Jianxin Li

One Pretrained Decision Model Is Enough for Training-Free Generalist Graph Anomaly Detection

Xinyu Zhao, Qingyun Sun, Ziwei Zhang +3

Graph anomaly detection (GAD) aims to identify irregular entities in graph-structured data, yet heterogeneous anomaly patterns and distributional differences across graphs challeng…

Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

Yi Huang, Qingyun Sun, Jia Li +2

Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational Deep Learning (RDL) addresse…

Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models

Haonan Yuan, Qingyun Sun, Junhua Shi +3

Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs fro…

Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

Xinyu Zhao, Qingyun Sun, Jiayi Luo +2

Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph da…

RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation

Haonan Yuan, Qingyun Sun, Jiacheng Tao +2

Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain c…

Is the Information Bottleneck Robust Enough? Towards Label-Noise Resistant Information Bottleneck Learning

Yi Huang, Qingyun Sun, Yisen Gao +3

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However,…

Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks

Jiayi Luo, Qingyun Sun, Yuecen Wei +3

Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. While it greatly improves the generalization of graph neural networks, its…

Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments

Qingyun Sun, Jiayi Luo, Haonan Yuan +4

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability un…

Robust Graph Condensation via Classification Complexity Mitigation

Jiayi Luo, Qingyun Sun, Beining Yang +5

Graph condensation (GC) has gained significant attention for its ability to synthesize smaller yet informative graphs. However, existing studies often overlook the robustness of GC…

GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning

Haonan Yuan, Qingyun Sun, Junhua Shi +4

Inspired by the remarkable success of foundation models in language and vision, Graph Foundation Models (GFMs) hold significant promise for broad applicability across diverse graph…

GraphKeeper: Graph Domain-Incremental Learning via Knowledge Disentanglement and Preservation

Zihao Guo, Qingyun Sun, Ziwei Zhang +4

Graph incremental learning (GIL), which continuously updates graph models by sequential knowledge acquisition, has garnered significant interest recently. However, existing GIL app…

Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction

Yisen Gao, Xingcheng Fu, Qingyun Sun +2

Graph diffusion models have made significant progress in learning structured graph data and have demonstrated strong potential for predictive tasks. Existing approaches typically e…

Robust Graph Learning Against Adversarial Evasion Attacks via Prior-Free Diffusion-Based Structure Purification

Jiayi Luo, Qingyun Sun, Haonan Yuan +2

Adversarial evasion attacks pose significant threats to graph learning, with lines of studies that have improved the robustness of Graph Neural Networks (GNNs). However, existing w…

Discrete Curvature Graph Information Bottleneck

Xingcheng Fu, Jian Wang, Yisen Gao +4

Graph neural networks(GNNs) have been demonstrated to depend on whether the node effective information is sufficiently passing. Discrete curvature (Ricci curvature) is used to stud…

Graph Size-imbalanced Learning with Energy-guided Structural Smoothing

Jiawen Qin, Pengfeng Huang, Qingyun Sun +3

Graph is a prevalent data structure employed to represent the relationships between entities, frequently serving as a tool to depict and simulate numerous systems, such as molecule…

DG-Mamba: Robust and Efficient Dynamic Graph Structure Learning with Selective State Space Models

Haonan Yuan, Qingyun Sun, Zhaonan Wang +5

Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy resul…

GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts

Zihao Guo, Qingyun Sun, Haonan Yuan +4

Real-world graphs have inherently complex and diverse topological patterns, known as topological heterogeneity. Most existing works learn graph representation in a single constant…

GC-Bench: An Open and Unified Benchmark for Graph Condensation

Qingyun Sun, Ziying Chen, Beining Yang +6

Graph condensation (GC) has recently garnered considerable attention due to its ability to reduce large-scale graph datasets while preserving their essential properties. The core c…

IGL-Bench: Establishing the Comprehensive Benchmark for Imbalanced Graph Learning

Jiawen Qin, Haonan Yuan, Qingyun Sun +8

Deep graph learning has gained grand popularity over the past years due to its versatility and success in representing graph data across a wide range of domains. However, the perva…

cs.LG2024★ 2 cited

Hyperbolic Geometric Latent Diffusion Model for Graph Generation

Xingcheng Fu, Yisen Gao, Yuecen Wei +4

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation…