Large language models (LLMs) often suffer from hallucination, generating factually incorrect statements when handling questions beyond their knowledge and perception. Retrieval-augmented generation (RAG) addresses this by retrieving query-relevant contexts from knowledge bases to support LLM reasoning. Recent advances leverage pre-constructed graphs to capture the relational connections among distributed documents, showing remarkable performance in complex tasks. However, existing Graph-based RAG (GraphRAG) methods rely on a costly process to transform the corpus into a graph, introducing overwhelming token cost and update latency. Moreover, real-world queries vary in type and complexity, requiring different logic structures for accurate reasoning. The pre-built graph may not align with these required structures, resulting in ineffective knowledge retrieval. To this end, we propose a Logic-aware Retrieval Augmented Generation framework (LogicRAG) that dynamically extracts reasoning structures at inference time to guide adaptive retrieval without any pre-built graph. LogicRAG begins by decomposing the input query into a set of subproblems and constructing a directed acyclic graph (DAG) to model the logical dependencies among them. To support coherent multi-step reasoning, LogicRAG then linearizes the graph using topological sort, so that subproblems can be addressed in a logically consistent order. Besides, LogicRAG applies graph pruning to reduce redundant retrieval and uses context pruning to filter irrelevant context, significantly reducing the overall token cost. Extensive experiments demonstrate that LogicRAG achieves both superior performance and efficiency compared to state-of-the-art baselines.

Recent studies have raised significant concerns regarding the reliability of current mathematical benchmarks, highlighting key limitations such as simplistic design and potential data contamination that undermine evaluation accuracy. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we develop question-generating functions to produce random variable questions (RVQs), whose background content mirrors the original benchmark problems, but with randomized variable combinations, rendering them "unseen" to LLMs. Models must completely understand the inherent question pattern to correctly answer RVQs with diverse variable combinations. Thus, an LLMs' genuine reasoning capability is reflected through its accuracy and robustness on RV-Bench. We conducted extensive experiments on over 30 representative LLMs across more than 1,000 RVQs. Our findings reveal that LLMs exhibit a proficiency imbalance between encountered and "unseen" data distributions. Furthermore, RV-Bench reveals that proficiency generalization across similar mathematical reasoning tasks is limited, but we verified that it can still be effectively elicited through test-time scaling.

In collaborative filtering, learning effective embeddings for users and items from interaction data remains a central challenge. While recent efforts leverage large language models (LLMs) to enhance collaborative filtering, two critical limitations persist: (1) Efficiency: LLM-based inference is significantly slower than traditional embedding-based search; and (2) Topological Modeling: LLMs struggle to capture graph structures, which are essential for modeling multi-order user-item interactions. To address these limitations, we propose New Language Collaborative Filtering (NLCF), a framework that aligns LLMs with collaborative filtering by conceptualizing user-item graphs as new languages. This approach is based on two key insights: (1) LLMs excel at mastering new languages when trained on suitable corpora, and (2) the empirical conditional probability between tokens in corpora converges to the transition probabilities between nodes in graphs. NLCF translates user-item graphs into corpora, where users and items are treated as tokens. These corpora are used to fine-tune LLMs, and the learned representations are aggregated to construct user and item embeddings that encode multi-order interactions. Unlike methods that deploy LLMs for inference, NLCF distills LLM knowledge learned from corpora into compact embeddings, enabling both efficient training and real-time inference. The framework has been deployed on a billion-scale e-commerce platform for several months. Extensive experiments demonstrate that NLCF outperforms traditional graph CF models and LLM-based baselines while achieving significant training and inference efficiency improvement over LLM-based baselines.

Yilin Xiao, Jin Chen, Qinggang Zhang, Yujing Zhang, Chuang Zhou, Longhao Yang, Lingfei Ren, Xin Yang, Xiao Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Chuang Zhou, Junnan Dong, Yilin Xiao, Shengyuan Chen, Su Dong, di Yin, Xing Sun, Zhaozhuo Xu, Xiao Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, Xiao Huang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Equipping large language models (LLMs) with external tools has emerged as a promising paradigm for addressing real-world tasks. Nonetheless, with the web-based tool ecosystems rapidly expanding, it is impractical to include all tools within the limited input length of LLMs. To alleviate these issues, researchers have explored incorporating a tool retrieval module to select the most relevant tools or represent tools as unique tokens within LLM parameters. However, most state-of-the-art methods are under transductive settings, assuming all tools have been observed during training. Such a setting deviates from reality as tools on the web are constantly updated and new tools are frequently added to the online ecosystem. When dealing with these unseen tools, which refer to tools not encountered during the training phase, these methods are limited by two key issues, including the large distribution shift and the sensitivity of semantic-only retrieval. To this end, inspired by human cognitive processes of mastering unseen tools through discovering and applying the logical information from prior experience, we introduce a novel Logic-Guided Semantic Bridging framework for inductive tool retrieval, namely, LoSemB, which aims to mine and transfer latent logical information for inductive tool retrieval without costly retraining. Specifically, LoSemB contains a logic-based embedding alignment module to mitigate distribution shifts and a relational augmented retrieval mechanism to overcome the limitations of semantic-only similarity methods. Extensive experiments demonstrate that LoSemB achieves advanced performance in both the inductive and transductive settings.

Click-through rate prediction tasks estimate interaction probabilities using user–item features (i.e., the combined set of user and item features). LLMs have emerged as a promising approach by organizing these features into prompts and fine-tuning LLMs to predict the interaction label. However, our feature-wise and interaction-wise analysis reveals two critical limitations, leading to incomplete relationship modeling between user–item features and interaction labels: (i) LLMs tend to utilize only a subset of available features, neglecting others, and (ii) they struggle with predictions for tail items that appear less frequently in the training samples. To bridge this gap, we propose Feature-Instructed Large language model for Monitoring ( FILM ), which introduces a self-monitoring temperature mechanism that dynamically guides LLMs to focus on informative features, and an auxiliary compaction loss that facilitates better feature-interaction relationship learning for tail items. By integrating these two designs, FILM not only improves feature utilization in LLMs but also enhances predictions for tail items. Furthermore, we demonstrate that FILM -generated interaction embeddings can be transferred to lightweight models, enabling efficient deployment. Extensive experiments demonstrate that FILM achieves significant performance improvements over state-of-the-art baselines by learning better relationships between user–item features and interaction labels and generalizes under different LLM backbones.

Chuang Zhou, Zhu Wang, Shengyuan Chen, Jiahe Du, Qiyuan Zheng, Zhaozhuo Xu, Xiao Huang. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Modeling text-attributed graphs is a well-known problem due to the difficulty of capturing both the text attribute and the graph structure effectively. Existing models often focus on either the text attribute or the graph structure, potentially neglecting the other aspect. This is primarily because both text learning and graph learning models require significant computational resources, making it impractical to directly connect these models in a series. However, there are situations where text-learning models correctly classify text-attributed nodes, while graph-learning models may classify them incorrectly, and vice versa. To fully leverage the potential of text-attributed graphs, we propose a Coupled Text-attributed Graph Learning (CTGL) framework that combines the strengths of both text-learning and graph-learning models in parallel and avoids the computational cost of serially connecting the two aspect models. Specifically, CTGL introduces coupled text-graph augmentation to enable coupled contrastive learning and facilitate the exchange of valuable information between text learning and graph learning. Experimental results on diverse datasets demonstrate the superior performance of our model compared to state-of-the-art text-learning and graph-learning baselines.

Generating novel enzymes for target molecules in zero-shot scenarios is a fundamental challenge in biomaterial synthesis and chemical production. Without known enzymes for a target molecule, training generative models becomes difficult due to the lack of direct supervision. To address this, we propose a retrieval-augmented generation method that uses existing enzyme-substrate data to guide enzyme design. Our method retrieves enzymes with substrates that share structural similarities with the target molecule, leveraging functional similarities in catalytic activity. Since none of the retrieved enzymes directly catalyze the target molecule, we use a conditioned discrete diffusion model to generate new enzymes based on the retrieved examples. An enzyme-substrate relationship classifier guides the generation process to ensure optimal protein sequence distributions. We evaluate our model on enzyme design tasks with diverse real-world substrates and show that it outperforms existing protein generation methods in catalytic capability, foldability, and docking accuracy. Additionally, we define the zero-shot substrate-specified enzyme generation task and introduce a dataset with evaluation benchmarks.

Recent advancements in large language models (LLMs) have shown promise in bridging the gap between natural language queries and database management systems, enabling users to interact with databases without the background of SQL. However, LLMs often struggle to fully exploit and comprehend the user intention and complex structures of databases. Decomposition-based methods have been proposed to enhance the performance of LLMs on complex tasks, but decomposing SQL generation into subtasks is non-trivial due to the declarative structure of SQL syntax and the intricate connections between query concepts and database elements. In this paper, we propose a novel Structure GUided text-to-SQL framework ( SGU-SQL) that incorporates syntax-based prompting to enhance the SQL generation capabilities of LLMs. Specifically, SGU-SQL establishes structure-aware links between user queries and database schema and recursively decomposes the complex generation task using syntax-based prompting to guide LLMs in incrementally constructing target SQLs. Extensive experiments on two benchmark datasets demonstrate that SGU-SQL consistently outperforms state-of-the-art text-to-SQL baselines.

Maintaining a healthy ecosystem in billion-scale online platforms is challenging, as users naturally gravitate toward popular items, leaving cold and less-explored items behind. This ''rich-get-richer'' phenomenon hinders the growth of potentially valuable cold items and harms the platform's ecosystem. Existing cold-start models primarily focus on improving initial recommendation performance for cold items but fail to address users' natural preference for popular content. In this paper, we introduce AliBoost, Alibaba's ecological boosting framework, designed to complement user-oriented natural recommendations and foster a healthier ecosystem. AliBoost incorporates a tiered boosting structure and boosting principles to ensure high-potential items quickly gain exposure while minimizing disruption to low-potential items. To achieve this, we propose the Stacking Fine-Tuning Cold Predictor to enhance the foundation CTR model's performance on cold items for accurate CTR and potential prediction. AliBoost then employs an Item-oriented Bidding Boosting mechanism to deliver cold items to the most suitable users while balancing boosting speed with user-personalized preferences. Over the past six months, AliBoost has been deployed across Alibaba's mainstream platforms, successfully cold-starting over a billion new items and increasing both clicks and GMV of cold items by over 60% within 180 days. Extensive online analysis and A/B testing demonstrate the effectiveness of AliBoost in addressing ecological challenges, offering new insights into the design of billion-scale recommender systems.

Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. Existing methods can be categorized into symbolic and neural models. Symbolic models, while precise, struggle with substructure heterogeneity and sparsity, whereas neural models, although effective, generally lack interpretability and cannot handle uncertainty. We propose NeuSymEA, a unified neuro-symbolic reasoning framework that combines the strengths of both methods to fully exploit the cross-KG structural pattern for robust entity alignment. NeuSymEA models the joint probability of all possible pairs' truth scores in a Markov random field, regulated by a set of rules, and optimizes it with the variational EM algorithm. In the E-step, a neural model parameterizes the truth score distributions and infers missing alignments. In the M-step, the rule weights are updated based on the observed and inferred alignments, handling uncertainty. We introduce an efficient symbolic inference engine driven by logic deduction, enabling reasoning with extended rule lengths. NeuSymEA achieves a significant 7.6\% hit@1 improvement on $DBP15K_{ZH-EN}$ compared with strong baselines and demonstrates robustness in low-resource settings, achieving 73.7\% hit@1 accuracy on $DBP15K_{FR-EN}$ with only 1\% pairs as seed alignments. Codes are released at https://github.com/chensyCN/NeuSymEA-NeurIPS25.

Semantic expertise remains a reliable foundation for industrial decision-making, while Large Language Models (LLMs) can augment the often limited empirical knowledge by generating domain-specific insights, though the quality of this generative knowledge is uncertain. Integrating LLMs with the collective wisdom of multiple stakeholders could enhance the quality and scale of knowledge, yet this integration might inadvertently raise privacy concerns for stakeholders. In response to this challenge, Federated Learning (FL) is harnessed to improve the knowledge base quality by cryptically leveraging other stakeholders’ knowledge, where knowledge base is represented in Knowledge Graph (KG) form. Initially, a multi-field hyperbolic (MFH) graph embedding method vectorizes entities, furnishing mathematical representations in lieu of solely semantic meanings. The FL framework subsequently encrypted identifies and fuses common entities, whereby the updated entities’ embedding can refine other private entities’ embedding locally, thus enhancing the overall KG quality. Finally, the KG complement method refines and clarifies triplets to improve the overall quality of the KG. An experiment assesses the proposed approach across different industrial KGs, confirming its effectiveness as a viable solution for collaborative KG creation, all while maintaining data security.

Collaborative filtering (CF) models have demonstrated remarkable performance in recommender systems, which represent users and items as embedding vectors. Recently, due to the powerful modeling capability of graph neural networks for user-item interaction graphs, graph-based CF models have gained increasing attention. They encode each user/item and its subgraph into a single super vector by combining graph embeddings after each graph convolution. However, each hop of the neighbor in the user-item subgraphs carries a specific semantic meaning. Encoding all subgraph information into single vectors and inferring user-item relations with dot products can weaken the semantic information between user and item subgraphs, thus leaving untapped potential. Exploiting this untapped potential provides insight into improving performance for existing recommendation models. To this end, we propose the Graph Cross-correlated Network for Recommendation (GCR), which serves as a general recommendation paradigm that explicitly considers correlations between user/item subgraphs. GCR first introduces the Plain Graph Representation (PGR) to extract information directly from each hop of neighbors into corresponding PGR vectors. Then, GCR develops Cross-Correlated Aggregation (CCA) to construct possible cross-correlated terms between PGR vectors of user/item subgraphs. Finally, GCR comprehensively incorporates the cross-correlated terms for recommendations. Experimental results show that GCR outperforms state-of-the-art models on both interaction prediction and click-through rate prediction tasks.

Knowledge-based visual question answering (KVQA) has been extensively studied to answer visual questions with external knowledge, e.g., knowledge graphs (KGs).While several attempts have been proposed to leverage large language models (LLMs) as an implicit knowledge source, it remains challenging since LLMs may generate hallucinations.Moreover, multiple knowledge sources, e.g., images, KGs and LLMs, cannot be readily aligned for complex scenarios.To tackle these, we present a novel modality-aware integration with LLMs for KVQA (MAIL).It carefully leverages multimodal knowledge for both image understanding and knowledge reasoning.Specifically, (i) we propose a two-stage prompting strategy with LLMs to densely embody the image into a scene graph with detailed visual features; (ii) We construct a coupled concept graph by linking the mentioned entities with external facts.(iii) A tailored pseudo-siamese graph medium fusion is designed for sufficient multimodal fusion.We utilize the shared mentioned entities in two graphs as mediums to bridge a tight intermodal exchange, while maximally preserving insightful intra-modal learning by constraining the fusion within mediums.Extensive experiments show the superiority of MAIL.

Generating recommendation reasons for recommendation results is a long-standing problem because it is challenging to explain the underlying reasons for recommending an item based on user and item IDs.Existing models usually learn semantic embeddings for each user and item, and generate the reasons according to the embeddings of the user-item pair.However, user and item IDs do not carry inherent semantic meaning, thus the limited number of reviews cannot model users' preferences and item characteristics effectively, negatively affecting the model generalization for unseen user-item pairs.To tackle the problem, we propose the Concept Enhanced Explainable Recommendation framework (CEER), which utilizes macro concepts as the intermediary to bridge the gap between the user/item embeddings and the recommendation reasons.Specifically, we maximize the information bottleneck to extract macro concepts from user-item reviews.Then, for recommended user-item pairs, we jointly train the concept embeddings with the user and item embeddings, and generate the explanation according to the concepts.Extensive experiments on three datasets verify the superiority of our CEER model.

Collaborative filtering on user-item interaction graphs has achieved success in the industrial recommendation. However, recommending users' truly fascinated items poses a seesaw dilemma for collaborative filtering models learned from the interaction graph. On the one hand, not all items that users interact with are equally appealing. Some items are genuinely fascinating to users, while others are unfascinated. Training graph collaborative filtering models in the absence of distinction between them can lead to the recommendation of unfascinating items to users. On the other hand, disregarding the interacted but unfascinating items during graph collaborative filtering will result in an incomplete representation of users' interaction intent, leading to a decline in the model's recommendation capabilities. To address this seesaw problem, we propose Feedback Reciprocal Graph Collaborative Filtering (FRGCF), which emphasizes the recommendation of fascinating items while attenuating the recommendation of unfascinating items. Specifically, FRGCF first partitions the entire interaction graph into the Interacted & Fascinated (I&F) graph and the Interacted & Unfascinated (I&U) graph based on the user feedback. Then, FRGCF introduces separate collaborative filtering on the I&F graph and the I&U graph with feedback-reciprocal contrastive learning and macro-level feedback modeling. This enables the I&F graph recommender to learn multi-grained interaction characteristics from the I&U graph without being misdirected by it. Extensive experiments on four benchmark datasets and a billion-scale industrial dataset demonstrate that FRGCF improves the performance by recommending more fascinating items and fewer unfascinating items. Besides, online A/B tests on Taobao's recommender system verify the superiority of FRGCF.

