consider alternative perspectives and engage with abstractions and analogies, thereby fostering a thorough comprehension through reflective reasoning.Extensive experiments validate the achievement of our aim, underscoring the unique advantages of our method and its complementary nature relative to existing augmentation techniques. 1 Question Answer Question

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.

Zhenyu Wu, Chao Shen, Meng Jiang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Online shopping is a complex multi-task, few-shot learning problem with a wide and evolving range of entities, relations, and tasks. However, existing models and benchmarks are commonly tailored to specific tasks, falling short of capturing the full complexity of online shopping. Large Language Models (LLMs), with their multi-task and few-shot learning abilities, have the potential to profoundly transform online shopping by alleviating task-specific engineering efforts and by providing users with interactive conversations. Despite the potential, LLMs face unique challenges in online shopping, such as domain-specific concepts, implicit knowledge, and heterogeneous user behaviors. Motivated by the potential and challenges, we propose Shopping MMLU, a diverse multi-task online shopping benchmark derived from real-world Amazon data. Shopping MMLU consists of 57 tasks covering 4 major shopping skills: concept understanding, knowledge reasoning, user behavior alignment, and multi-linguality, and can thus comprehensively evaluate the abilities of LLMs as general shop assistants. With Shoppping MMLU, we benchmark over 20 existing LLMs and uncover valuable insights about practices and prospects of building versatile LLM-based shop assistants. Shopping MMLU can be publicly accessed at https://github.com/KL4805/ShoppingMMLU. In addition, with Shopping MMLU, we are hosting a competition in KDD Cup 2024 with over 500 participating teams. The winning solutions and the associated workshop can be accessed at our website https://amazon-kddcup24.github.io/.

Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data. Existing models were designed for the nodes on a single graph, which would not be able to utilize information across multiple graphs. The real world does have multiple graphs where the nodes are often partially aligned . For examples, knowledge graphs share a number of named entities though they may have different relation schema; collaboration networks on publications and awarded projects share some researcher nodes who are authors and investigators, respectively; people use multiple web services, shopping, tweeting, rating movies, and some may register the same e-mail account across the platforms. In this article, we propose partially aligned graph convolutional networks to learn node representations across the models. We provide multiple methods such as model sharing, regularization, and alignment reconstruction, as well as theoretical analysis to positively transfer knowledge across the set of partially aligned nodes. Extensive experiments on real-world knowledge graphs, collaboration networks, and bipartite rating graphs show the superior performance of our proposed methods on relation classification, link prediction, and item recommendation.

Graph rationales are representative subgraph structures that best explain and support the graph neural network (GNN) predictions. Graph rationalization involves the joint identification of these subgraphs during GNN training, resulting in improved interpretability and generalization. GNN is widely used for node-level tasks such as paper classification and graph-level tasks such as molecular property prediction. However, on both levels, little attention has been given to GNN rationalization and the lack of training examples makes it difficult to identify the optimal graph rationales. In this work, we address the problem by proposing a unified data augmentation framework with two novel operations on environment subgraphs to rationalize GNN prediction. We define the environment subgraph as the remaining subgraph after rationale identification and separation. The framework efficiently performs rationale–environment separation in the representation space for a node’s neighborhood graph or a graph’s complete structure to avoid the high complexity of explicit graph decoding and encoding. We conduct experiments on 17 datasets spanning node classification, graph classification, and graph regression. Results demonstrate that our framework is effective and efficient in rationalizing and enhancing GNNs for different levels of tasks on graphs.

Large language models (LLMs), such as GPT4 and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs are mainly designed to process pure texts, there are many real-world scenarios where text data is associated with rich structure information in the form of graphs (e.g., academic networks, and e-commerce networks) or scenarios where graph data is paired with rich textual information (e.g., molecules with descriptions). Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graphs (i.e., graph-based reasoning). In this paper, we provide a systematic review of scenarios and techniques related to large language models on graphs. We first summarize potential scenarios of adopting LLMs on graphs into three categories, namely pure graphs, text-attributed graphs, and text-paired graphs. We then discuss detailed techniques for utilizing LLMs on graphs, including LLM as Predictor, LLM as Encoder, and LLM as Aligner, and compare the advantages and disadvantages of different schools of models. Furthermore, we discuss the real-world applications of such methods and summarize open-source codes and benchmark datasets. Finally, we conclude with potential future research directions in this fast-growing field.

Multi-task learning (MTL) has become increasingly popular in natural language processing (NLP) because it improves the performance of related tasks by exploiting their commonalities and differences.Nevertheless, it is still not understood very well how multi-task learning can be implemented based on the relatedness of training tasks.In this survey, we review recent advances of multi-task learning methods in NLP, with the aim of summarizing them into two general multi-task training methods based on their task relatedness: (i) joint training and (ii) multi-step training.We present examples in various NLP downstream applications, summarize the task relationships and discuss future directions of this promising topic.

Although counterfactual reasoning is a fundamental aspect of intelligence, the lack of largescale counterfactual open-domain questionanswering (QA) benchmarks makes it difficult to evaluate and improve models on this ability.To address this void, we introduce the first such dataset, named IfQA, where each question is based on a counterfactual presupposition via an "if" clause.Such questions require models to go beyond retrieving direct factual knowledge from the Web: they must identify the right information to retrieve and reason about an imagined situation that may even go against the facts built into their parameters.The IfQA dataset contains 3,800 questions that were annotated by crowdworkers on relevant Wikipedia passages.Empirical analysis reveals that the IfQA dataset is highly challenging for existing open-domain QA methods, including supervised retrieve-then-read pipeline methods (F1 score 44.5), as well as recent few-shot approaches such as chain-of-thought prompting with ChatGPT (F1 score 57.2).We hope the unique challenges posed by IfQA will push open-domain QA research on both retrieval and reasoning fronts, while also helping endow counterfactual reasoning abilities to today's language understanding models.The IfQA dataset can be found and downloaded at https://allenai.org/data/ifqa.

Comparative reasoning is a process of comparing objects, concepts, or entities to draw conclusions, which constitutes a fundamental cognitive ability.In this paper, we propose a novel framework to pre-train language models for enhancing their abilities of comparative reasoning over texts.While there have been approaches for NLP tasks that require comparative reasoning, they suffer from costly manual data labeling and limited generalizability to different tasks.Our approach introduces a novel method of collecting scalable data for text-based entity comparison, which leverages both structured and unstructured data.Moreover, we present a framework of pre-training language models via three novel objectives on comparative reasoning.Evaluation on downstream tasks including comparative question answering, question generation, and summarization shows that our pre-training framework significantly improves the comparative reasoning abilities of language models, especially under low-resource conditions.This work also releases the first integrated benchmark for comparative reasoning.

Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph datasets are often small because labeling them requires expensive equipment and effort. To address the lack of examples of rare label values in graph regression tasks, we propose a semi-supervised framework to progressively balance training data and reduce model bias via self-training. The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels. The former is to identify quality examples from unlabeled data whose labels are confidently predicted and sample a subset of them with a reverse distribution from the imbalanced annotated data. The latter collaborates with the former to target a perfect balance using a novel label-anchored mixup algorithm. We perform experiments in seven regression tasks on graph datasets. Results demonstrate that the proposed framework significantly reduces the error of predicted graph properties, especially in under-represented label areas.

Language models are being developed and deployed in many applications, "small"-scale and large-scale, generic and specialized, text-only and multimodal, etc. Meanwhile, the missingness of important knowledge causes limitations and safety challenges. The knowledge includes commonsense, world facts, domain expertise, personalization, and especially the unique patterns that need to be discovered from big data applications. Training and inference processes of the language models can be and should be augmented with the knowledge. The first KnowledgeNLP at AAAI 2023 attracted scientists on knowledge augmentation methods towards higher language intelligence. This workshop offers a broad platform to share ideas and discuss various topics, such as (1) synergy between knowledge and language model, (2) scalable architectures that integrate NLP, knowledge graph, and graph learning technologies, (3) KnowledgeNLP for e-commerce, education, and healthcare, (4) human factors and social good in KnowledgeNLP.

Modern machine learning techniques, especially deep neural networks, have demonstrated excellent performance for various knowledge discovery and data mining applications. However, the development of many of these techniques still encounters resource constraint challenges in many scenarios, such as limited labeled data (data-level), small model size requirements in real-world computing platforms (model-level), and efficient mapping of the computations to heterogeneous target hardware (system-level). Addressing all of these metrics is critical for the effective and efficient usage of the developed models in a wide variety of real systems, such as large-scale social network analysis, large-scale recommendation systems, and real-time anomaly detection. Therefore, it is desirable to develop efficient learning techniques to tackle challenges of resource limitations from data, model/algorithm, or (and) system/hardware perspectives. The proposed international workshop on "Resource-Efficient Learning for Knowledge Discovery (RelKD 2023)" will provide a great venue for academic researchers and industrial practitioners to share challenges, solutions, and future opportunities of resource-efficient learning.

Graph property prediction tasks are important and numerous. While each task offers a small size of labeled examples, unlabeled graphs have been collected from various sources and at a large scale. A conventional approach is training a model with the unlabeled graphs on self-supervised tasks and then fine-tuning the model on the prediction tasks. However, the self-supervised task knowledge could not be aligned or sometimes conflicted with what the predictions needed. In this paper, we propose to extract the knowledge underlying the large set of unlabeled graphs as a specific set of useful data points to augment each property prediction model. We use a diffusion model to fully utilize the unlabeled graphs and design two new objectives to guide the model's denoising process with each task's labeled data to generate task-specific graph examples and their labels. Experiments demonstrate that our data-centric approach performs significantly better than fifteen existing various methods on fifteen tasks. The performance improvement brought by unlabeled data is visible as the generated labeled examples unlike the self-supervised learning.

Knowledge in NLP has been a rising trend especially after the advent of large-scale pre-trained models. Knowledge is critical to equip statistics-based models with common sense, logic and other external information. In this tutorial, we will introduce recent state-of-the-art works in applying knowledge in language understanding, language generation and commonsense reasoning.

