Publications (28)
PrimeKG-CL: A Continual Graph Learning Benchmark on Evolving Biomedical Knowledge Graphs
Yousef A. Radwan, Yao Li, Qing Qing +5
Biomedical knowledge graphs underwrite drug repurposing and clinical decision support, yet the upstream ontologies they depend on update on independent cycles that add millions of…
UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains
Shuyi Miao, Wangjie Qiu, Shengda Zhuo +5
As cross-chain interoperability advances, decentralized finance (DeFi) protocols enable illicit funds to be reorganized into uniform liquid assets that flow throughout the cryptocu…
Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization
Yunxiao Zhao, Zhiqiang Wang, Xingtong Yu +3
Rationalization, a data-centric framework, aims to build self-explanatory models to explain the prediction outcome by generating a subset of human-intelligible pieces of the input…
Event-Aware Prompt Learning for Dynamic Graphs
Xingtong Yu, Ruijuan Liang, Renhe Jiang +4
Real-world graph typically evolve via a series of events, modeling dynamic interactions between objects across various domains. For dynamic graph learning, dynamic graph neural net…
A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning
Xingtong Yu, Yuan Fang, Zemin Liu +5
Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily r…
GraphReAct: Reasoning and Acting for Multi-step Graph Inference
Xingtong Yu, Zhongwei Kuai, Chang Zhou +6
Reasoning-acting frameworks enhance large language models (LLMs) by interleaving reasoning with actions for dynamic information acquisition. However, extending this paradigm to gra…
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
Quanxin Wang, Xuanting Xie, Bingheng Li +4
Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight prompts. However, existing methods operate within a…
Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs
Xingtong Yu, Zhenghao Liu, Yuan Fang +3
Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce label…
GCoT: Chain-of-Thought Prompt Learning for Graphs
Xingtong Yu, Chang Zhou, Zhongwei Kuai +2
Chain-of-thought (CoT) prompting has achieved remarkable success in natural language processing (NLP). However, its vast potential remains largely unexplored for graphs. This raise…
Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity
Shiyin Tan, Dongyuan Li, Renhe Jiang +3
Popularity bias occurs when popular items are recommended far more frequently than they should be, negatively impacting both user experience and recommendation accuracy. Existing d…
SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
Xingtong Yu, Zechuan Gong, Chang Zhou +2
Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a…
GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks
Zemin Liu, Xingtong Yu, Yuan Fang +1
Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neur…
UrbanGraphEmbeddings: Learning and Evaluating Spatially Grounded Multimodal Embeddings for Urban Science
Jie Zhang, Xingtong Yu, Yuan Fang +2
Learning transferable multimodal embeddings for urban environments is challenging because urban understanding is inherently spatial, yet existing datasets and benchmarks lack expli…
MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs
Xingtong Yu, Chang Zhou, Yuan Fang +1
Graphs can inherently model interconnected objects on the Web, thereby facilitating a series of Web applications, such as web analyzing and content recommendation. Recently, Graph…
Node-Time Conditional Prompt Learning In Dynamic Graphs
Xingtong Yu, Zhenghao Liu, Xinming Zhang +1
Dynamic graphs capture evolving interactions between entities, such as in social networks, online learning platforms, and crowdsourcing projects. For dynamic graph modeling, dynami…
Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Wenyu Zhang, Xin Deng, Baojun Jia +5
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-re…
CoEvoT: Co-Evolving Chain-of-Thought Prompting for Graph-LLM Reasoning
Haohua Niu, Xingtong Yu, Yang Liu +6
Graph learning under distribution shift presents a persistent challenge, where models adapt to new graphs with limited or even no supervision. Recent graph--LLM approaches move tow…
HyperClaim: Fine-Grained Cross-Modal Hypergraph Reasoning for Video Misinformation Detection
Xiangbo Wang, Jiasheng Zhang, Xingtong Yu +2
The paper introduces HyperClaim, a temporal hypergraph model that jointly reasons over query text, evidence text, and video frames to detect misinformation in videos, preserving fi…
Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models
Xingtong Yu, Chang Zhou, Yuan Fang +1
Given the ubiquity of graph data, it is intriguing to ask: Is it possible to train a graph foundation model on a broad range of graph data across diverse domains? A major hurdle to…
HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding
Peng Xia, Xingtong Yu, Ming Hu +4
Object categories are typically organized into a multi-granularity taxonomic hierarchy. When classifying categories at different hierarchy levels, traditional uni-modal approaches…
Learning Multi-Relational Graph Representations for DNA Methylation-Based Biological Age Estimation
Qing Qing, Xikun Zhang, Zhongyuan Zhang +7
Aging clocks aim to estimate biological age, a measure of physiological state distinct from chronological age, from observable biomarkers, and are widely used for health assessment…
Learning to Count Isomorphisms with Graph Neural Networks
Xingtong Yu, Zemin Liu, Yuan Fang +1
Subgraph isomorphism counting is an important problem on graphs, as many graph-based tasks exploit recurring subgraph patterns. Classical methods usually boil down to a backtrackin…
MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
Xingtong Yu, Chang Zhou, Xinming Zhang +1
Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated strong performance, they overlook…
Non-Homophilic Graph Pre-Training and Prompt Learning
Xingtong Yu, Jie Zhang, Yuan Fang +1
Graphs are ubiquitous for modeling complex relationships between objects across various fields. Graph neural networks (GNNs) have become a mainstream technique for graph-based appl…
HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning
Xingtong Yu, Yuan Fang, Zemin Liu +1
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their per…
StaR-KVQA: Structured Reasoning Traces for Implicit-Knowledge Visual Question Answering
Zhihao Wen, Wenkang Wei, Yuan Fang +4
Knowledge-based Visual Question Answering (KVQA) requires models to ground entities in images and reason over factual knowledge. Recent work has introduced its implicit-knowledge v…
Clustering as Reasoning: A -Means Interpretation of Chain-of-Thought Graph Learning
Xuanting Xie, Zhaochen Guo, Bingheng Li +4
Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large language models (LLMs) on text-attributed graphs (TAGs). This work reframes CoT-…
Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights
Xingtong Yu, Shenghua Ye, Ruijuan Liang +4
Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in gr…