Decision-making problems, categorized as single-agent, e.g., Atari, cooperative multi-agent, e.g., Hanabi, competitive multi-agent, e.g., Hold'em poker, and mixed cooperative and competitive, e.g., football, are ubiquitous in the real world. Although various methods have been proposed to address the specific decision-making categories, these methods typically evolve independently and cannot generalize to other categories. Therefore, a fundamental question for decision-making is: *Can we develop **a single algorithm** to tackle **ALL** categories of decision-making problems?* There are several main challenges to address this question: i) different decision-making categories involve different numbers of agents and different relationships between agents, ii) different categories have different solution concepts and evaluation measures, and iii) there lacks a comprehensive benchmark covering all the categories. This work presents a preliminary attempt to address the question with three main contributions. i) We propose the generalized mirror descent (GMD), a generalization of MD variants, which considers multiple historical policies and works with a broader class of Bregman divergences. ii) We propose the configurable mirror descent (CMD) where a meta-controller is introduced to dynamically adjust the hyper-parameters in GMD conditional on the evaluation measures. iii) We construct the GameBench with 15 academic-friendly games across different decision-making categories. Extensive experiments demonstrate that CMD achieves empirically competitive or better outcomes compared to baselines while providing the capability of exploring diverse dimensions of decision making.

Representing information of multiple behaviors in the single graph collaborative filtering (CF) vector has been a long-standing challenge. This is because different behaviors naturally form separate behavior graphs and learn separate CF embeddings. Existing models merge the separate embeddings by appointing the CF embeddings for some behaviors as the primary embedding and utilizing other auxiliaries to enhance the primary embedding. However, this approach often results in the joint embedding performing well on the main tasks but poorly on the auxiliary ones. To address the problem arising from the separate behavior graphs, we propose the concept of Partial Order Recommendation Graphs (POG). POG defines the partial order relation of multiple behaviors and models behavior combinations as weighted edges to merge separate behavior graphs into a joint POG. Theoretical proof verifies that POG can be generalized to any given set of multiple behaviors. Based on POG, we propose the tailored Partial Order Graph Convolutional Networks (POGCN) that convolute neighbors' information while considering the behavior relations between users and items. POGCN also introduces a partial-order BPR sampling strategy for efficient and effective multiple-behavior CF training. POGCN has been successfully deployed on the homepage of Alibaba for two months, providing recommendation services for over one billion users. Extensive offline experiments conducted on three public benchmark datasets demonstrate that POGCN outperforms state-of-the-art multi-behavior baselines across all types of behaviors. Furthermore, online A/B tests confirm the superiority of POGCN in billion-scale recommender systems.

Inductive knowledge graph completion (KGC) aims to infer the missing relation for a set of newly-coming entities that never appeared in the training set. Such a setting is more in line with reality, as real-world KGs are constantly evolving and introducing new knowledge. Recent studies have shown promising results using message passing over subgraphs to embed newly-coming entities for inductive KGC. However, the inductive capability of these methods is usually limited by two key issues. (i) KGC always suffers from data sparsity, and the situation is even exacerbated in inductive KGC where new entities often have few or no connections to the original KG. (ii) Cold-start problem. It is over coarse-grained for accurate KG reasoning to generate representations for new entities by gathering the local information from few neighbors. To this end, we propose a novel iNfOmax RelAtion Network, namely NORAN, for inductive KG completion. It aims to mine latent relation patterns for inductive KG completion. Specifically, by centering on relations, NORAN provides a hyper view towards KG modeling, where the correlations between relations can be naturally captured as entity-independent logical evidence to conduct inductive KGC. Extensive experiment results on five benchmarks show that our framework substantially outperforms the state-of-the-art KGC methods.

Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. While existing methods heavily rely on human-generated labels, it is prohibitively expensive to incorporate cross-domain experts for annotation in real-world scenarios. The advent of Large Language Models (LLMs) presents new avenues for automating EA with annotations, inspired by their comprehensive capability to process semantic information. However, it is nontrivial to directly apply LLMs for EA since the annotation space in real-world KGs is large. LLMs could also generate noisy labels that may mislead the alignment. To this end, we propose a unified framework, LLM4EA, to effectively leverage LLMs for EA. Specifically, we design a novel active learning policy to significantly reduce the annotation space by prioritizing the most valuable entities based on the entire inter-KG and intra-KG structure. Moreover, we introduce an unsupervised label refiner to continuously enhance label accuracy through in-depth probabilistic reasoning. We iteratively optimize the policy based on the feedback from a base EA model. Extensive experiments demonstrate the advantages of LLM4EA on four benchmark datasets in terms of effectiveness, robustness, and efficiency.

Knowledge-based question answering (KBQA) is widely used in many scenarios that necessitate domain knowledge. Large language models (LLMs) bring opportunities to KBQA, while their costs are significantly higher and absence of domain-specific knowledge during pre-training. We are motivated to combine LLMs and prior small models on knowledge graphs (KGMs) for both inferential accuracy and cost saving. However, it remains challenging since accuracy and cost are not readily combined in the optimization as two distinct metrics. It is also laborious for model selection since different models excel in diverse knowledge. To this end, we propose Coke, a novel cost-efficient strategy for KBQA with LLMs, modeled as a tailored multi-armed bandit problem to minimize calls to LLMs within limited budgets. We first formulate the accuracy expectation with a cluster-level Thompson Sampling for either KGMs or LLMs. A context-aware policy is optimized to further distinguish the expert model subject to the question semantics. The overall decision is bounded by the cost regret according to historical expenditure on failures. Extensive experiments showcase the superior performance of Coke, which moves the Pareto frontier with up to 20.89% saving of GPT-4 fees while achieving a 2.74% higher accuracy on the benchmark datasets.

Large Language Models (LLMs) have demonstrated remarkable capabilities in many real-world applications. Nonetheless, LLMs are often criticized for their tendency to produce hallucinations, wherein the models fabricate incorrect statements on tasks beyond their knowledge and perception. To alleviate this issue, graph retrieval-augmented generation (GraphRAG) has been extensively explored which leverages the factual knowledge in knowledge graphs (KGs) to ground the LLM's responses in established facts and principles. However, most state-of-the-art LLMs are closed-source, making it challenging to develop a prompting framework that can efficiently and effectively integrate KGs into LLMs with hard prompts only. Generally, existing KG-enhanced LLMs usually suffer from three critical issues, including huge search space, high API costs, and laborious prompt engineering, that impede their widespread application in practice. To this end, we introduce a novel **Know**ledge **Gr**aph based **P**romp**T**ing framework, namely **KnowGPT**, to enhance LLMs with domain knowledge. KnowGPT contains a knowledge extraction module to extract the most informative knowledge from KGs, and a context-aware prompt construction module to automatically convert extracted knowledge into effective prompts. Experiments on three benchmarks demonstrate that KnowGPT significantly outperforms all competitors. Notably, KnowGPT achieves a 92.6% accuracy on OpenbookQA leaderboard, comparable to human-level performance.

Predicting Click-Through Rate (CTR) in billion-scale recommender systems poses a long-standing challenge for Graph Neural Networks (GNNs) due to the overwhelming computational complexity involved in aggregating billions of neighbors. To tackle this, GNN-based CTR models usually sample hundreds of neighbors out of the billions to facilitate efficient online recommendations. However, sampling only a small portion of neighbors results in a severe sampling bias and the failure to encompass the full spectrum of user or item behavioral patterns. To address this challenge, we name the conventional user-item recommendation graph as "micro recommendation grap" and introduce a revolutionizing MAcro Recommendation Graph (MAG) for billion-scale recommendations to reduce the neighbor count from billions to hundreds in the graph structure infrastructure. Specifically, We group micro nodes (users and items) with similar behavior patterns to form macro nodes and then MAG directly describes the relation between the user/item and the hundred of macro nodes rather than the billions of micro nodes. Subsequently, we introduce tailored Macro Graph Neural Networks (MacGNN) to aggregate information on a macro level and revise the embeddings of macro nodes. MacGNN has already served Taobao's homepage feed for two months, providing recommendations for over one billion users. Extensive offline experiments on three public benchmark datasets and an industrial dataset present that MacGNN significantly outperforms twelve CTR baselines while remaining computationally efficient. Besides, online A/B tests confirm MacGNN's superiority in billion-scale recommender systems.

City-wide short-term parking vacancy (PV) prediction is essential to transportation management. In many cities, only partial parking lots are equipped with sensors, causing severe data missing issues. Predicting PVs for parking lots without sensors is attractive but challenging. First, PV prediction itself is a nontrivial task since spatial dependencies among different regions in a city are complex and dynamic. By connecting parking lots based on geographical closeness using pre-designed rules, state-of-the-art PV prediction models achieve reasonable performance. However, those connectivities are not able to adapt to capture the changing dependencies in the graph. Second, node-to-node-based spatial and temporal dependencies will no longer be reliable since neighboring parking lot sensors may be intensely missing, which deteriorates the ability of the model to accurately impute PVs, leveraging the complex dependencies. To this end, we propose a novel framework named Collaborative graph Learning for pArking vacancy Prediction (CLaP). Specifically, to overcome the limitation of traditional pre-designed node connections, we propose a collaborative training method incorporating node attributes into graph augmentation, thus enhancing the ability to capture dynamic spatial dependencies through message aggregation. Besides, a recurrent PV recovering module is developed to impute missing embeddings by deeply coupling spatial-temporal dependencies. Experimental results on two real-world datasets demonstrate that CLaP outperforms state-of-the-art PV prediction models on city-wide PV prediction and imputation precision for parking lots without sensors.