Abstract Contrast consistency, the ability of a model to make consistently correct predictions in the presence of perturbations, is an essential aspect in NLP. While studied in tasks such as sentiment analysis and reading comprehension, it remains unexplored in open-domain question answering (OpenQA) due to the difficulty of collecting perturbed questions that satisfy factuality requirements. In this work, we collect minimally edited questions as challenging contrast sets to evaluate OpenQA models. Our collection approach combines both human annotation and large language model generation. We find that the widely used dense passage retriever (DPR) performs poorly on our contrast sets, despite fitting the training set well and performing competitively on standard test sets. To address this issue, we introduce a simple and effective query-side contrastive loss with the aid of data augmentation to improve DPR training. Our experiments on the contrast sets demonstrate that DPR’s contrast consistency is improved without sacrificing its accuracy on the standard test sets.1

Most graph neural network models learn embeddings of nodes in static attributed graphs for predictive analysis. Recent attempts have been made to learn temporal proximity of the nodes. We find that real dynamic attributed graphs exhibit complex phenomenon of co-evolution between node attributes and graph structure. Learning node embeddings for forecasting change of node attributes and evolution of graph structure over time remains an open problem. In this work, we present a novel framework called CoEvoGNN for modeling dynamic attributed graph sequence. It preserves the impact of earlier graphs on the current graph by embedding generation through the sequence of attributed graphs. It has a temporal self-attention architecture to model long-range dependencies in the evolution. Moreover, CoEvoGNN optimizes model parameters jointly on two dynamic tasks, attribute inference and link prediction over time. So the model can capture the co-evolutionary patterns of attribute change and link formation. This framework can adapt to any graph neural algorithms so we implemented and investigated three methods based on it: CoEvoGCN, CoEvoGAT, and CoEvoSAGE. Experiments demonstrate the framework (and its methods) outperforms strong baseline methods on predicting an entire unseen graph snapshot of personal attributes and interpersonal links in dynamic social graphs and financial graphs.

Complementarity plays a significant role in the synergistic effect created by different components of a complex data object. Complementarity learning on multimodal data has fundamental challenges of representation learning because the complementarity exists along with multiple modalities and one or multiple items of each modality. Also, an appropriate metric is needed for measuring the complementarity in the representation space. Existing methods that rely on similarity-based metrics cannot adequately capture the complementarity. In this work, we propose a novel deep architecture for systematically learning the complementarity of components from multimodal multi-item data. The proposed model consists of three major modules: 1) unimodal aggregation for extracting the intramodal complementarity; 2) cross-modal fusion for extracting the intermodal complementarity at the modality level; and 3) interactive aggregation for extracting the intermodal complementarity at the item level. To quantify complementarity, we utilize the TUBE distance metric to measure the difference between the composited data object and its label in the representation space. Experiments on three real datasets show that our model outperforms the state-of-the-art by +6.8% of mean reciprocal rank (MRR) on object classification and +3.0% of MRR on hold-out item prediction. Qualitative analyses reveal that complementarity is significantly different from similarity.

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled.However, applying such methods to commonsense reasoning tasks faces two unique challenges, i.e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever.In this paper, we systematically investigate how to leverage commonsense knowledge retrieval to improve commonsense reasoning tasks.We proposed a unified framework of Retrieval-Augmented Commonsense reasoning (called RACO), including a newly constructed commonsense corpus with over 20 million documents and novel strategies for training a commonsense retriever.We conducted experiments on four different commonsense reasoning tasks.Extensive evaluation results showed that our proposed RACO can significantly outperform other knowledgeenhanced method counterparts, achieving new SoTA performance on the CommonGen 1 and CREAK 2 leaderboards.Our code is available at https://github.com/wyu97/RACo.

Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks.We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation.Existing approaches tried to index, retrieve, and read external documents as evidence, but they suffered from a large computational overhead.In this work, we propose an Encoder-Decoder framework with an entity Memory, namely EDMem.The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters.To precisely generate entity names, we design three decoding methods to constrain entity generation by linking entities in the memory.EDMem is a unified framework that can be used on various entity-intensive question answering and generation tasks.Extensive experimental results show that EDMem outperforms both memory-based auto-encoder models and non-memory encoder-decoder models.

Learning to predict missing links is important for many graph-based applications. Existing methods were designed to learn the association between observed graph structure and existence of link between a pair of nodes. However, the causal relationship between the two variables was largely ignored for learning to predict links on a graph. In this work, we visit this factor by asking a counterfactual question: "would the link still exist if the graph structure became different from observation?" Its answer, counterfactual links, will be able to augment the graph data for representation learning. To create these links, we employ causal models that consider the information (i.e., learned representations) of node pairs as context, global graph structural properties as treatment, and link existence as outcome. We propose a novel data augmentation-based link prediction method that creates counterfactual links and learns representations from both the observed and counterfactual links. Experiments on benchmark data show that our graph learning method achieves state-of-the-art performance on the task of link prediction.

Automatic product description generation for e-commerce has witnessed significant advancement in the past decade. Product copy- writing aims to attract users' interest and improve user experience by highlighting product characteristics with textual descriptions. As the services provided by e-commerce platforms become diverse, it is necessary to adapt the patterns of automatically-generated descriptions dynamically. In this paper, we report our experience in deploying an E-commerce Prefix-based Controllable Copywriting Generation (EPCCG) system into the JD.com e-commerce product recommendation platform. The development of the system contains two main components: 1) copywriting aspect extraction; 2) weakly supervised aspect labelling; 3) text generation with a prefix-based language model; and 4) copywriting quality control. We conduct experiments to validate the effectiveness of the proposed EPCCG. In addition, we introduce the deployed architecture which cooperates the EPCCG into the real-time JD.com e-commerce recommendation platform and the significant payoff since deployment. The codes for implementation are provided at https://github.com/xguo7/Automatic-Controllable-Product-Copywriting-for-E-Commerce.git.

The MIS2-TrueFact is geared towards bringing academic, industry, and government researchers and practitioners together to tackle the challenges in misinformation, misbehavior, and data quality issues on the web with heterogeneous and multi-modal sources of information including texts, images, videos, relational data, social networks, and knowledge graphs.

Rationale is defined as a subset of input features that best explains or supports the prediction by machine learning models. Rationale identification has improved the generalizability and interpretability of neural networks on vision and language data. In graph applications such as molecule and polymer property prediction, identifying representative subgraph structures named as graph rationales plays an essential role in the performance of graph neural networks. Existing graph pooling and/or distribution intervention methods suffer from the lack of examples to learn to identify optimal graph rationales. In this work, we introduce a new augmentation operation called environment replacement that automatically creates virtual data examples to improve rationale identification. We propose an efficient framework that performs rationale-environment separation and representation learning on the real and augmented examples in latent spaces to avoid the high complexity of explicit graph decoding and encoding. Comparing against recent techniques, experiments on seven molecular and four polymer datasets demonstrate the effectiveness and efficiency of the proposed augmentation-based graph rationalization framework. Data and the implementation of the proposed framework are publicly available https://github.com/liugangcode/GREA.

MOTIVATION: Prediction of node and graph labels are prominent network science tasks. Data analyzed in these tasks are sometimes related: entities represented by nodes in a higher-level (higher scale) network can themselves be modeled as networks at a lower level. We argue that systems involving such entities should be integrated with a 'network of networks' (NoNs) representation. Then, we ask whether entity label prediction using multi-level NoN data via our proposed approaches is more accurate than using each of single-level node and graph data alone, i.e. than traditional node label prediction on the higher-level network and graph label prediction on the lower-level networks. To obtain data, we develop the first synthetic NoN generator and construct a real biological NoN. We evaluate accuracy of considered approaches when predicting artificial labels from the synthetic NoNs and proteins' functions from the biological NoN. RESULTS: For the synthetic NoNs, our NoN approaches outperform or are as good as node- and network-level ones depending on the NoN properties. For the biological NoN, our NoN approaches outperform the single-level approaches for just under half of the protein functions, and for 30% of the functions, only our NoN approaches make meaningful predictions, while node- and network-level ones achieve random accuracy. So, NoN-based data integration is important. AVAILABILITY AND IMPLEMENTATION: The software and data are available at https://nd.edu/~cone/NoNs. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Distributed surveillance systems have the ability to detect, track, and snapshot objects moving around in a certain space. The systems generate video data from multiple personal devices or street cameras. Intelligent video-analysis models are needed to learn dynamic representation of the objects for detection and tracking. Can we exploit the structural and dynamic information without storing the spatiotemporal video data at a central server that leads to a violation of user privacy? In this work, we introduce Federated Dynamic Graph Neural Network (Feddy), a distributed and secured framework to learn the object representations from graph sequences: (1) It aggregates structural information from nearby objects in the current graph as well as dynamic information from those in the previous graph. It uses a self-supervised loss of predicting the trajectories of objects. (2) It is trained in a federated learning manner. The centrally located server sends the model to user devices. Local models on the respective user devices learn and periodically send their learning to the central server without ever exposing the user’s data to server. (3) Studies showed that the aggregated parameters could be inspected though decrypted when broadcast to clients for model synchronizing, after the server performed a weighted average. We design an appropriate aggregation mechanism of secure aggregation primitives that can protect the security and privacy in federated learning with scalability. Experiments on four video camera datasets as well as simulation demonstrate that Feddy achieves great effectiveness and security.

Online medical consult and offline medical check-in have generated a large amount of health-related data in medical forums and patient records. However, exploiting the user-generated content for orienting patients online and assisting medical checkup offline is nontrivial due to the sparsity of symptom-disease associations. The serious sparsity is caused by the informal/chatty expressions of symptoms in the data.

Detecting anomalies on graph data has two types of methods. One is pattern mining that discovers strange structures globally such as quasi-cliques, bipartite cores, or dense blocks in the graph's adjacency matrix. The other is feature learning that mainly uses graph neural networks (GNNs) to aggregate information from local neighborhood into node representations. However, there is a lack of study that utilizes both the global and local information for graph anomaly detection. In this article, we propose a synergistic approach that leverages pattern mining to inform the GNN algorithms on how to aggregate local information through connections to capture the global patterns. Specifically, it uses a GNN encoder to perform feature aggregation, and the pattern mining algorithms supervise the GNN training process through a novel loss function. We provide theoretical analysis on the effectiveness of the loss function, as well as empirical analysis on the proposed approach across a variety of GNN algorithms and pattern mining methods. Experiments on real-world data show that the synergistic approach performs significantly better than existing graph anomaly detection methods.

Data augmentation has been widely used to improve generalizability of machine learning models. However, comparatively little work studies data augmentation for graphs. This is largely due to the complex, non-Euclidean structure of graphs, which limits possible manipulation operations. Augmentation operations commonly used in vision and language have no analogs for graphs. Our work studies graph data augmentation for graph neural networks (GNNs) in the context of improving semi-supervised node-classification. We discuss practical and theoretical motivations, considerations and strategies for graph data augmentation. Our work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra-class edges and demote inter-class edges in given graph structure, and our main contribution introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction. Extensive experiments on multiple benchmarks show that augmentation via GAug improves performance across GNN architectures and datasets.

The proliferation of web platforms has created incentives for online abuse. Many graph-based anomaly detection techniques are proposed to identify the suspicious accounts and behaviors. However, most of them detect the anomalies once the users have performed many such behaviors. Their performance is substantially hindered when the users' observed data is limited at an early stage, which needs to be improved to minimize financial loss. In this work, we propose Eland, a novel framework that uses action sequence augmentation for early anomaly detection. Eland utilizes a sequence predictor to predict next actions of every user and exploits the mutual enhancement between action sequence augmentation and user-action graph anomaly detection. Experiments on three real-world datasets show that Eland improves the performance of a variety of graph-based anomaly detection methods. With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.

Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG).Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and to generate coherent content.To enhance the role of entity in NLG, in this paper, we aim to model the entity type in the decoding phase to generate contextual words accurately.We develop a novel NLG model to produce a target sequence based on a given list of entities.Our model has a multistep decoder that injects the entity types into the process of entity mention generation.Experiments on two public news datasets demonstrate type injection performs better than existing type embedding concatenation baselines.

Generating paragraphs of diverse contents is important in many applications.Existing generation models produce similar contents from homogenized contexts due to the fixed left-toright sentence order.Our idea is permuting the sentence orders to improve the content diversity of multi-sentence paragraph.We propose a novel framework PermGen whose objective is to maximize the expected log-likelihood of output paragraph distributions with respect to all possible sentence orders.PermGen uses hierarchical positional embedding and designs new procedures for both training phase and inference phase.Experiments on three paragraph generation benchmarks demonstrate Per-mGen generates more diverse outputs with a higher quality than existing models.

Graph representation learning aims at preserving structural and attributed information in latent representations. It has been studied mostly in the setting of static graph. In this work, we propose a novel approach for representation learning over dynamic attributed graph using the tool of normalizing flows for exact density estimation. Our approach has three components: (1) a time-aware graph neural component for aggregating graph information at each time step, (2) an adapted graph recurrent component for updating graph temporal contexts, and (3) a conditional normalizing flows component for capturing the evolution of node representations in latent space along time. Particularly, the third component has two sub-models of normalizing flows. One is used to capture the distribution of node representations of arbitrary complexity by considering graph temporal contexts as conditions. It learns invertible transformations to map node representations into simple priors conditioning on temporal contexts. The other one is dedicated to capture the evolutionary patterns of prior distributions. Extensive experiments demonstrate the proposed approach can outperform competitive baselines by a significant margin for dynamic link prediction on future graphs.

Software traceability establishes and leverages associations between diverse development artifacts. Researchers have proposed the use of deep learning trace models to link natural language artifacts, such as requirements and issue descriptions, to source code; however, their effectiveness has been restricted by availability of labeled data and efficiency at runtime. In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts. To address data sparsity, we leverage a three-step training strategy to enable trace models to transfer knowledge from a closely related Software Engineering challenge, which has a rich dataset, to produce trace links with much higher accuracy than has previously been achieved. We then apply the T-BERT framework to recover links between issues and commits in Open Source Projects. We comparatively evaluated accuracy and efficiency of three BERT architectures. Results show that a Single-BERT architecture generated the most accurate links, while a Siamese-BERT architecture produced comparable results with significantly less execution time. Furthermore, by learning and transferring knowledge, all three models in the framework outperform classical IR trace models. On the three evaluated real-word OSS projects, the best T-BERT stably outperformed the VSM model with average improvements of 60.31% measured using Mean Average Precision (MAP). RNN severely underperformed on these projects due to insufficient training data, while T-BERT overcame this problem by using pretrained language models and transfer learning.

Misinformation and misbehavior mining on the web (MIS2) workshop is held virtually on August 14, 2021 and is co-located with the ACM SIGKDD 2021 conference. The web has become a breeding ground for misbehavior and misinformation. It is timely and crucial to understand, detect, forecast, and mitigate their harm. MIS2 workshop as an interdisciplinary venue for researchers and practitioners who study the dark side of the web. The workshop program includes a peer-reviewed set of paper presentations and keynote talks, giving the attendees an immersive experience of this research field.

Graph neural networks have been widely used for learning representations of nodes for many downstream tasks on graph data. Existing models were designed for the nodes on a single graph, which would not be able to utilize information across multiple graphs. The real world does have multiple graphs where the nodes are often partially aligned. For examples, knowledge graphs share a number of named entities though they may have different relation schema; collaboration networks on publications and awarded projects share some researcher nodes who are authors and investigators, respectively; people use multiple web services, shopping, tweeting, rating movies, and some may register the same email account across the platforms. In this paper, I propose partially aligned graph convolutional networks to learn node representations across the models. I investigate multiple methods (including model sharing, regularization, and alignment reconstruction) as well as theoretical analysis to positively transfer knowledge across the (small) set of partially aligned nodes. Extensive experiments on real-world knowledge graphs and collaboration networks show the superior performance of our proposed methods on relation classification and link prediction.

Automatic construction of a taxonomy supports many applications in e-commerce, web search, and question answering. Existing taxonomy expansion or completion methods assume that new concepts have been accurately extracted and their embedding vectors learned from the text corpus. However, one critical and fundamental challenge in fixing the incompleteness of taxonomies is the incompleteness of the extracted concepts, especially for those whose names have multiple words and consequently low frequency in the corpus. To resolve the limitations of extraction-based methods, we propose GenTaxo to enhance taxonomy completion by identifying positions in existing taxonomies that need new concepts and then generating appropriate concept names. Instead of relying on the corpus for concept embeddings, GenTaxo learns the contextual embeddings from their surrounding graph-based and language-based relational information, and leverages the corpus for pre-training a concept name generator. Experimental results demonstrate that GenTaxo improves the completeness of taxonomies over existing methods.

Prevailing methods of graph representation learning (GRL) usually rely on learning from "big'' data, requiring a large amount of labeled data for model training. However, it is common that graphs are associated with "small'' labeled data as data annotation and labeling is always a time and resource consuming task. The fact overshadows GRL's capability and applicability for many real situations. Therefore, data efficient learning on graphs has become essential for many real-world applications and there have been many studies working on this topic in recent years. In this tutorial, we will systematically review recent studies of data efficient learning on graphs, in particular a series of methods and applications of graph few-shot learning and graph self-supervised learning. At first, we will introduce the overview of graph representation learning methods, conventional few-shot learning, and self-supervised learning techniques. Then, we will present the work of data efficient learning on graphs in terms of three major graph mining tasks at different granularity levels: node-level learning tasks, graph-level learning tasks, and edge-level learning tasks. In the end, we will conclude the tutorial and raise open problems and pressing issues in future research. The authors of this tutorial are active and productive researchers in this research area.

Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training dataset for each property, impairing their performance in cases (especially for new molecular properties) with a limited amount of experimental data, which are common in real situations. To this end, we propose Meta-MGNN, a novel model for few-shot molecular property prediction. Meta-MGNN applies molecular graph neural network to learn molecular representations and builds a meta-learning framework for model optimization. To exploit unlabeled molecular information and address task heterogeneity of different molecular properties, Meta-MGNN further incorporates molecular structures, attribute based self-supervised modules and self-attentive task weights into the former framework, strengthening the whole learning model. Extensive experiments on two public multi-property datasets demonstrate that Meta-MGNN outperforms a variety of state-of-the-art methods.

Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse knowledge. However, extracting knowledge from relational tables is challenging because of sparse contextual information. Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells information in the same table. In this work, we propose a novel relational table representation learning approach considering both the intra- and inter-table contextual information. On one hand, the proposed Table Convolutional Network model employs the attention mechanism to adaptively focus on the most informative intra-table cells of the same row or column; and, on the other hand, it aggregates inter-table contextual information from various types of implicit connections between cells across different tables. Specifically, we propose three novel aggregation modules for (i) cells of the same value, (ii) cells of the same schema position, and (iii) cells linked to the same page topic. We further devise a supervised multi-task training objective for jointly predicting column type and pairwise column relation, as well as a table cell recovery objective for pre-training. Experiments on real Web table datasets demonstrate our method can outperform competitive baselines by of F1 for column type prediction and by of F1 for pairwise column relation prediction.

Conditions play an essential role in biomedical statements. However, existing biomedical knowledge graphs (BioKGs) only focus on factual knowledge, organized as a flat relational network of biomedical concepts. These BioKGs ignore the conditions of the facts being valid, which loses essential contexts for knowledge exploration and inference. We consider both facts and their conditions in biomedical statements and proposed a three-layered information-lossless representation of BioKG. The first layer has biomedical concept nodes, attribute nodes. The second layer represents both biomedical fact and condition tuples by nodes of the relation phrases, connecting to the subject and object in the first layer. The third layer has nodes of statements connecting to a set of fact tuples and/or condition tuples in the second layer. We transform the BioKG construction problem into a sequence labeling problem based on a novel designed tag schema. We design a Multi-Input Multi-Output sequence labeling model (MIMO) that learns from multiple input signals and generates proper number of multiple output sequences for tuple extraction. Experiments on a newly constructed dataset show that MIMO outperforms the existing methods. Further case study demonstrates that the BioKGs constructed provide a good understanding of the biomedical statements.

People are looking for complementary contexts, such as team members of complementary skills for project team building and/or reading materials of complementary knowledge for effective student learning, to make their behaviors more likely to be successful. Complementarity has been revealed by behavioral sciences as one of the most important factors in decision making. Existing computational models that learn low-dimensional context representations from behavior data have poor scalability and recent network embedding methods only focus on preserving the similarity between the contexts. In this work, we formulate a behavior entry as a set of context items and propose a novel representation learning method, Multi-type Itemset Embedding , to learn the context representations preserving the itemset structures. We propose a measurement of complementarity between context items in the embedding space. Experiments demonstrate both effectiveness and efficiency of the proposed method over the state-of-the-art methods on behavior prediction and context recommendation. We discover that the complementary contexts and similar contexts are significantly different in human behaviors.

Web personalization, e.g., recommendation or relevance search, tailoring a service/product to accommodate specific online users, is becoming increasingly important. Inductive personalization aims to infer the relations between existing entities and unseen new ones, e.g., searching relevant authors for new papers or recommending new items to users. This problem, however, is challenging since most of recent studies focus on transductive problem for existing entities. In addition, despite some inductive learning approaches have been introduced recently, their performance is sub-optimal due to relatively simple and inflexible architectures for aggregating entity’s content. To this end, we propose the inductive contextual personalization (ICP) framework through contextual relation learning. Specifically, we first formulate the pairwise relations between entities with a ranking optimization scheme that employs neural aggregator to fuse entity’s heterogeneous contents. Next, we introduce a node embedding term to capture entity’s contextual relations, as a smoothness constraint over the prior ranking objective. Finally, the gradient descent procedure with adaptive negative sampling is employed to learn the model parameters. The learned model is capable of inferring the relations between existing entities and inductive ones. Thorough experiments demonstrate that ICP outperforms numerous baseline methods for two different applications, i.e., relevant author search and new item recommendation.

Patent categorization, which is to assign multiple International Patent Classification (IPC) codes to a patent document, relies heavily on expert efforts, as it requires substantial domain knowledge. When formulated as a multi-label text classification (MTC) problem, it draws two challenges to existing models: one is to learn effective document representations from text content; the other is to model the cross-section behavior of label set. In this work, we propose a label attention model based on graph convolutional network. It jointly learns the document-word associations and word-word co-occurrences to generate rich semantic embeddings of documents. It employs a non-local attention mechanism to learn label representations in the same space of document representations for multi-label classification. On a large CIRCA patent database, we evaluate the performance of our model and as many as seven competitive baselines. We find that our model outperforms all those prior state of the art by a large margin and achieves high performance on P@k and nDCG@k.

Towards the challenging problem of semi-supervised node classification, there have been extensive studies. As a frontier, Graph Neural Networks (GNNs) have aroused great interest recently, which update the representation of each node by aggregating information of its neighbors. However, most GNNs have shallow layers with a limited receptive field and may not achieve satisfactory performance especially when the number of labeled nodes is quite small. To address this challenge, we innovatively propose a graph few-shot learning (GFL) algorithm that incorporates prior knowledge learned from auxiliary graphs to improve classification accuracy on the target graph. Specifically, a transferable metric space characterized by a node embedding and a graph-specific prototype embedding function is shared between auxiliary graphs and the target, facilitating the transfer of structural knowledge. Extensive experiments and ablation studies on four real-world graph datasets demonstrate the effectiveness of our proposed model and the contribution of each component.

Knowledge graphs (KGs) serve as useful resources for various natural language processing applications. Previous KG completion approaches require a large number of training instances (i.e., head-tail entity pairs) for every relation. The real case is that for most of the relations, very few entity pairs are available. Existing work of one-shot learning limits method generalizability for few-shot scenarios and does not fully use the supervisory information; however, few-shot KG completion has not been well studied yet. In this work, we propose a novel few-shot relation learning model (FSRL) that aims at discovering facts of new relations with few-shot references. FSRL can effectively capture knowledge from heterogeneous graph structure, aggregate representations of few-shot references, and match similar entity pairs of reference set for every relation. Extensive experiments on two public datasets demonstrate that FSRL outperforms the state-of-the-art.

Answer retrieval is to find the most aligned answer from a large set of candidates given a question.Learning vector representations of questions/answers is the key factor.Questionanswer alignment and question/answer semantics are two important signals for learning the representations.Existing methods learned semantic representations with dual encoders or dual variational auto-encoders.The semantic information was learned from language models or question-to-question (answer-to-answer) generative processes.However, the alignment and semantics were too separate to capture the aligned semantics between question and answer.In this work, we propose to cross variational auto-encoders by generating questions with aligned answers and generating answers with aligned questions.Experiments show that our method outperforms the state-of-theart answer retrieval method on SQuAD.Question Answer Decoder 𝑝(𝑞|𝒛 𝒂 ) 𝑝(𝑎|𝒛 𝒒 ) 𝑝(𝑦|𝑧 !, 𝑧 " ) 𝑝(𝑦|𝑧 !, 𝑧 " ) Question Answer Question Answer Decoder Encoder Encoder Decoder Decoder Encoder 𝑝(𝑧 !|𝑞) 𝑝(𝑧 " |𝑎) Encoder Encoder (a) Dual-Encoders (Yang et al., 2019)Question Answer Decoder 𝑝(𝑞|𝒛 𝒂 ) 𝑝(𝑎|𝒛 𝒒 ) 𝑝(𝑦|𝑧 !, 𝑧 " ) 𝑝(𝑦|𝑧 !, 𝑧 " ) Question Answer Question Answer Decoder Encoder Encoder Decoder Decoder Encoder 𝑝(𝑧 !|𝑞) 𝑝(𝑧 " |𝑎) Encoder Encoder (b) Dual-VAEs (Shen et al., 2018) 𝑧 !~𝑝(𝑧 ! ) 𝑧 " ~𝑝(𝑧 " ) Question Answer 𝑧 !~𝑝(𝑧 ! ) 𝑝(𝑧 !|𝑞) 𝑧 " ~𝑝(𝑧 " ) 𝑝(𝑧 " |𝑎) Question Answer 𝑝(𝑦|𝑧 !, 𝑧 " ) 𝑝(𝑞|𝑧 ! ) 𝑝(𝑎|𝑧 " )

Understanding user characteristics such as demographic information is useful for the personalization of online content promoted to users. However, it is difficult to obtain such data for each user visiting the website. Since demographic data for some users can be collected, their behavior can be used to predict the attributes of unknown users. Through online news consumption, we can infer the attributes of users from the articles they view. Most existing models take a supervised learning approach to this modeling task. However, by representing the user-URL interactions with a network, we can convert it to a semi-supervised learning problem and learn embeddings for users. Graph embeddings have become popular in recent years, with research mainly focusing on algorithmic developments. However, while we have an intuitive understanding of the problems they may overcome, such as data sparsity, this problem remains unexplored in the domain of demographic prediction using behavior. In this paper, we first investigate the effectiveness of using user embeddings generated from network representation learning for prediction by comparing its performance with other traditional feature sets, including content and item-based features. We find that the embeddings can represent a user generally on two prediction tasks, (1) gender prediction (classification) and (2) age prediction (regression). Second, we explore the advantages of using these embeddings over the other methods in two cases of data sparsity, where (1) the training and testing sets of users are temporally split and (2) the user labels are imbalanced. In both these cases, the embeddings outperform the baseline.

Knowledge plays an essential role in biomedical literature search (BLS) systems, filling the semantic gap between queries and documents. Knowledge bases, constructed by human experts or machine learning methods, are generally regarded as the main sources serving external knowledge. However, a good knowledge base must balances its particularity and generalization, resulting limited knowledge coverage and utilization to BLS systems. Considering massive documents in a BLS system, and recently developing Open IE techniques by which we can automatically extract structured knowledge from documents, how about harnessing distilled internal knowledge rather than external knowledge to conduct BLS systems? Internal knowledge, providing tailored particular knowledge to BLS systems, is supposed to lead better knowledge utilization and much more competitive performance on literature search. In this paper, we design an novel internal knowledge driven BLS system upon a Multi-layered Encoders incorporating Multi-layered internal Knowledge graph, called MEMK. MEMK harnesses distilled internal structural knowledge, empowering interactive representations learning of query and documents. The experiments show that MEMK outperforms strong baselines on a public benchmark, and internal knowledge based query expansion can further improve the performance to a new state of the art.

In this paper, we discuss a tensor decomposition method for imputing similarity scores between individual clinical pictures at predefined patient age intervals in order to construct a dynamic similarity network of patients with respect to early childhood anthropomorphic development. The method leverages Canonical Polyadic Decomposition (or PARAFAC) to compute missing Euclidean similarity scores between pairwise growth pictures, made up of height and weight measurements. We construct a tensor made up of serial affinity matrices to model how the similarities between different patients change over different trajectory snapshots. We intend to use this method to aid Un Kilo de Ayuda (UKA), a non-governmental organization located in Mexico that is made up of facilitators seeking to identify children at risk for malnutrition and suboptimal development. This tensor completion strategy will assist UKA with determining pairs of children with similar clinical pictures, so that they can better assist with selecting treatment strategies and ultimately build better programs tailored to specific families' needs.

The mission of the National Science Foundation (NSF) is to promote progress of science. It supports fundamental research and education in science and engineering. It provides funding for researchers to explore a variety of disciplines in thousands of institutions across the United States. The outcomes of such research projects vary widely and with much funding being funneled into these projects, it would be efficient and cost-effective to be able to predict these outcomes so the NSF can make informed decisions on the amount of funding they allocate to future projects. We consider a variety of factors that point to general trends and use a combination of natural language processing techniques (such as topic models and phrase mining) and neural networks to predict how many papers and citations will come from potential research projects seeking funding.

Graph neural networks (GNNs) have been widely used to learn node representations from graph data in an unsupervised way for downstream tasks. However, when applied to detect anomalies (e.g., outliers, unexpected density), they deliver unsatisfactory performance as existing loss functions fail. For example, any loss based on random walk (RW) algorithms would no longer work because the assumption that anomalous nodes were close with each other could not hold. Moreover, the nature of class imbalance in anomaly detection tasks brings great challenges to reduce the prediction error. In this work, we propose a novel loss function to train GNNs for anomaly-detectable node representations. It evaluates node similarity using global grouping patterns discovered from graph mining algorithms. It can automatically adjust margins for minority classes based on data distribution. Theoretically, we prove that the prediction error is bounded given the proposed loss function. We empirically investigate the GNN effectiveness of different loss variants based on different algorithms. Experiments on two real-world datasets show that they perform significantly better than RW-based loss for graph anomaly detection.

