Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Luzhi Wang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hi-GMAE: Hierarchical Graph Masked Autoencoders

    by Chuang Liu, Zelin Yao, Xueqi Ma, Mukun Chen, Luzhi Wang, Jia Wu, Wenbin Hu


  • Open Access

    A Graph Foundation Model for Unified Anomaly Detection

    by Renda Han, Xiaobao Wang, Luzhi Wang, Wenxin Zhang, Guangzhen Yao, Hongxiang Liang


  • Open Access

    Cross-Type Semantic Alignment for Multi-Type Anomaly Detection in Heterogeneous Graphs

    by Di Jin, Xiao Huang, Xiaobao Wang, Fengyu Yan, Luzhi Wang, Hongxiang Liang

    Graph Anomaly Detection (GAD) is critical in applications such as fraud prevention, cybersecurity, and social governance. While Graph Neural Networks (GNNs) have achieved remarkable success in detecting anomalies on homogeneous graphs, they face fundamental challenges in real-world heterogeneous settings involving diverse node types and imbalanced semantic richness. In heterogeneous graphs, nodes often vary significantly in semantic richness, with anomalies potentially spanning multiple types and emerging implicitly through cross-type dependencies. We identify two core limitations of existing methods: (i) the ineffective propagation of discriminative anomaly cues from informative to sparse nodes due to semantic imbalance, and (ii) conflicting optimization objectives arising from joint detection across multiple node types. To address these issues, we propose CSA-MTHGAD, a novel framework that integrates smoothness-guided cross-type semantic alignment with dynamic multi-task learning. It selectively propagates anomaly-sensitive features across types and harmonizes task-specific gradients through adaptive projection and weighting.To facilitate research, we employ two real-world heterogeneous benchmarks in the domain of social governance. Extensive experiments demonstrate that CSA-MTHGAD achieves superior performance over state-of-the-art baselines in accuracy, robustness, and generalization for multi-type anomaly detection.

  • Open Access

    GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

    by Luzhi Wang, Dongxiao He, He Zhang, Yixin Liu, Wenjie Wang, Shirui Pan, Di Jin, Tat-Seng Chua

    Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted with samples from an unfamiliar distribution (out-of-distribution, OOD). To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. Despite their effectiveness, these methods come with heavy training resources and costs, as they need to optimize the GNN-based models on training data. Moreover, their reliance on modifying the original GNNs and accessing training data further restricts their universality. To this end, this paper introduces a method to detect Graph Out-of-Distribution At Test-time (namely GOODAT), a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture. With a lightweight graph masker, GOODAT can learn informative subgraphs from test samples, enabling the capture of distinct graph patterns between OOD and ID samples. To optimize the graph masker, we meticulously design three unsupervised objective functions based on the graph information bottleneck principle, motivating the masker to capture compact yet informative subgraphs for OOD detection. Comprehensive evaluations confirm that our GOODAT method outperforms state-of-the-art benchmarks across a variety of real-world datasets.


  • Open Access

    GOODAT: Towards Test-time Graph Out-of-Distribution Detection

    by Luzhi Wang, Dongxiao He, He Zhang, Yixin Liu, Wenjie Wang, Shirui Pan, Di Jin, Tat-Seng Chua

    Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted with samples from an unfamiliar distribution (out-of-distribution, OOD). To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. Despite their effectiveness, these methods come with heavy training resources and costs, as they need to optimize the GNN-based models on training data. Moreover, their reliance on modifying the original GNNs and accessing training data further restricts their universality. To this end, this paper introduces a method to detect Graph Out-of-Distribution At Test-time (namely GOODAT), a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture. With a lightweight graph masker, GOODAT can learn informative subgraphs from test samples, enabling the capture of distinct graph patterns between OOD and ID samples. To optimize the graph masker, we meticulously design three unsupervised objective functions based on the graph information bottleneck principle, motivating the masker to capture compact yet informative subgraphs for OOD detection. Comprehensive evaluations confirm that our GOODAT method outperforms state-of-the-art benchmarks across a variety of real-world datasets. The code is available at Github: https://github.com/Ee1s/GOODAT

  • Open Access

    Contrastive Graph Similarity Networks

    by Luzhi Wang, Yizhen Zheng, Di Jin, Fuyi Li, Yongliang Qiao, Shirui Pan

    Graph similarity learning is a significant and fundamental issue in the theory and analysis of graphs, which has been applied in a variety of fields, including object tracking, recommender systems, similarity search, and so on. Recent methods for graph similarity learning that utilize deep learning typically share two deficiencies: (1) they leverage graph neural networks as backbones for learning graph representations but have not well captured the complex information inside data, and (2) they employ a cross-graph attention mechanism for graph similarity learning, which is computationally expensive. Taking these limitations into consideration, a method for graph similarity learning is devised in this study, namely, Contrastive Graph Similarity Network (CGSim). To enhance graph similarity learning, CGSim makes use of the complementary information of two input graphs and captures pairwise relations in a contrastive learning framework. By developing a dual contrastive learning module with a node-graph matching and a graph-graph matching mechanism, our method significantly reduces the quadratic time complexity for cross-graph interaction modeling to linear time complexity. Jointly learning in an end-to-end framework, the graph representation embedding module and the well-designed contrastive learning module can be beneficial to one another. A comprehensive series of experiments indicate that CGSim outperforms state-of-the-art baselines on six datasets and significantly reduces the computational cost, which demonstrates our CGSim model’s superiority over other baselines.