To provide real-time parking information, existing studies focus on predicting parking availability, which seems an indirect approach to saving drivers’ cruising time. In this paper, we first time propose an on-street parking recommendation (OPR) task to directly recommend parking spaces for a driver. To this end, a learn-to-rank (LTR) based OPR model called OPR-LTR is built. Specifically, parking recommendation is closely related to the “turnover events” (state switching between occupied and vacant) of each parking space, and hence we design a highly efficient heterogeneous graph called ESGraph to represent historical and real-time meters’ turnover events as well as geographical relations; afterward, a convolution-based event-then-graph network is used to aggregate and update representations of the heterogeneous graph. A ranking model is further utilized to learn a score function that helps recommend a list of ranked parking spots for a specific on-street parking query. The method is verified using the on-street parking meter data in Hong Kong and San Francisco. By comparing with the other two types of methods: prediction-only and prediction-then-recommendation, the proposed direct-recommendation method achieves satisfactory performance in different metrics. Extensive experiments also demonstrate that the proposed ESGraph and the recommendation model are more efficient in terms of computational efficiency as well as saving drivers’ on-street parking time.

The problem of few-shot graph classification targets at assigning class labels for graph samples, where only limited labeled graphs are provided for each class. To solve the problem brought by label scarcity, recent studies have proposed to adopt the prevalent few-shot learning framework to achieve fast adaptations to graph classes with limited labeled graphs. In particular, these studies typically propose to accumulate meta-knowledge across a large number of meta-training tasks, and then generalize such meta-knowledge to meta-test tasks sampled from a disjoint class set. Nevertheless, existing studies generally ignore the crucial task correlations among meta-training tasks and treat them independently. In fact, such task correlations can help promote the model generalization to meta-test tasks and result in better classification performance. On the other hand, it remains challenging to capture and utilize task correlations due to the complex components and interactions in meta-training tasks. To deal with this, we propose a novel few-shot graph classification framework FAITH to capture task correlations via learning a hierarchical task structure at different granularities. We further propose a task-specific classifier to incorporate the learned task correlations into the few-shot graph classification process. Moreover, we derive FAITH+, a variant of FAITH that can improve the sampling process for the hierarchical task structure. The extensive experiments on four prevalent graph datasets further demonstrate the superiority of FAITH and FAITH+ over other state-of-the-art baselines.

Graph neural networks (GNNs) have shown prominent performance on attributed network embedding. However, existing efforts mainly focus on exploiting network structures, while the exploitation of node attributes is rather limited as they only serve as node features at the initial layer. This simple strategy impedes the potential of node attributes in augmenting node connections, leading to limited receptive field for inactive nodes with few or even no neighbors. Furthermore, the training objectives (i.e., reconstructing network structures) of most GNNs also do not include node attributes, although studies have shown that reconstructing node attributes is beneficial. Thus, it is encouraging to deeply involve node attributes in the key components of GNNs, including graph convolution operations and training objectives. However, this is a nontrivial task since an appropriate way of integration is required to maintain the merits of GNNs. To bridge the gap, in this paper, we propose COllaborative graph Neural Networks–CONN, a tailored GNN architecture for attribute network embedding. It improves model capacity by 1) selectively diffusing messages from neighboring nodes and involved attribute categories, and 2) jointly reconstructing node-to-node and node-to-attribute-category interactions via cross-correlation. Experiments on real-world networks demonstrate that CONN excels state-of-the-art embedding algorithms with a great margin.

Knowledge graphs (KGs) can structurally organize large-scale information in the form of triples and significantly support many real-world applications. While most KG embedding algorithms hold the assumption that all triples are correct, considerable errors were inevitably injected during the construction process. It is urgent to develop effective error-aware KG embedding, since errors in KGs would lead to significant performance degradation in downstream applications. To this end, we propose a novel framework named Attributed Error-aware Knowledge Embedding (AEKE). It leverages the semantics contained in entity attributes to guide the KG embedding model learning against the impact of erroneous triples. We design two triple-level hypergraphs to model the topological structures of the KG and its attributes, respectively. The confidence score of each triple is jointly calculated based on self-contradictory within the triple, consistency between local and global structures, and homogeneity between structures and attributes. We leverage confidence scores to adaptively update the weighted aggregation in the multi-view graph learning framework and margin loss in KG embedding, such that potential errors will contribute little to KG learning. Experiments on three real-world KGs demonstrate that AEKE outperforms state-of-the-art KG embedding and error detection algorithms.

Graph contrastive learning (GCL) has emerged as an effective tool to learn representations for whole graphs in the absence of labels. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL models mainly focus on applying identical augmentation strategies for all graphs within a given scenario. However, real-world graphs are often not monomorphic but abstractions of diverse natures. Even within the same scenario (e.g., macromolecules and online communities), different graphs might need diverse augmentations to perform effective GCL. Thus, blindly augmenting all graphs without considering their individual characteristics may undermine the performance of GCL arts. However, it is non-trivial to achieve personalized allocation since the search space for all graphs is exponential to the number of graphs. To bridge the gap, we propose the first principled framework, termed as Graph contrastive learning with Personalized Augmentation (GPA). It advances conventional GCL by allowing each graph to choose its own suitable augmentation operations. To cope with the huge search space, we design a tailored augmentation selector by converting the discrete space into continuous, which is a plug-and-play module and can be effectively trained with downstream GCL models end-to-end. Extensive experiments across 10 benchmark datasets from different types and domains demonstrate the superiority of GPA against state-of-the-art competitors. Moreover, by visualizing the learned augmentation distributions across different types of datasets, we show that GPA can effectively identify the most suitable augmentations for each graph based on its characteristics. The code is available athttps://github.com/qiaoyu-tan/GPA.

Extracting users' interests from their behavior, particularly their 1-hop neighbors, has been shown to enhance Click-Through Rate (CTR) prediction performance. However, online recommender systems impose strict constraints on the inference time of CTR models, which necessitates pruning or filtering users' 1-hop neighbors to reduce computational complexity. Furthermore, while the graph information of users and items has been proven effective in collaborative filtering models, recursive graph convolution can be computationally costly and expensive to implement. To address these challenges, we propose the Non-Recursive Cluster-scale Graph Interacted (NRCGI) model, which reorganizes graph convolutional networks in a non-recursive and cluster-scale view to enable CTR models to consider deep graph information with low computational cost. NRCGI employs non-recursive cluster-scale graph aggregation, which allows the online recommendation computational complexity to shrink from tens of thousands of items to tens to hundreds of clusters. Additionally, since NRCGI aggregates neighbors in a non-recursive view, each hop of neighbors has a clear physical meaning. NRCGI explicitly constructs meaningful interactions between the hops of neighbors of users and items to fully model users' intent towards the given item. Experimental results demonstrate that NRCGI outperforms state-of-the-art baselines in three public datasets and one industrial dataset while maintaining efficient inference.

Training graph neural networks (GNNs) is extremely time consuming because sparse graph-based operations are hard to be accelerated by community hardware. Prior art successfully reduces the computation cost of dense matrix based operations (e.g., convolution and linear) via sampling-based approximation. However, unlike dense matrices, sparse matrices are stored in the irregular data format such that each row/column may have different number of non-zero entries. Thus, compared to the dense counterpart, approximating sparse operations has two unique challenges (1) we cannot directly control the efficiency of approximated sparse operation since the computation is only executed on non-zero entries; (2) sampling sparse matrices is much more inefficient due to the irregular data format. To address the issues, our key idea is to control the accuracy-efficiency trade off by optimizing computation resource allocation layer-wisely and epoch-wisely. For the first challenge, we customize the computation resource to different sparse operations, while limit the total used resource below a certain budget. For the second challenge, we cache previous sampled sparse matrices to reduce the epoch-wise sampling overhead. Finally, we propose a switching mechanisms to improve the generalization of GNNs trained with approximated operations. To this end, we propose Randomized Sparse Computation. In practice, rsc can achieve up to 11.6X speedup for a single sparse operation and 1.6X end-to-end wall-clock time speedup with almost no accuracy drop.

Sequential recommender systems have demonstrated a huge success for next-item recommendation by explicitly exploiting the temporal order of users' historical interactions. In practice, user interactions contain more useful temporal information beyond order, as shown by some pioneering studies. In this paper, we systematically investigate various temporal information for sequential recommendation and identify three types of advantageous temporal patterns beyond order, including absolute time information, relative item time intervals and relative recommendation time intervals. We are the first to explore item-oriented absolute time patterns. While existing models consider only one or two of these three patterns, we propose a novel holistic temporal pattern based neural network, named HTP, to fully leverage all these three patterns. In particular, we introduce novel components to address the subtle correlations between relative item time intervals and relative recommendation time intervals, which render a major technical challenge. Extensive experiments on three real-world benchmark datasets show that our HTP model consistently and substantially outperforms many state-of-the-art models. Our code is publically available at https://github.com/623851394/HTP/tree/main/HTP-main.