With the recent advancement of deep learning, molecular representation learning -- automating the discovery of feature representation of molecular structure, has attracted significant attention from both chemists and machine learning researchers. Deep learning can facilitate a variety of downstream applications, including bio-property prediction, chemical reaction prediction, etc. Despite the fact that current SMILES string or molecular graph molecular representation learning algorithms (via sequence modeling and graph neural networks, respectively) have achieved promising results, there is no work to integrate the capabilities of both approaches in preserving molecular characteristics (e.g, atomic cluster, chemical bond) for further improvement. In this paper, we propose GraSeq, a joint graph and sequence representation learning model for molecular property prediction. Specifically, GraSeq makes a complementary combination of graph neural networks and recurrent neural networks for modeling two types of molecular inputs, respectively. In addition, it is trained by the multitask loss of unsupervised reconstruction and various downstream tasks, using limited size of labeled datasets. In a variety of chemical property prediction tests, we demonstrate that our GraSeq model achieves better performance than state-of-the-art approaches.

Unstructured scientific text, in various forms of textual artifacts, including manuscripts, publications, patents, and proposals, is used to store the tremendous wealth of knowledge discovered after weeks, months, and years, developing hypotheses, working in the lab or clinic, and analyzing results. A grand challenge on data mining research is to develop effective methods for transforming the scientific text into well-structured forms (e.g., ontology, taxonomy, knowledge graphs), so that machine intelligent systems can build on them for hypothesis generation and validation. In this tutorial, we provide a comprehensive overview on recent research and development in this direction. First, we introduce a series of text mining methods that extract phrases, entities, scientific concepts, relations, claims, and experimental evidence. Then we discuss methods that construct and learn from scientific knowledge graphs for accurate search, document classification, and exploratory analysis. Specifically, we focus on scalable, effective, weakly supervised methods that work on text in sciences (e.g., chemistry, biology).

User behavior modeling is important for industrial applications such as demographic attribute prediction, content recommendation, and target advertising. Existing methods represent behavior log as a sequence of adopted items and find sequential patterns; however, concrete location and time information in the behavior log, reflecting dynamic and periodic patterns, joint with the spatial dimension, can be useful for modeling users and predicting their characteristics. In this work, we propose a novel model based on graph neural networks for learning user representations from spatiotemporal behavior data. Our model's architecture incorporates two networked structures. One is a tripartite network of items, sessions, and locations. The other is a hierarchical calendar network of hour, week, and weekday nodes. It first aggregates embeddings of location and items into session embeddings via the tripartite network, and then generates user embeddings from the session embeddings via the calendar structure. The user embeddings preserve spatial patterns and temporal patterns of a variety of periodicity (e.g., hourly, weekly, and weekday patterns). It adopts the attention mechanism to model complex interactions among the multiple patterns in user behaviors. Experiments on real datasets (i.e., clicks on news articles in a mobile app) show our approach outperforms strong baselines for predicting missing demographic attributes.

In today's information and computational society, complex systems are often modeled as multi-modal networks associated with heterogeneous structural relation, unstructured attribute/content, temporal context, or their combinations. The abundant information in multi-modal network requires both a domain understanding and large exploratory search space when doing feature engineering for building customized intelligent solutions in response to different purposes. Therefore, automating the feature discovery through representation learning in multi-modal networks has become essential for many applications. In this tutorial, we systematically review the area of multi-modal network representation learning, including a series of recent methods and applications. These methods will be categorized and introduced in the perspectives of unsupervised, semi-supervised and supervised learning, with corresponding real applications respectively. In the end, we conclude the tutorial and raise open discussions. The authors of this tutorial are active and productive researchers in this area.

In many regulated domains, traceability is established across diverse artifacts such as requirements, design, code, test cases, and hazards - either manually or with the help of supporting tools, and the resulting trace links are used to support activities such as impact analysis, compliance verification, and safety inspections. Automated tracing techniques need to leverage the semantics of underlying artifacts in order to establish more accurate trace links and to provide explanations of links that have been created in either a manual or automated fashion. To support this, we propose an automated technique which leverages source code, project artifacts and an external domain corpus to generate a domain-specific concept model. We then use the generated concept model to improve traceability results and to provide explanations of the results. Our approach overcomes existing problems with deep-learning traceability algorithms, as it does not require a training set of existing trace links. Finally, as an initial proof-of-concept, we apply our semantically-guided approach to the Dronology project, and show that it improves over other tracing techniques that do not use a concept model.

Data Science has been one of the most popular fields in higher education and research activities. It takes tons of time to read the experimental section of thousands of papers and figure out the performance of the data science techniques. In this work, we build an experimental evidence extraction system to automate the integration of tables (in the paper PDFs) into a database of experimental results. First, it crops the tables and recognizes the templates. Second, it classifies the column names and row names into “method”, “dataset”, or “evaluation metric”, and then unified all the table cells into (method, dataset, metric, score)-quadruples. We propose hybrid features including structural and semantic table features as well as an ensemble learning approach for column/row name classification and table unification. SQL statements can be used to answer questions such as whether a method is the state-of-the-art or whether the reported numbers are conflicting.

Citing, quoting, and forwarding & commenting behaviors are widely seen in academia, news media, and social media. Existing behavior modeling approaches focused on mining content and describing preferences of authors, speakers, and users. However, behavioral intention plays an important role in generating content on the platforms. In this work, we propose to identify the referential intention which motivates the action of using the referred (e.g., cited, quoted, and retweeted) source and content to support their claims. We adopt a theory in sociology to develop a schema of four types of intentions. The challenge lies in the heterogeneity of observed contextual information surrounding the referential behavior, such as referred content (e.g., a cited paper), local context (e.g., the sentence citing the paper), neighboring context (e.g., the former and latter sentences), and network context (e.g., the academic network of authors, affiliations, and keywords). We propose a new neural framework with Interactive Hierarchical Attention (IHA) to identify the intention of referential behavior by properly aggregating the heterogeneous contexts. Experiments demonstrate that the proposed method can effectively identify the type of intention of citing behaviors (on academic data) and retweeting behaviors (on Twitter). And learning the heterogeneous contexts collectively can improve the performance. This work opens a door for understanding content generation from a fundamental perspective of behavior sciences.

This article explores the weight binarization of the deconvolution-based generator in a generative adversarial network (GAN) for memory saving and speedup of image construction on the edge. This article suggests that different from convolutional neural networks (including the discriminator) where all layers can be binarized, only some of the layers in the generator can be binarized without significant performance loss. Supported by theoretical analysis and verified by experiments, a direct metric based on the dimension of deconvolution operations is established, which can be used to quickly decide which layers in a generator can be binarized. Our results also indicate that both the generator and the discriminator should be binarized simultaneously for balanced competition and better performance during training. The experimental results on CelebA dataset with DCGAN and original loss functions suggest that directly applying state-of-the-art binarization techniques to all the layers of the generator will lead to 2.83× performance loss measured by sliced Wasserstein distance compared with the original generator, while applying them to selected layers only can yield up to 25.81× saving in memory consumption, and 1.96× and 1.32× speedup in inference and training, respectively, with little performance loss. Similar conclusions can also be drawn on other loss functions for different GANs.

Treatment effect plays an important role on decision making in many fields, such as social marketing, healthcare, and public policy. The key challenge on estimating treatment effect in the wild observational studies is to handle confounding bias induced by imbalance of the confounder distributions between treated and control units. Traditional methods remove confounding bias by re-weighting units with supposedly accurate propensity score estimation under the unconfoundedness assumption. Controlling high-dimensional variables may make the unconfoundedness assumption more plausible, but poses new challenge on accurate propensity score estimation. One strand of recent literature seeks to directly optimize weights to balance confounder distributions, bypassing propensity score estimation. But existing balancing methods fail to do selection and differentiation among the pool of a large number of potential confounders, leading to possible underperformance in many high-dimensional settings. In this article, we propose a data-driven Differentiated Confounder Balancing (DCB) algorithm to jointly select confounders, differentiate weights of confounders and balance confounder distributions for treatment effect estimation in the wild high-dimensional settings. Besides, under some settings with heavy confounding bias, in order to further reduce the bias and variance of estimated treatment effect, we propose a Regression Adjusted Differentiated Confounder Balancing (RA-DCB) algorithm based on our DCB algorithm by incorporating outcome regression adjustment. The synergistic learning algorithms we proposed are more capable of reducing the confounding bias in many observational studies. To validate the effectiveness of our DCB and RA-DCB algorithms, we conduct extensive experiments on both synthetic and real-world datasets. The experimental results clearly demonstrate that our algorithms outperform the state-of-the-art methods. By incorporating regression adjustment, our RA-DCB algorithm achieves more precise estimation on treatment effect than DCB algorithm, especially under the settings with heavy confounding bias. Moreover, we show that the top features ranked by our algorithm generate accurate prediction of online advertising effect.

Scientists are relying heavily on biomedical literature search (BLS) engines (e.g., PubMed) to acquire knowledge. Existing BLS systems adopt a “C-A” paradigm that is to design query-document similarity measurement based on words/phrases in the unstructured Content and to develop search Algorithms. In this work, we argue that structures should be extracted and utilized to bridge the gap between text content and knowledge-based search. And graph is one of the most effective structured forms of knowledge and more informative than words or phrases. So we carry out a paradigm shift from “C-A” to “CTGA”. Here “T” is for factual tuple of concepts and relations, and “G” is for knowledge graph. Our proposed graph-based BLS system has three parts: (1) it uses neural information extraction models to turn text into tuples; (2) it represents the tuples of a query or a document as a knowledge graph of linked concept nodes; (3) it has an efficient graph-based matching algorithm to return related documents at the level of structured knowledge. Experiments show that in both objective and subjective evaluation, our CTGA performs significantly better than traditional CA-based PubMed.

We develop a new representation learning method in the chemistry domain. Given a large set of compounds of inorganic crystals, the extraction model learns the embeddings of atoms so that the predictive model can place them into the periodic table correctly. Our method preserves not only the compounds' compositions but also their crystal structures. Experiments demonstrate the effectiveness of the proposed method, compared to the state-of-the-art method (in PNAS 2018).

Tianwen Jiang, Tong Zhao, Bing Qin, Ting Liu, Nitesh Chawla, Meng Jiang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Conditions play an essential role in scientific observations, hypotheses, and statements. Unfortunately, existing scientific knowledge graphs (SciKGs) represent factual knowledge as a flat relational network of concepts, as same as the KGs in general domain, without considering the conditions of the facts being valid, which loses important contexts for inference and exploration. In this work, we propose a novel representation of SciKG, which has three layers. The first layer has concept nodes, attribute nodes, as well as the attaching links from attribute to concept. The second layer represents both fact tuples and condition tuples. Each tuple is a node of the relation name, connecting to the subject and object that are concept or attribute nodes in the first layer. The third layer has nodes of statement sentences traceable to the original paper and authors. Each statement node connects to a set of fact tuples and/or condition tuples in the second layer. We design a semi-supervised Multi-Input Multi-Output sequence labeling model that learns complex dependencies between the sequence tags from multiple signals and generates output sequences for fact and condition tuples. It has a self-training module of multiple strategies to leverage the massive scientific data for better performance when manual annotation is limited. Experiments on a data set of 141M sentences show that our model outperforms existing methods and the SciKGs we constructed provide a good understanding of the scientific statements.

Given a project plan and the goal, can we predict the plan's success rate? The key challenge is to learn the feature vectors of billions of the plan's components for effective prediction. However, existing methods did not model the behavior outcomes but component proximities. In this work, we define a measurement of behavior outcomes, which forms a test tube-shaped region to represent "success", in a vector space. We propose a novel representation learning method to learn the embeddings of behavior components (including contexts, plans, and goals) by preserving the behavior outcome information. Experiments on real datasets show that our proposed method significantly improves the performance of goal prediction as well as context recommendation over the state-of-the-art.

The task of temporal slot filling (TSF) is to extract the values (or called facts) of specific attributes for a given entity from text data and find the time points when the values were valid. It is challenging to find precise time points with incomplete and noisy temporal contexts in the text. In this work, we propose an unsupervised approach of two modules that mutually enhance each other: one is a reliability estimator on fact extractors conditionally to the temporal contexts; the other is a fact trustworthiness estimator based on the extractor's reliability. The iterative learning process reduces the noise of the extractions. Experiments demonstrate that our approach, with the novel design, can accurately and efficiently extract precise temporal facts from newspaper corpora.

Web research, data science, and artificial intelligence have been rapidly changing our life and society. Researchers and practitioners in the fields take a large amount of time to read literature and compare existing approaches. It would significantly improve their efficiency if there was a system that extracted and managed experimental evidences (say, a specific method achieves a score of a specific metric on a specific dataset) from tables of paper PDFs for search, exploration, and analytic. We build such a demonstration system, called Tablepedia, that use rule-based and learning-based methods to automate the “reading” of PDF tables. It has three modules: template recognition, unification, and SQL operations. We implement three functions to facilitate research and practice: (1) finding related methods and datasets, (2) finding top-performing baseline methods, and (3) finding conflicting reported numbers. A pointer to a screencast on Vimeo: https://vimeo.com/310162310

We have been spotting massive suspicious behaviors on bipartite graph-based applications such as social networks and e-commercial platforms. Existing detection methods estimate the suspiciousness score of source users (e.g., followers, buyers) assuming that the behavioral patterns of suspicious source users (e.g., botnet followers, bully buyers) lead to abnormal high density in the graphs. A serious issue when putting the methods into real use is the false positives - the platforms cannot automatically suspend the source users just based on their suspiciousness scores. In this work, we revisit the problem of suspicious behavior detection from the perspective of the target users (e.g., followees, sellers), and provide them an effective and actionable solution using big behavior data analytics. We propose a novel method called Actionable Objective Optimization in which the variables are the target users' decisions rather than source users' scores. Experimental results show that our proposed actionable method consistently outperforms the state-of-the-art methods.

In coal-fired power plants, it is critical to improve the operational efficiency of boilers for sustainability. In this work, we formulate real-time boiler control as an optimization problem that looks for the best distribution of temperature in different zones and oxygen content from the flue to improve the boiler's stability and energy efficiency. We employ an efficient algorithm by integrating appropriate machine learning and optimization techniques. We obtain a large dataset collected from a real boiler for more than two months from our industry partner, and conduct extensive experiments to demonstrate the effectiveness and efficiency of the proposed algorithm.

Data cube is a cornerstone architecture in multidimensional analysis of structured datasets. It is highly desirable to conduct multidimensional analysis on text corpora with cube structures for various text-intensive applications in healthcare, business intelligence, and social media analysis. However, one bottleneck to constructing text cube is to automatically put millions of documents into the right cube cells so that quality multidimensional analysis can be conducted afterwards-it is too expensive to allocate documents manually or rely on massively labeled data. We propose Doc2Cube, a method that constructs a text cube from a given text corpus in an unsupervised way. Initially, only the label names (e.g., USA, China) of each dimension (e.g., location) are provided instead of any labeled data. Doc2Cube leverages label names as weak supervision signals and iteratively performs joint embedding of labels, terms, and documents to uncover their semantic similarities. To generate joint embeddings that are discriminative for cube construction, Doc2Cube learns dimension-tailored document representations by selectively focusing on terms that are highly label-indicative in each dimension. Furthermore, Doc2Cube alleviates label sparsity by propagating the information from label names to other terms and enriching the labeled term set. Our experiments on real data demonstrate the superiority of Doc2Cube over existing methods.

Pattern-based methods have been successful in information extraction and NLP research. Previous approaches learn the quality of a textual pattern as relatedness to a certain task based on statistics of its individual content (e.g., length, frequency) and hundreds of carefully-annotated labels. However, patterns of good content-quality may generate heavily conflicting information due to the big gap between relatedness and correctness. Evaluating the correctness of information is critical in (entity, attribute, value)-tuple extraction. In this work, we propose a novel method, called TruePIE, that finds reliable patterns which can extract not only related but also correct information. TruePIE adopts the self-training framework and repeats the training-predicting-extracting process to gradually discover more and more reliable patterns. To better represent the textual patterns, pattern embeddings are formulated so that patterns with similar semantic meanings are embedded closely to each other. The embeddings jointly consider the local pattern information and the distributional information of the extractions. To conquer the challenge of lacking supervision on patterns' reliability, TruePIE can automatically generate high quality training patterns based on a couple of seed patterns by applying the arity-constraints to distinguish highly reliable patterns (i.e., positive patterns) and highly unreliable patterns (i.e., negative patterns). Experiments on a huge news dataset (over 25GB) demonstrate that the proposed TruePIE significantly outperforms baseline methods on each of the three tasks: reliable tuple extraction, reliable pattern extraction, and negative pattern extraction.

Contextual behavior modeling uses data from multiple contexts to discover patterns for predictive analysis. However, existing behavior prediction models often face difficulties when scaling for massive datasets. In this work, we formulate a behavior as a set of context items of different types (such as decision makers, operators, goals and resources), consider an observable itemset as a behavior success, and propose a novel scalable method, "multi-type itemset embedding", to learn the context items' representations preserving the success structures. Unlike most of existing embedding methods that learn pair-wise proximity from connection between a behavior and one of its items, our method learns item embeddings collectively from interaction among all multi-type items of a behavior, based on which we develop a novel framework, LearnSuc, for (1) predicting the success rate of any set of items and (2) finding complementary items which maximize the probability of success when incorporated into an itemset. Extensive experiments demonstrate both effectiveness and efficency of the proposed framework.

Taxonomy construction is not only a fundamental task for semantic analysis of text corpora, but also an important step for applications such as information filtering, recommendation, and Web search. Existing pattern-based methods extract hypernym-hyponym term pairs and then organize these pairs into a taxonomy. However, by considering each term as an independent concept node, they overlook the topical proximity and the semantic correlations among terms. In this paper, we propose a method for constructing topic taxonomies, wherein every node represents a conceptual topic and is defined as a cluster of semantically coherent concept terms. Our method, TaxoGen, uses term embeddings and hierarchical clustering to construct a topic taxonomy in a recursive fashion. To ensure the quality of the recursive process, it consists of: (1) an adaptive spherical clustering module for allocating terms to proper levels when splitting a coarse topic into fine-grained ones; (2) a local embedding module for learning term embeddings that maintain strong discriminative power at different levels of the taxonomy. Our experiments on two real datasets demonstrate the effectiveness of TaxoGen compared with baseline methods.

Misinformation and misbehavior mining on the web(MIS2) workshop is held in Los Angeles, California, USA on February 9, 2018, and co-located with the 11th ACM International Conference on Web Search and Data Mining(WSDM 2018). Web is a dynamic ecosystem that enables malicious users to create and spread deceptive information to a wide audience in a matter of minutes. These malicious actors work on a wide variety of platforms, such as social media, e-commerce, and more. The main object of MIS2 is to discuss new and upcoming research on modeling, discovery, detection, and mitigation methods of misbehavior and misinformation on the web. MIS2 is an interdisciplinary venue for leading researchers and practitioners from the areas of data mining, social network analysis, cybersecurity, communications, human-computer interaction, and natural language processing. The topics addressed in MIS2 are extremely timely and the research presented by refereed papers and invited keynote speakers will participants a full dose of emerging research.

Nowdays, many companies, organizations and individuals are using the function of sharing or retweeting information to promote their products, policies, and ideas on social media. While a growing body of research has focused on identifying the promoters from millions of users, the promoters themselves are seeking to know which strategy can improve promotional effectiveness, which is rarely studied in the literature. In this work, we investigate an open problem of effective promotional strategy selection via causal analysis which is challenging in identifying and quantifying promotional strategies as well as the selection bias when estimating the causal effect of promotional strategies from observational data. We study the promotional strategies not only on the content level (what to promote) but also on the context level (when and how to promote). To alleviate the issue of selection bias in observational studies, we propose a data-driven approach that is a Propensity Score Matching (PSM) based method, which helps to evaluate the causal effect of each promotional strategy and discover the set of effective strategies to predict the promotional effectiveness (i.e., the number of users infected by the promotion). We evaluate our proposed method on a real social dataset including 194 million users and 5 million promoted messages. Experimental results show that (1) the top-ranked strategies by our PSM based method significantly and consistently outperform the correlation based feature selection methods in predicting promotional effectiveness; (2) we conclude our observations from the real data with three interpretable and practical ideas for steering social media promotion.

In the literature, two series of models have been proposed to address prediction problems including classification and regression. Simple models, such as generalized linear models, have ordinary performance but strong interpretability on a set of simple features. The other series, including tree-based models, organize numerical, categorical and high dimensional features into a comprehensive structure with rich interpretable information in the data. In this paper, we propose a novel Discriminative Pattern-based Prediction framework (DPPred) to accomplish the prediction tasks by taking their advantages of both effectiveness and interpretability. Specifically, DPPred adopts the concise discriminative patterns that are on the prefix paths from the root to leaf nodes in the tree-based models. DPPred selects a limited number of the useful discriminative patterns by searching for the most effective pattern combination to fit generalized linear models. Extensive experiments show that in many scenarios, DPPred provides competitive accuracy with the state-of-the-art as well as the valuable interpretability for developers and experts. In particular, taking a clinical application dataset as a case study, our DPPred outperforms the baselines by using only 40 concise discriminative patterns out of a potentially exponentially large set of patterns.

As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus and has various downstream applications including information extraction/retrieval, taxonomy construction, and topic modeling. Most existing methods rely on complex, trained linguistic analyzers, and thus likely have unsatisfactory performance on text corpora of new domains and genres without extra but expensive adaption. None of the state-of-the-art models, even data-driven models, is fully automated because they require human experts for designing rules or labeling phrases. In this paper, we propose a novel framework for automated phrase mining, AutoPhrase, which supports any language as long as a general knowledge base (e.g., Wikipedia) in that language is available, while benefiting from, but not requiring, a POS tagger. Compared to the state-of-the-art methods, AutoPhrase has shown significant improvements in both effectiveness and efficiency on five real-world datasets across different domains and languages. Besides, AutoPhrase can be extended to model single-word quality phrases.

One fundamental problem in causal inference is the treatment effect estimation in observational studies when variables are confounded. Control for confounding effect is generally handled by propensity score. But it treats all observed variables as confounders and ignores the adjustment variables, which have no influence on treatment but are predictive of the outcome. Recently, it has been demonstrated that the adjustment variables are effective in reducing the variance of the estimated treatment effect. However, how to automatically separate the confounders and adjustment variables in observational studies is still an open problem, especially in the scenarios of high dimensional variables, which are common in big data era. In this paper, we propose a Data-Driven Variable Decomposition (D$^2$VD) algorithm, which can 1) automatically separate confounders and adjustment variables with a data driven approach, and 2) simultaneously estimate treatment effect in observational studies with high dimensional variables. Under standard assumptions, we show experimentally that the proposed D$^2$VD algorithm can automatically separate the variables precisely, and estimate treatment effect more accurately and with tighter confidence intervals than the state-of-the-art methods on both synthetic data and real online advertising dataset.

Online users have generated a large amount of health-related data on medical forums and search engines. However, exploiting these rich data for orienting patient online and assisting medical checkup offline is nontrivial due to the sparseness of existing symptom-disease links, which caused by the natural and chatty expressions of symptoms. In this paper, we propose a novel and general representation learning method ContextCare for human generated health-related data, which learns the latent relationship between symptoms and diseases from the symptom-disease diagnosis network for disease prediction, disease category prediction and disease clustering. To alleviate the network sparseness, ContextCare adopts regularizations from rich contextual information networks including a symptom co-occurrence network and a disease evolution network. Therefore, our representations of symptoms and diseases incorporate knowledge from these three networks. Extensive experiments on medical forum data demonstrate that ContextCare outperforms the state-of-the-art methods in disease category prediction, disease prediction and disease clustering.

Mining textual patterns in news, tweets, papers, and many other kinds of text corpora has been an active theme in text mining and NLP research. Previous studies adopt a dependency parsing-based pattern discovery approach. However, the parsing results lose rich context around entities in the patterns, and the process is costly for a corpus of large scale. In this study, we propose a novel typed textual pattern structure, called meta pattern, which is extended to a frequent, informative, and precise subsequence pattern in certain context. We propose an efficient framework, called MetaPAD, which discovers meta patterns from massive corpora with three techniques: (1) it develops a context-aware segmentation method to carefully determine the boundaries of patterns with a learnt pattern quality assessment function, which avoids costly dependency parsing and generates high-quality patterns; (2) it identifies and groups synonymous meta patterns from multiple facets---their types, contexts, and extractions; and (3) it examines type distributions of entities in the instances extracted by each group of patterns, and looks for appropriate type levels to make discovered patterns precise. Experiments demonstrate that our proposed framework discovers high-quality typed textual patterns efficiently from different genres of massive corpora and facilitates information extraction.

Estimating treatment effect plays an important role on decision making in many fields, such as social marketing, healthcare, and public policy. The key challenge on estimating treatment effect in the wild observational studies is to handle confounding bias induced by imbalance of the confounder distributions between treated and control units. Traditional methods remove confounding bias by re-weighting units with supposedly accurate propensity score estimation under the unconfoundedness assumption. Controlling high-dimensional variables may make the unconfoundedness assumption more plausible, but poses new challenge on accurate propensity score estimation. One strand of recent literature seeks to directly optimize weights to balance confounder distributions, bypassing propensity score estimation. But existing balancing methods fail to do selection and differentiation among the pool of a large number of potential confounders, leading to possible underperformance in many high dimensional settings. In this paper, we propose a data-driven Differentiated Confounder Balancing (DCB) algorithm to jointly select confounders, differentiate weights of confounders and balance confounder distributions for treatment effect estimation in the wild high dimensional settings. The synergistic learning algorithm we proposed is more capable of reducing the confounding bias in many observational studies. To validate the effectiveness of our DCB algorithm, we conduct extensive experiments on both synthetic and real datasets. The experimental results clearly demonstrate that our DCB algorithm outperforms the state-of-the-art methods. We further show that the top features ranked by our algorithm generate accurate prediction of online advertising effect.

In today's computerized and information-based society, people are inundated with vast amounts of text data, ranging from news articles, social media post, scientific publications, to a wide range of textual information from various domains (corporate reports, advertisements, legal acts, medical reports). To turn such massive unstructured text data into structured, actionable knowledge, one of the grand challenges is to gain an understanding of the factual information (e.g., entities, attributes, relations) in the text.

In real-world applications, objects of multiple types are interconnected, formingHeterogeneous Information Networks. In such heterogeneous information networks, we make the key observation that many interactions happen due to someeventand the objects in each event form a complete semantic unit. By taking advantage of such a property, we propose a generic framework calledHyperEdge-BasedEmbedding(Hebe) to learn object embeddings with events in heterogeneous information networks, where ahyperedgeencompasses the objects participating in one event. TheHebeframework models the proximity among objects in each event with two methods: (1) predicting a target object given other participating objects in the event, and (2) predicting if the event can be observed given all the participating objects. Since each hyperedge encapsulates more information of a given event,Hebeis robust to data sparseness and noise. In addition,Hebeis scalable when the data size spirals. Extensive experiments on large-scale real-world datasets show the efficacy and robustness of the proposed framework.

People often use multiple platforms to fulfill their different information needs. With the ultimate goal of serving people intelligently, a fundamental way is to get comprehensive understanding about user needs. How to organically integrate and bridge cross-platform information in a human-centric way is important. Existing transfer learning assumes either fully-overlapped or non-overlapped among the users. However, the real case is the users of different platforms are partially overlapped. The number of overlapped users is often small and the explicitly known overlapped users is even less due to the lacking of unified ID for a user across different platforms. In this paper, we propose a novel semi-supervised transfer learning method to address the problem of cross-platform behavior prediction, called XPTrans. To alleviate the sparsity issue, it fully exploits the small number of overlapped crowds to optimally bridge a user's behaviors in different platforms. Extensive experiments across two real social networks show that XPTrans significantly outperforms the state-of-the-art. We demonstrate that by fully exploiting 26% overlapped users, XPTrans can predict the behaviors of non-overlapped users with the same accuracy as overlapped users, which means the small overlapped crowds can successfully bridge the information across different platforms.

Heterogeneous events, which are defined as events connecting strongly-typed objects, are ubiquitous in the real world. We propose a HyperEdge-Based Embedding (Hebe) framework for heterogeneous event data, where a hyperedge represents the interaction among a set of involving objects in an event. The Hebe framework models the proximity among objects in an event by predicting a target object given the other participating objects in the event (hyperedge). Since each hyperedge encapsulates more information on a given event, Hebe is robust to data sparseness. In addition, Hebe is scalable when the data size spirals. Extensive experiments on large-scale real-world datasets demonstrate the efficacy and robustness of Hebe.

On social media platforms, companies, organizations and individuals are using the function of sharing or retweeting information to promote their products, policies, and ideas. While a growing body of research has focused on identifying the promoters from millions of users, the promoters themselves are seeking to know what strategies can improve promotional effectiveness, which is rarely studied in literature. In this work, we study a new problem of promotional strategy effect estimation which is challenging in identifying and quantifying promotional strategies, as well as estimating effectiveness of promotional strategies with selection bias in observational data. Here we study a series of strategies on both context and content levels. To alleviate the selection bias issue, we propose a method based on Propensity Score Matching (PSM) to evaluate the effect of each promotional strategy. Our data study provides three interpretable and insightful ideas on steering social media promotions, including (1) three significant and stable strategies, (2) a critical trade-off, and (3) different concerns for promoters of different popularity. These results provided comprehensive suggestions to the practitioners to steer social media promotions with effective strategies.