  • Open Access

    A Time-Sensitive Graph Neural Network for Session-Based New Item Recommendation

    by Luzhi Wang, Di Jin

    Session-based recommendation plays an important role in daily life and exists in many scenarios, such as online shopping websites and streaming media platforms. Recently, some works have focused on using graph neural networks (GNNs) to recommend new items in session-based scenarios. However, these methods have encountered several limitations. First, existing methods typically ignore the impact of items’ visited time in constructing session graphs, resulting in a departure from real-world recommendation dynamics. Second, sessions are often sparse, making it challenging for GNNs to learn valuable item embedding and user preferences. Third, the existing methods usually overemphasize the impact of the last item on user preferences, neglecting their interest in multiple items in a session. To address these issues, we introduce a time-sensitive graph neural network for new item recommendation in session-based scenarios, namely, TSGNN. Specifically, TSGNN provides a novel time-sensitive session graph constructing technique to solve the first problem. For the second problem, TSGNN introduces graph augmentation and contrastive learning into it. To solve the third problem, TSGNN designs a time-aware attention mechanism to accurately discern user preferences. By evaluating the compatibility between user preferences and candidate new item embeddings, our method recommends items with high relevance scores for users. Comparative experiments demonstrate the superiority of TSGNN over state-of-the-art (SOTA) methods.


  • Open Access

    A Survey on Fairness-aware Recommender Systems

    by Di Jin, Luzhi Wang, He Zhang, Yizhen Zheng, Weiping Ding, Feng Xia, Shirui Pan

    As information filtering services, recommender systems have extremely enriched our daily life by providing personalized suggestions and facilitating people in decision-making, which makes them vital and indispensable to human society in the information era. However, as people become more dependent on them, recent studies show that recommender systems potentially own unintentional impacts on society and individuals because of their unfairness (e.g., gender discrimination in job recommendations). To develop trustworthy services, it is crucial to devise fairness-aware recommender systems that can mitigate these bias issues. In this survey, we summarise existing methodologies and practices of fairness in recommender systems. Firstly, we present concepts of fairness in different recommendation scenarios, comprehensively categorize current advances, and introduce typical methods to promote fairness in different stages of recommender systems. Next, after introducing datasets and evaluation metrics applied to assess the fairness of recommender systems, we will delve into the significant influence that fairness-aware recommender systems exert on real-world industrial applications. Subsequently, we highlight the connection between fairness and other principles of trustworthy recommender systems, aiming to consider trustworthiness principles holistically while advocating for fairness. Finally, we summarize this review, spotlighting promising opportunities in comprehending concepts, frameworks, the balance between accuracy and fairness, and the ties with trustworthiness, with the ultimate goal of fostering the development of fairness-aware recommender systems.

  • Open Access

    Dual Intent Enhanced Graph Neural Network for Session-based New Item Recommendation

    by Di Jin, Luzhi Wang, Yizhen Zheng, Guojie Song, Fei Jiang, Xiang Li, Wei Lin, Shirui Pan

    Recommender systems are essential to various fields, e.g., e-commerce, e-learning, and streaming media. At present, graph neural networks (GNNs) for session-based recommendations normally can only recommend items existing in users’ historical sessions. As a result, these GNNs have difficulty recommending items that users have never interacted with (new items), which leads to a phenomenon of information cocoon. Therefore, it is necessary to recommend new items to users. As there is no interaction between new items and users, we cannot include new items when building session graphs for GNN session-based recommender systems. Thus, it is challenging to recommend new items for users when using GNN-based methods. We regard this challenge as “GNN Session-based New Item Recommendation (GSNIR)”. To solve this problem, we propose a dual-intent enhanced graph neural network for it. Due to the fact that new items are not tied to historical sessions, the users’ intent is difficult to predict. We design a dual-intent network to learn user intent from an attention mechanism and the distribution of historical data respectively, which can simulate users’ decision-making process in interacting with a new item. To solve the challenge that new items cannot be learned by GNNs, inspired by zero-shot learning (ZSL), we infer the new item representation in GNN space by using their attributes. By outputting new item probabilities, which contain recommendation scores of the corresponding items, the new items with higher scores are recommended to users. Experiments on two representative real-world datasets show the superiority of our proposed method. The case study from the real-world verifies interpretability benefits brought by the dual-intent module and the new item reasoning module.