Knowledge graph (KG) reasoning utilizes two primary techniques, i.e., rule-based and KG-embedding based. The former provides precise inferences, but inferring via concrete rules is not scalable. The latter enables efficient reasoning at the cost of ambiguous inference accuracy. Neuro-symbolic reasoning seeks to amalgamate the advantages of both techniques. The crux of this approach is replacing the predicted existence of all possible triples (i.e., truth scores inferred from rules) with a suitable approximation grounded in embedding representations. However, constructing an effective approximation of all possible triples' truth scores is a challenging task, because it needs to balance the tradeoff between accuracy and efficiency, while compatible with both the rule-based and KG-embedding models. To this end, we proposed a differentiable framework - DiffLogic. Instead of directly approximating all possible triples, we design a tailored filter to adaptively select essential triples based on the dynamic rules and weights. The truth scores assessed by KG-embedding are continuous, so we employ a continuous Markov logic network named probabilistic soft logic (PSL). It employs the truth scores of essential triples to assess the overall agreement among rules, weights, and observed triples. PSL enables end-to-end differentiable optimization, so we can alternately update embedding and weighted rules. On benchmark datasets, we empirically show that DiffLogic surpasses baselines in both effectiveness and efficiency.

Recommending cold items in recommendation systems is a longstanding challenge due to the inherent differences between warm items, which are recommended based on user behavior, and cold items, which are recommended based on content features. To tackle this, generative models generate synthetic embeddings from content features, while dropout models enhance the robustness of the recommendation system by randomly dropping behavioral embeddings during training. However, these models primarily focus on handling the recommendation of cold items, but do not effectively address the differences between warm and cold recommendations. As a result, generative models may over-recommend either warm or cold items, neglecting the other type, and dropout models may negatively impact warm item recommendations. To address this, we propose the Aligning Distillation (ALDI) framework, which leverages warm items as "teachers" to transfer their behavioral information to cold items, referred to as "students". ALDI aligns the students with the teachers by comparing the differences in their recommendation characters, using tailored rating distribution aligning, ranking aligning, and identification aligning losses to narrow these differences. Furthermore, ALDI incorporates a teacher-qualifying weighting structure to prevent students from learning inaccurate information from unreliable teachers. Experiments on three datasets show that our approach outperforms state-of-the-art baselines in terms of overall, warm, and cold recommendation performance with three different recommendation backbones.

The graph neural network-based collaborative filtering (CF) models user-item interactions as a bipartite graph and performs iterative aggregation to enhance performance. Unfortunately, the aggregation process may amplify the popularity bias, which impedes user engagement with niche (unpopular) items. While some efforts have studied the popularity bias in CF, they often focus on modifying loss functions, which can not fully address the popularity bias in GNN-based CF models. This is because the debiasing loss can be falsely backpropagated to non-target nodes during the backward pass of the aggregation.

Knowledge graphs (KGs) could effectively integrate a large number of real-world assertions, and improve the performance of various applications, such as recommendation and search. KG error detection has been intensively studied since real-world KGs inevitably contain erroneous triples. While existing studies focus on developing a novel algorithm dedicated to one or a few data characteristics, we explore advancing KG error detection by assembling a set of state-of-the-art (SOTA) KG error detectors. However, it is nontrivial to develop a practical ensemble learning framework for KG error detection. Existing ensemble learning models heavily rely on labels, while it is expensive to acquire labeled errors in KGs. Also, KG error detection itself is challenging since triples contain rich semantic information and might be false because of various reasons. To this end, we propose to leverage active learning to minimize human efforts. Our proposed framework - KAEL, could effectively assemble a set of off-the-shelf error detection algorithms, by actively using a limited number of manual annotations. It adaptively updates the ensemble learning policy in each iteration based on active queries, i.e., the answers from experts. After all annotation budget is used, KAEL utilizes the trained policy to identify remaining suspicious triples. Experiments on real-world KGs demonstrate that we can achieve significant improvement when applying KAEL to assemble SOTA error detectors. KAEL also outperforms SOTA ensemble learning baselines significantly.

A knowledge graph (KG) consists of numerous triples, in which each triple, i.e., (head entity, relation, tail entity), denotes a real-world assertion. Many large-scale KGs have been developed, e.g., general-purpose KGs Freebase and YAGO. Also, lots of domain-specific KGs are emerging, e.g., COVID-19 KGs, biomedical KGs, and agricultural KGs. By embedding KGs into low-dimensional vectors, i.e., representations of entities and relations, we could integrate KGs into machine learning models and enhance the performance of many prediction tasks, including search, recommendations, and question answering. During the construction, refinement, embedding, and application of KGs, a variety of KG learning algorithms have been developed to handle challenges in various real-world scenarios. Moreover, graph neural networks have also brought new opportunities to KG learning. This workshop aims to engage with active researchers from KG communities, recommendation communities, natural language processing communities, and other communities, and deliver state-of-the-art research insights into the core challenges in KG learning.

Self-supervised learning (SSL) has been demonstrated to be effective in pre-training models that can be generalized to various downstream tasks. Graph Autoencoder (GAE), an increasingly popular SSL approach on graphs, has been widely explored to learn node representations without ground-truth labels. However, recent studies show that existing GAE methods could only perform well on link prediction tasks, while their performance on classification tasks is rather limited. This limitation casts doubt on the generalizability and adoption of GAE. In this paper, for the first time, we show that GAE can generalize well to both link prediction and classification scenarios, including node-level and graph-level tasks, by redesigning its critical building blocks from the graph masking perspective. Our proposal is called Self-Supervised Graph Autoencoder--S2GAE, which unleashes the power of GAEs with minimal yet nontrivial efforts. Specifically, instead of reconstructing the whole input structure, we randomly mask a portion of edges and learn to reconstruct these missing edges with an effective masking strategy and an expressive decoder network. Moreover, we theoretically prove that S2GAE could be regarded as an edge-level contrastive learning framework, providing insights into why it generalizes well. Empirically, we conduct extensive experiments on 21 benchmark datasets across link prediction and node & graph classification tasks. The results validate the superiority of S2GAE against state-of-the-art generative and contrastive methods. This study demonstrates the potential of GAE as a universal representation learner on graphs. Our code is publicly available at https://github.com/qiaoyu-tan/S2GAE.

Knowledge graphs (KGs) have been widely used to enhance complex question answering (QA). To understand complex questions, existing studies employ language models (LMs) to encode contexts. Despite the simplicity, they neglect the latent relational information among question concepts and answers in KGs. While question concepts ubiquitously present hyponymy at the semantic level, e.g., mammals and animals, this feature is identically reflected in the hierarchical relations in KGs, e.g., a_type_of. Therefore, we are motivated to explore comprehensive reasoning by the hierarchical structures in KGs to help understand questions. However, it is non-trivial to reason over tree-like structures compared with chained paths. Moreover, identifying appropriate hierarchies relies on expertise. To this end, we propose HamQA, a novel Hierarchy-aware multi-hop Question Answering framework on knowledge graphs, to effectively align the mutual hierarchical information between question contexts and KGs. The entire learning is conducted in Hyperbolic space, inspired by its advantages of embedding hierarchical structures. Specifically, (i) we design a context-aware graph attentive network to capture context information. (ii) Hierarchical structures are continuously preserved in KGs by minimizing the Hyperbolic geodesic distances. The comprehensive reasoning is conducted to jointly train both components and provide a top-ranked candidate as an optimal answer. We achieve a higher ranking than the state-of-the-art multi-hop baselines on the official OpenBookQA leaderboard with an accuracy of 85%.

Graph anomaly detection (GAD) has wide applications in real-world networked systems. In many scenarios, people need to identify anomalies on new (sub)graphs, but they may lack labels to train an effective detection model. Since recent semi-supervised GAD methods, which can leverage the available labels as prior knowledge, have achieved superior performance than unsupervised methods, one natural idea is to directly adopt a trained semi-supervised GAD model to the new (sub)graphs for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issues, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the graph. Motivated by this, we formally define the problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph(s) and the unseen test graph(s). Nevertheless, it is a challenging task since only limited labels are available, and the normal data distribution may differ between training and testing data. Accordingly, we propose a data augmentation method namedAugAN(Augmentation forAnomaly andNormal distributions) to enrich training data and adopt a customized episodic training strategy for learning with the augmented data. Extensive experiments verify the effectiveness ofAugANin improving model generalizability.