Representing and summarizing human behaviors with rich contexts facilitates behavioral sciences and user-oriented services. Traditional behavioral modeling represents a behavior as a tuple in which each element is one contextual factor of one type, and the tensor-based summaries look for high-order dense blocks by clustering the values (including timestamps) in each dimension. However, the human behaviors are multicontextual and dynamic: (1) each behavior takes place within multiple contexts in a few dimensions, which requires the representation to enable non-value and set-values for each dimension; (2) many behavior collections, such as tweets or papers, evolve over time. In this paper, we represent the behavioral data as a two-level matrix (temporal-behaviors by dimensional-values) and propose a novel representation for behavioral summary called Tartan that includes a set of dimensions, the values in each dimension, a list of consecutive time slices and the behaviors in each slice. We further develop a propagation method CatchTartan to catch the dynamic multicontextual patterns from the temporal multidimensional data in a principled and scalable way: it determines the meaningfulness of updating every element in the Tartan by minimizing the encoding cost in a compression manner. CatchTartan outperforms the baselines on both the accuracy and speed. We apply CatchTartan to four Twitter datasets up to 10 million tweets and the DBLP data, providing comprehensive summaries for the events, human life and scientific development.

Given a directed graph of millions of nodes, how can we automatically spot anomalous, suspicious nodes judging only from their connectivity patterns? Suspicious graph patterns show up in many applications, from Twitter users who buy fake followers, manipulating the social network, to botnet members performing distributed denial of service attacks, disturbing the network traffic graph. We propose a fast and effective method, C atch S ync , which exploits two of the tell-tale signs left in graphs by fraudsters: (a) synchronized behavior: suspicious nodes have extremely similar behavior patterns because they are often required to perform some task together (such as follow the same user); and (b) rare behavior: their connectivity patterns are very different from the majority. We introduce novel measures to quantify both concepts (“synchronicity” and “normality”) and we propose a parameter-free algorithm that works on the resulting synchronicity-normality plots. Thanks to careful design, C atch S ync has the following desirable properties: (a) it is scalable to large datasets, being linear in the graph size; (b) it is parameter free ; and (c) it is side-information-oblivious : it can operate using only the topology, without needing labeled data, nor timing information, and the like., while still capable of using side information if available. We applied C atch S ync on three large, real datasets, 1-billion-edge Twitter social graph, 3-billion-edge, and 12-billion-edge Tencent Weibo social graphs, and several synthetic ones; C atch S ync consistently outperforms existing competitors, both in detection accuracy by 36% on Twitter and 20% on Tencent Weibo, as well as in speed.

Many commercial products and academic research activities are embracing behavior analysis as a technique for improving detection of attacks of many sorts-from retweet boosting, hashtag hijacking to link advertising. Traditional approaches focus on detecting dense blocks in the adjacency matrix of graph data, and recently, the tensors of multimodal data. No method gives a principled way to score the suspiciousness of dense blocks with different numbers of modes and rank them to draw human attention accordingly. In this paper, we first give a list of axioms that any metric of suspiciousness should satisfy; we propose an intuitive, principled metric that satisfies the axioms, and is fast to compute; moreover, we propose CrossSpot, an algorithm to spot dense blocks that are worth inspecting, typically indicating fraud or some other noteworthy deviation from the usual, and sort them in the order of importance (“suspiciousness”). Finally, we apply CrossSpot to the real data, where it improves the F1 score over previous techniques by 68 percent and finds suspicious behavioral patterns in social datasets spanning 0.3 billion posts.

Which seems more suspicious: 5,000 tweets from 200 users on 5 IP addresses, or 10,000 tweets from 500 users on 500 IP addresses but all with the same trending topic and all in 10 minutes? The literature has many methods that try to find dense blocks in matrices, and, recently, tensors, but no method gives a principled way to score the suspiciouness of dense blocks with different numbers of modes and rank them to draw human attention accordingly. Dense blocks are worth inspecting, typically indicating fraud, emerging trends, or some other noteworthy deviation from the usual. Our main contribution is that we show how to unify these methods and how to give a principled answer to questions like the above. Specifically, (a) we give a list of axioms that any metric of suspicousness should satisfy, (b) we propose an intuitive, principled metric that satisfies the axioms, and is fast to compute, (c) we propose CROSSSPOT, an algorithm to spot dense regions, and sort them in importance ("suspiciousness") order. Finally, we apply CROSSSPOT to real data, where it improves the F1 score over previous techniques by 68% and finds retweet-boosting in a real social dataset spanning 0.3 billion posts.

Recommender systems can suffer from data sparsity and cold start issues. However, social networks, which enable users to build relationships and create different types of items, present an unprecedented opportunity to alleviate these issues. In this paper, we represent a social network as a star-structured hybrid graph centered on a social domain, which connects with other item domains. With this innovative representation, useful knowledge from an auxiliary domain can be transferred through the social domain to a target domain. Various factors of item transferability, including popularity and behavioral consistency, are determined. We propose a novel Hybrid Random Walk (HRW) method, which incorporates such factors, to select transferable items in auxiliary domains, bridge cross-domain knowledge with the social domain, and accurately predict user-item links in a target domain. Extensive experiments on a real social dataset demonstrate that HRW significantly outperforms existing approaches.

Given a directed graph of millions of nodes, how can we automatically spot anomalous, suspicious nodes, judging only from their connectivity patterns? Suspicious graph patterns show up in many applications, from Twitter users who buy fake followers, manipulating the social network, to botnet members performing distributed denial of service attacks, disturbing the network traffic graph. We propose a fast and effective method, CatchSync, which exploits two of the tell-tale signs left in graphs by fraudsters: (a) synchronized behavior: suspicious nodes have extremely similar behavior pattern, because they are often required to perform some task together (such as follow the same user); and (b) rare behavior: their connectivity patterns are very different from the majority. We introduce novel measures to quantify both concepts ("synchronicity" and "normality") and we propose a parameter-free algorithm that works on the resulting synchronicity-normality plots. Thanks to careful design, CatchSync has the following desirable properties: (a) it is scalable to large datasets, being linear on the graph size; (b) it is parameter free; and (c) it is side-information-oblivious: it can operate using only the topology, without needing labeled data, nor timing information, etc., while still capable of using side information, if available. We applied CatchSync on two large, real datasets 1-billion-edge Twitter social graph and 3-billion-edge Tencent Weibo social graph, and several synthetic ones; CatchSync consistently outperforms existing competitors, both in detection accuracy by 36% on Twitter and 20% on Tencent Weibo, as well as in speed.

Behavioral pattern discovery is increasingly being studied to understand human behavior and the discovered patterns can be used in many real world applications such as web search, recommender system and advertisement targeting. Traditional methods usually consider the behaviors as simple user and item connections, or represent them with a static model. In real world, however, human behaviors are actually complex and dynamic: they include correlations between user and multiple types of objects and also continuously evolve along time. These characteristics cause severe data sparsity and computational complexity problem, which pose great challenge to human behavioral analysis and prediction. In this paper, we propose a Flexible Evolutionary Multi-faceted Analysis (FEMA) framework for both behavior prediction and pattern mining. FEMA utilizes a flexible and dynamic factorization scheme for analyzing human behavioral data sequences, which can incorporate various knowledge embedded in different object domains to alleviate the sparsity problem. We give approximation algorithms for efficiency, where the bound of approximation loss is theoretically proved. We extensively evaluate the proposed method in two real datasets. For the prediction of human behaviors, the proposed FEMA significantly outperforms other state-of-the-art baseline methods by 17.4%. Moreover, FEMA is able to discover quite a number of interesting multi-faceted temporal patterns on human behaviors with good interpretability. More importantly, it can reduce the run time from hours to minutes, which is significant for industry to serve real-time applications.

Exponential growth of information generated by online social networks demands effective and scalable recommender systems to give useful results. Traditional techniques become unqualified because they ignore social relation data; existing social recommendation approaches consider social network structure, but social contextual information has not been fully considered. It is significant and challenging to fuse social contextual factors which are derived from users' motivation of social behaviors into social recommendation. In this paper, we investigate the social recommendation problem on the basis of psychology and sociology studies, which exhibit two important factors: individual preference and interpersonal influence. We first present the particular importance of these two factors in online behavior prediction. Then we propose a novel probabilistic matrix factorization method to fuse them in latent space. We further provide a scalable algorithm which can incrementally process the large scale data. We conduct experiments on both Facebook style bidirectional and Twitter style unidirectional social network data sets. The empirical results and analysis on these two large data sets demonstrate that our method significantly outperforms the existing approaches.approaches.

Exponential growth of information generated by online social networks demands effective recommender systems to give useful results. Traditional techniques become unqualified because they ignore social relation data; existing social recommendation approaches consider social network structure, but social context has not been fully considered. It is significant and challenging to fuse social contextual factors which are derived from users' motivation of social behaviors into social recommendation. In this paper, we investigate social recommendation on the basis of psychology and sociology studies, which exhibit two important factors: individual preference and interpersonal influence. We first present the particular importance of these two factors in online item adoption and recommendation. Then we propose a novel probabilistic matrix factorization method to fuse them in latent spaces. We conduct experiments on both Facebook style bidirectional and Twitter style unidirectional social network datasets in China. The empirical result and analysis on these two large datasets demonstrate that our method significantly outperform the existing approaches.

Social networks enable users to create different types of personal items. In dealing with serious information overload, the major problems of social recommendation are sparsity and cold start. In existing approaches, relational and heterogeneous domains can not be effectively utilized for social recommendation, which brings a challenge to model users and multiple types of items together on social networks. In this paper, we consider how to represent social networks with multiple relational domains and alleviate the major problems in an individual domain by transferring knowledge from other domains. We propose a novel Hybrid Random Walk (HRW), which can integrate multiple heterogeneous domains including directed/undirected links, signed/unsigned links and within-domain/cross-domain links into a star-structured hybrid graph with user graph at the center. We perform random walk until convergence and use the steady state distribution for recommendation. We conduct experiments on a real social network dataset and show that our method can significantly outperform existing social recommendation approaches.

Influence is a complex and subtle force that governs the dynamics of social networks as well as the behaviors of involved users. Understanding influence can benefit various applications such as viral marketing, recommendation, and information retrieval. However, most existing works on social influence analysis have focused on verifying the existence of social influence. Few works systematically investigate how to mine the strength of direct and indirect influence between nodes in heterogeneous networks.