Knowledge Graph (KG) errors introduce non-negligible noise, severely affecting KG-related downstream tasks. Detecting errors in KGs is challenging since the patterns of errors are unknown and diverse, while ground-truth labels are rare or even unavailable. A traditional solution is to construct logical rules to verify triples, but it is not generalizable since different KGs have distinct rules with domain knowledge involved. Recent studies focus on designing tailored detectors or ranking triples based on KG embedding loss. However, they all rely on negative samples for training, which are generated by randomly replacing the head or tail entity of existing triples. Such a negative sampling strategy is not enough for prototyping practical KG errors, e.g., (Bruce_Lee, place_of_birth, China), in which the three elements are often relevant, although mismatched. We desire a more effective unsupervised learning mechanism tailored for KG error detection. To this end, we propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED). It introduces contrastive learning into KG learning and provides a novel way of modeling KG. Instead of following the traditional setting, i.e., considering entities as nodes and relations as semantic edges, CAGED augments a KG into different hyper-views, by regarding each relational triple as a node. After joint training with KG embedding and contrastive learning loss, CAGED assesses the trustworthiness of each triple based on two learning signals, i.e., the consistency of triple representations across multi-views and the self-consistency within the triple. Extensive experiments on three real-world KGs show that CAGED outperforms state-of-the-art methods in KG error detection. Our codes and datasets are available at https://github.com/Qing145/CAGED.git.

Learning interest representation plays a core role in click-through rate prediction task. Existing Transformer-based approaches learn multi-interests from a sequence of interacted items with rich attributes. The attention weights explain how relevant an item's specific attribute sequence is to the user's interest. However, it implicitly assumes the independence of attributes regarding the same item, which may not always hold in practice. Empirically, the user places varied emphasis on different attributes to consider whether interacting with one item, which is unobserved. Independently modeling each attribute may allow attention to assign probability mass to some unimportant attributes. Collaborative attributes of varied emphasis can be incorporated to help the model more reasonably approximate attributes' relevance to others and generate refined interest representations.

Few-shot graph classification aims at predicting classes for graphs, given limited labeled graphs for each class. To tackle the bottleneck of label scarcity, recent works propose to incorporate few-shot learning frameworks for fast adaptations to graph classes with limited labeled graphs. Specifically, these works propose to accumulate meta-knowledge across diverse meta-training tasks, and then generalize such meta-knowledge to the target task with a disjoint label set. However, existing methods generally ignore task correlations among meta-training tasks while treating them independently. Nevertheless, such task correlations can advance the model generalization to the target task for better classification performance. On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. Then we further design a loss-based sampling strategy to select tasks with more correlated classes. Moreover, a task-specific classifier is proposed to utilize the learned task correlations for few-shot classification. Extensive experiments on four prevalent few-shot graph classification datasets demonstrate the superiority of FAITH over other state-of-the-art baselines.

Network anomaly detection is a crucial task since a few anomalies can cause huge losses. Semi-supervised anomaly detection methods can effectively leverage a small number of labels as prior knowledge to enhance detection accuracy. But in real-world scenarios, novel types of anomalies (i.e., unseen anomalies) usually exist on networks which may present different characteristics with the seen anomalies and are hard to be identified by prior semi-supervised anomaly detection methods. In this paper, we propose the novel problem of unseen network anomaly detection that aims to identify both seen and unseen anomalies to eliminate potential dangers. Accordingly, we propose a method called Multi-hypersphere Graph Learning (MHGL) to effectively leverage existing labels by learning fine-grained normal patterns to discriminate anomalies. Experiments demonstrate that MHGL outperforms state-of-the-art methods significantly.

The cold-start problem has been a long-standing issue in recommendation. Embedding-based recommendation models provide recommendations by learning embeddings for each user and item from historical interactions. Therefore, such embedding-based models perform badly for cold items which haven't emerged in the training set. The most common solutions are to generate the cold embedding for the cold item from its content features. However, the cold embeddings generated from contents have different distribution as the warm embeddings are learned from historical interactions. In this case, current cold-start methods are facing an interesting seesaw phenomenon, which improves the recommendation of either the cold items or the warm items but hurts the opposite ones. To this end, we propose a general framework named Generative Adversarial Recommendation (GAR). By training the generator and the recommender adversarially, the generated cold item embeddings can have similar distribution as the warm embeddings that can even fool the recommender. Simultaneously, the recommender is fine-tuned to correctly rank the "fake'' warm embeddings and the real warm embeddings. Consequently, the recommendation of the warms and the colds will not influence each other, thus avoiding the seesaw phenomenon. Additionally, GAR could be applied to any off-the-shelf recommendation model. Experiments on two datasets present that GAR has strong overall recommendation performance in cold-starting both the CF-based model (improved by over 30.18%) and the GNN-based model (improved by over 17.78%).

Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and predict their next items. The accumulated user behavior records on real systems could be very long. This rich data brings opportunities to track actual interests of users. Prior efforts mainly focus on making recommendations based on relatively recent behaviors. However, the overall sequential data may not be effectively utilized, as early interactions might affect users' current choices. Also, it has become intolerable to scan the entire behavior sequence when performing inference for each user, since real-world system requires short response time. To bridge the gap, we propose a novel long sequential recommendation model, called Dynamic Memory-based Attention Network (DMAN). It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve long-term interests of users. To improve memory fidelity, DMAN dynamically abstracts each user's long-term interest into its own memory blocks by minimizing an auxiliary reconstruction loss. Based on the dynamic memory, the user's short-term and long-term interests can be explicitly extracted and combined for efficient joint recommendation. Empirical results over four benchmark datasets demonstrate the superiority of our model in capturing long-term dependency over various state-of-the-art sequential models.

Knowledge graphs (KGs) are of great importance in various artificial intelligence systems, such as question answering, relation extraction, and recommendation. Nevertheless, most real-world KGs are highly incomplete, with many missing relations between entities. To discover new triples (i.e., head entity, relation, tail entity), many KG completion algorithms have been proposed in recent years. However, a vast majority of existing studies often require a large number of training triples for each relation, which contradicts the fact that the frequency distribution of relations in KGs often follows a long tail distribution, meaning a majority of relations have only very few triples. Meanwhile, since most existing large-scale KGs are constructed automatically by extracting information from crowd-sourcing data using heuristic algorithms, plenty of errors could be inevitably incorporated due to the lack of human verification, which greatly reduces the performance for KG completion. To tackle the aforementioned issues, in this paper, we study a novel problem of error-aware few-shot KG completion and present a principled KG completion framework REFORM. Specifically, we formulate the problem under the few-shot learning framework, and our goal is to accumulate meta-knowledge across different meta-tasks and generalize the accumulated knowledge to the meta-test task for error-aware few-shot KG completion. To address the associated challenges resulting from insufficient training samples and inevitable errors, we propose three essential modules neighbor encoder, cross-relation aggregation, and error mitigation in each meta-task. Extensive experiments on three widely used KG datasets demonstrate the superiority of the proposed framework REFORM over competitive baseline methods.

Attributed network anomaly detection is essential in various networked systems. It aims to detect nodes that significantly deviate from their corresponding background. In conventional anomaly detection, the background is defined as the vast majority. But in networks, anomalies can be local and look normal when compared with the majority. While several efforts have explored to consider communities as the background, it remains challenging to learn suitable communities for effective anomaly detection. Also, the patterns of anomalies are unknown and it is nontrivial to define criteria of anomalies. To bridge the gap, in this paper, we argue that, by using appropriate models, it is sufficient to simply consider neighbor nodes as the background to detect anomalies. Correspondingly, we propose a novel abnormality-aware graph neural network (AAGNN). It utilizes subtractive aggregation to represent each node as the deviation from its neighbors (the background). Normal nodes with high confidence are employed as labels to learn a tailored hypersphere as the criterion of anomalies. Experiments demonstrate that AAGNN surpasses state-of-the-art methods significantly.

Graph alignment aims to identify node correspondence across multiple graphs, with significant implications in various domains. As supervision information is often not available, unsupervised methods have attracted a surge of research interest recently. Most of existing unsupervised methods assume that corresponding nodes should have similar local structure, which, however, often does not hold. Meanwhile, rich node attributes are often available and have shown to be effective in alleviating the above local topology inconsistency issue. Motivated by the success of graph convolution networks (GCNs) in fusing network and node attributes for various learning tasks, we aim to tackle the graph alignment problem on the basis of GCNs. However, directly grafting GCNs to graph alignment is often infeasible due to multi-faceted challenges. To bridge the gap, we propose a novel unsupervised graph alignment framework WAlign. We first develop a lightweight GCN architecture to capture both local and global graph patterns and their inherent correlations with node attributes. Then we prove that in the embedding space, obtaining optimal alignment results is equivalent to minimizing the Wasserstein distance between embeddings of nodes from different graphs. Towards this, we propose a novel Wasserstein distance discriminator to identify candidate node correspondence pairs for updating node embeddings. The whole process acts like a two-player game, and in the end, we obtain discriminative embeddings that are suitable for the alignment task. Extensive experiments on both synthetic and real-world datasets validate the effectiveness and efficiency of the proposed framework WAlign.

Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vectors when GNNs keep recursively aggregating the representations of neighbors. To enable deep GNNs, several methods have been explored recently. But they are developed from either techniques in convolutional neural networks or heuristic strategies. There is no generalizable and theoretical principle to guide the design of deep GNNs. To this end, we analyze the bottleneck of deep GNNs by leveraging the Dirichlet energy of node embeddings, and propose a generalizable principle to guide the training of deep GNNs. Based on it, a novel deep GNN framework -- Energetic Graph Neural Networks (EGNN) is designed. It could provide lower and upper constraints in terms of Dirichlet energy at each layer to avoid over-smoothing. Experimental results demonstrate that EGNN achieves state-of-the-art performance by using deep layers.

Session-based recommendation aims to predict the next item that is most likely to be clicked by an anonymous user, based on his/her clicking sequence within one visit. It becomes an essential function of many recommender systems since it protects privacy. However, as the accumulated session records keep increasing, it becomes challenging to model the user interests since they would drift when the time span is large. Efforts have been devoted to handling dynamic user interests by modeling all historical sessions at one time or conducting offline retraining regularly. These solutions are far from practical requirements in terms of efficiency and capturing timely user interests. To this end, we propose a memory-efficient framework - TASRec. It constructs a graph for each day to model the relations among items. Thus, the same item on different days could have different neighbors, corresponding to the drifting user interests. We design a tailored graph neural network to embed this dynamic graph of items and learn temporal augmented item representations. Based on this, we leverage a sequential neural architecture to predict the next item of a given sequence. Experiments on real-world datasets demonstrate that TASRec outperforms state-of-the-art session-based recommendation methods.

Interpersonal ties describe the intensity of information and activity interactions among individuals. It plays a critical role in social network analysis and sociological studies. Existing efforts focus on leveraging individuals' non-structural characteristics to measure tie strength. With the booming of online social networks (OSNs), it has become difficult to process and measure all the non-structural data. We study the tie strength measuring from the network topological aspect. However, it remains a nontrivial task due to the controversial comprehensions of its definition and the large volume of OSNs. To tackle the challenges, we develop a scalable measuring framework - IETSM. From the network view, we formally define the tie strength of an edge as the inverse of its impact on the similarity between its two nodes' influences in information diffusion. To measure this impact, IETSM constructs a node's influence as the embedding learned from its neighborhoods inductively. It estimates the tie strength of an edge through its impact on its nodes' influences brought by deleting it. The learned tie strength scores could, in turn, facilitate the node representation learning, and we update them iteratively. Experiments on real-world datasets demonstrate the effectiveness and efficiency of IETSM.

The classification of graph-structured data has be-come increasingly crucial in many disciplines. It has been observed that the implicit or explicit hierarchical community structures preserved in real-world graphs could be useful for downstream classification applications. A straightforward way to leverage the hierarchical structure is to make use the pooling algorithms to cluster nodes into fixed groups, and shrink the input graph layer by layer to learn the pooled graphs.However, the pool shrinking discards the graph details to make it hard to distinguish two non-isomorphic graphs, and the fixed clustering ignores the inherent multiple characteristics of nodes. To compensate the shrinking loss and learn the various nodes’ characteristics, we propose the multi-channel graph neural networks (MuchGNN). Motivated by the underlying mechanisms developed in convolutional neural networks, we define the tailored graph convolutions to learn a series of graph channels at each layer, and shrink the graphs hierarchically to en-code the pooled structures. Experimental results on real-world datasets demonstrate the superiority of MuchGNN over the state-of-the-art methods.

Graph neural networks (GNNs), which learn the representation of a node by aggregating its neighbors, have become an effective computational tool in downstream applications. Over-smoothing is one of the key issues which limit the performance of GNNs as the number of layers increases. It is because the stacked aggregators would make node representations converge to indistinguishable vectors. Several attempts have been made to tackle the issue by bringing linked node pairs close and unlinked pairs distinct. However, they often ignore the intrinsic community structures and would result in sub-optimal performance. The representations of nodes within the same community/class need be similar to facilitate the classification, while different classes are expected to be separated in embedding space. To bridge the gap, we introduce two over-smoothing metrics and a novel technique, i.e., differentiable group normalization (DGN). It normalizes nodes within the same group independently to increase their smoothness, and separates node distributions among different groups to significantly alleviate the over-smoothing issue. Experiments on real-world datasets demonstrate that DGN makes GNN models more robust to over-smoothing and achieves better performance with deeper GNNs.

Feature embedding aims to learn a low-dimensional vector representation for each instance to preserve the information in its features. These representations can benefit various offthe-shelf learning algorithms. While embedding models for a single type of features have been well-studied, real-world instances often contain multiple types of correlated features or even information within a different modality such as networks. Existing studies such as multiview learning show that it is promising to learn unified vector representations from all sources. However, high computational costs of incorporating heterogeneous information limit the applications of existing algorithms. The number of instances and dimensions of features in practice are often large. To bridge the gap, we propose a scalable framework FeatWalk, which can model and incorporate instance similarities in terms of different types of features into a unified embedding representation. To enable the scalability, FeatWalk does not directly calculate any similarity measure, but provides an alternative way to simulate the similarity-based random walks among instances to extract the local instance proximity and preserve it in a set of instance index sequences. These sequences are homogeneous with each other. A scalable word embedding algorithm is applied to them to learn a joint embedding representation of instances. Experiments on four real-world datasets demonstrate the efficiency and effectiveness of FeatWalk.

Anomaly detection in attributed networks (instance-to-instance dependencies and interactions are available) has various applications such as monitoring suspicious accounts in social media and financial fraud in transaction networks. However, it remains a challenging task since the definition of anomaly becomes more complicated and topological structures are heterogeneous with nodal attributes. In this paper, we propose a spectral convolution and deconvolution based framework - SpecAE, to project the attributed network into a tailored space to detect global and community anomalies. SpecAE leverages Laplacian sharpening to amplify the distances between representations of anomalies and the ones of the majority. The learned representations along with reconstruction errors are combined with a density estimation model to perform the detection. Experiments on real-world datasets demonstrate the effectiveness of the proposed SpecAE.

Arguably, every entity in this universe is networked in one wayr another. With the prevalence of network data collected, such as social media and biological networks, learning from networks has become an essential task in many applications. It is well recognized that network data is intricate and large-scale, and analytic tasks on network data become more and more sophisticated. In this tutorial, we systematically review the area of learning from networks, including algorithms, theoretical analysis, and illustrative applications. Starting with a quick recollection of the exciting history of the area, we formulate the core technical problems. Then, we introduce the fundamental approaches, that is, the feature selection based approaches and the network embedding based approaches. Next, we extend our discussion to attributed networks, which are popular in practice. Last, we cover the latest hot topic, graph neural based approaches. For each group of approaches, we also survey the associated theoretical analysis and real-world application examples. Our tutorial also inspires a series of open problems and challenges that may lead to future breakthroughs. The authors are productive and seasoned researchers active in this area who represent a nice combination of academia and industry.

Random walks are widely adopted in various network analysis tasks ranging from network embedding to label propagation. It could capture and convert geometric structures into structured sequences while alleviating the issues of sparsity and curse of dimensionality. Though random walks on plain networks have been intensively studied, in real-world systems, nodes are often not pure vertices, but own different characteristics, described by the rich set of data associated with them. These node attributes contain plentiful information that often complements the network, and bring opportunities to the random-walk-based analysis. However, it is unclear how random walks could be developed for attributed networks towards an effective joint information extraction. Node attributes make the node interactions more complicated and are heterogeneous with respect to topological structures.

Question answering over knowledge graph (QA-KG) aims to use facts in the knowledge graph (KG) to answer natural language questions. It helps end users more efficiently and more easily access the substantial and valuable knowledge in the KG, without knowing its data structures. QA-KG is a nontrivial problem since capturing the semantic meaning of natural language is difficult for a machine. Meanwhile, many knowledge graph embedding methods have been proposed. The key idea is to represent each predicate/entity as a low-dimensional vector, such that the relation information in the KG could be preserved. The learned vectors could benefit various applications such as KG completion and recommender systems. In this paper, we explore to use them to handle the QA-KG problem. However, this remains a challenging task since a predicate could be expressed in different ways in natural language questions. Also, the ambiguity of entity names and partial names makes the number of possible answers large. To bridge the gap, we propose an effective Knowledge Embedding based Question Answering (KEQA) framework. We focus on answering the most common types of questions, i.e., simple questions, in which each question could be answered by the machine straightforwardly if its single head entity and single predicate are correctly identified. To answer a simple question, instead of inferring its head entity and predicate directly, KEQA targets at jointly recovering the question's head entity, predicate, and tail entity representations in the KG embedding spaces. Based on a carefully-designed joint distance metric, the three learned vectors' closest fact in the KG is returned as the answer. Experiments on a widely-adopted benchmark demonstrate that the proposed KEQA outperforms the state-of-the-art QA-KG methods.

Link prediction in social networks is to infer the new links likely to be formed next or to reconstruct the links that are currently missing. Other than the pure topological network structures, social networks are often associated with rich information of social activities of users, such as tweeting, retweeting, and replying. Social theories such as social influence indicate that social activities could have potential impacts on the neighbors, and links in social media could be the results of the social influence among users. It motivates us to learn and model social influence among users to tackle the link prediction problem. However, this is a non-trivial task since it is challenging to model heterogeneous social activities. Traditional methods often define universal metrics of social influence for all users, but even for the same activity of a user, the influence towards different neighbors might not be the same. It motivates a personalized learning schema. In information theory, if a time-series signal influences another, then the uncertainty in the latter one will be reduced, given the distribution of the former one. Thus, we are motivated to learn social influence based on the timestamps of social activities. Given the timestamps of each user, we use entropy to measure the reduction of uncertainty of his/her neighbors. The learned social influence is then incorporated into a graph based link prediction model to perform joint learning. Through comprehensive experiments, we demonstrate that the proposed framework can perform better than the state-of-the-art methods on different real-world networks.

Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While existing work focuses on generating adversarial perturbations in multiclass classification problems, many real-world applications fall into the multi-label setting, in which one instance could be associated with more than one label. To analyze the vulnerability and robustness of multi-label learning models, we investigate the generation of multi-label adversarial perturbations. This is a challenging task due to the uncertain number of positive labels associated with one instance, and the fact that multiple labels are usually not mutually exclusive with each other. To bridge the gap, in this paper, we propose a general attacking framework targeting multi-label classification problem and conduct a premier analysis on the perturbations for deep neural networks. Leveraging the ranking relationships among labels, we further design a ranking-based framework to attack multi-label ranking algorithms. Experiments on two different datasets demonstrate the effectiveness of the proposed frameworks and provide insights of the vulnerability of multi-label deep models under diverse targeted attacks.

Network embedding has been increasingly used in many network analytics applications to generate low-dimensional vector representations, so that many off-the-shelf models can be applied to solve a wide variety of data mining tasks. However, similar to many other machine learning methods, network embedding results remain hard to be understood by users. Each dimension in the embedding space usually does not have any specific meaning, thus it is difficult to comprehend how the embedding instances are distributed in the reconstructed space. In addition, heterogeneous content information may be incorporated into network embedding, so it is challenging to specify which source of information is effective in generating the embedding results. In this paper, we investigate the interpretation of network embedding, aiming to understand how instances are distributed in embedding space, as well as explore the factors that lead to the embedding results. We resort to the post-hoc interpretation scheme, so that our approach can be applied to different types of embedding methods. Specifically, the interpretation of network embedding is presented in the form of a taxonomy. Effective objectives and corresponding algorithms are developed towards building the taxonomy. We also design several metrics to evaluate interpretation results. Experiments on real-world datasets from different domains demonstrate that, by comparing with the state-of-the-art alternatives, our approach produces effective and meaningful interpretation to embedding results.

Attributed network embedding has been widely used in modeling real-world systems. The obtained low-dimensional vector representations of nodes preserve their proximity in terms of both network topology and node attributes, upon which different analysis algorithms can be applied. Recent advances in explanation-based learning and human-in-the-loop models show that by involving experts, the performance of many learning tasks can be enhanced. It is because experts have a better cognition in the latent information such as domain knowledge, conventions, and hidden relations. It motivates us to employ experts to transform their meaningful cognition into concrete data to advance network embedding. However, learning and incorporating the expert cognition into the embedding remains a challenging task. Because expert cognition does not have a concrete form, and is difficult to be measured and laborious to obtain. Also, in a real-world network, there are various types of expert cognition such as the comprehension of word meaning and the discernment of similar nodes. It is nontrivial to identify the types that could lead to a significant improvement in the embedding. In this paper, we study a novel problem of exploring expert cognition for attributed network embedding and propose a principled framework NEEC. We formulate the process of learning expert cognition as a task of asking experts a number of concise and general queries. Guided by the exemplar theory and prototype theory in cognitive science, the queries are systematically selected and can be generalized to various real-world networks. The returned answers from the experts contain their valuable cognition. We model them as new edges and directly add into the attributed network, upon which different embedding methods can be applied towards a more informative embedding representation. Experiments on real-world datasets verify the effectiveness and efficiency of NEEC.

Network analysis has been widely applied in many real-world tasks, such as gene analysis and targeted marketing. To extract effective features for these analysis tasks, network embedding automatically learns a low-dimensional vector representation for each node, such that the meaningful topological proximity is well preserved. While the embedding algorithms on pure topological structure have attracted considerable attention, in practice, nodes are often abundantly accompanied with other types of meaningful information, such as node attributes, second-order proximity, and link directionality. A general framework for incorporating the heterogeneous information into network embedding could be potentially helpful in learning better vector representations. However, it remains a challenging task to jointly embed the geometrical structure and a distinct type of information due to the heterogeneity. In addition, the real-world networks often contain a large number of nodes, which put demands on the scalability of the embedding algorithms. To bridge the gap, in this article, we propose a general embedding framework named Heterogeneous Information Learning in Large-scale networks (HILL) to accelerate the joint learning. It enables the simultaneous node proximity assessing process to be done in a distributed manner by decomposing the complex modeling and optimization into many simple and independent sub-problems. We validate the significant correlation between the heterogeneous information and topological structure, and illustrate the generalizability of HILL by applying it to perform attributed network embedding and second-order proximity learning. A variation is proposed for link directionality modeling. Experimental results on real-world networks demonstrate the effectiveness and efficiency of HILL.

Attributed networks, in which network connectivity and node attributes are available, have been increasingly used to model real-world information systems, such as social media and e-commerce platforms. While outlier detection has been extensively studied to identify anomalies that deviate from certain chosen background, existing algorithms cannot be directly applied on attributed networks due to the heterogeneous types of information and the scale of real-world data. Meanwhile, it has been observed that local anomalies, which may align with global condition, are hard to be detected by existing algorithms with interpretability. Motivated by the observations, in this paper, we propose to study the problem of effective and efficient local anomaly detection in attributed networks. In particular, we design a collective way for modeling heterogeneous network and attribute information, and develop a novel and efficient distributed optimization algorithm to handle large-scale data. In the experiments, we compare the proposed framework with the state-of-the-art methods on both real and synthetic datasets, and demonstrate its effectiveness and efficiency through quantitative evaluation and case studies.

Tensor completion has become an effective computational tool in many real-world data-driven applications. Beyond traditional static setting, with the increasing popularity of high velocity streaming data, it requires efficient online processing without reconstructing the whole model from scratch. Existing work on streaming tensor completion is usually built upon the assumption that tensors only grow in one mode. Unfortunately, the assumption does not hold in many real-world situations in which tensors may grow in multiple modes, i.e., multi-aspect streaming tensors. Efficiently modeling and completing these incremental tensors without sacrificing its effectiveness remains a challenging task due to the uncertainty of tensor mode changes and complex data structure of multi-aspect streaming tensors. To bridge this gap, we propose a Multi-Aspect Streaming Tensor completion framework (MAST) based on CANDECOMP/PARAFAC (CP) decomposition to track the subspace of general incremental tensors for completion. In addition, we investigate a special situation where time is one mode of the tensors, and leverage its extra structure information to improve the general framework towards higher effectiveness. Experimental results on four datasets collected from various real-world applications demonstrate the effectiveness and efficiency of the proposed framework.

Network embedding is to learn low-dimensional vector representations for nodes in a network. It has shown to be effective in a variety of tasks such as node classification and link prediction. While embedding algorithms on pure networks have been intensively studied, in many real-world applications, nodes are often accompanied with a rich set of attributes or features, aka attributed networks. It has been observed that network topological structure and node attributes are often strongly correlated with each other. Thus modeling and incorporating node attribute proximity into network embedding could be potentially helpful, though non-trivial, in learning better vector representations. Meanwhile, real-world networks often contain a large number of nodes and features, which put demands on the scalability of embedding algorithms. To bridge the gap, in this paper, we propose an accelerated attributed network embedding algorithm AANE, which enables the joint learning process to be done in a distributed manner by decomposing the complex modeling and optimization into many sub-problems. Experimental results on several real-world datasets demonstrate the effectiveness and efficiency of the proposed algorithm.

Attributed network embedding aims to seek low-dimensional vector representations for nodes in a network, such that original network topological structure and node attribute proximity can be preserved in the vectors. These learned representations have been demonstrated to be helpful in many learning tasks such as network clustering and link prediction. While existing algorithms follow an unsupervised manner, nodes in many real-world attributed networks are often associated with abundant label information, which is potentially valuable in seeking more effective joint vector representations. In this paper, we investigate how labels can be modeled and incorporated to improve attributed network embedding. This is a challenging task since label information could be noisy and incomplete. In addition, labels are completely distinct with the geometrical structure and node attributes. The bewildering combination of heterogeneous information makes the joint vector representation learning more difficult. To address these issues, we propose a novel Label informed Attributed Network Embedding (LANE) framework. It can smoothly incorporate label information into the attributed network embedding while preserving their correlations. Experiments on real-world datasets demonstrate that the proposed framework achieves significantly better performance compared with the state-of-the-art embedding algorithms.