9 papers
UniGAP: A Universal and Adaptive Graph Upsampling Approach to Mitigate Over-Smoothing in Node Classification Tasks
Xiaotang Wang, Yun Zhu, Haizhou Shi +2
In the graph domain, deep graph networks based on Message Passing Neural Networks (MPNNs) or Graph Transformers often cause over-smoothing of node features, limiting their expressi…
GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs
Yun Zhu, Haizhou Shi, Xiaotang Wang +5
Recently, research on Text-Attributed Graphs (TAGs) has gained significant attention due to the prevalence of free-text node features in real-world applications and the advancement…
Transferable and Forecastable User Targeting Foundation Model
Bin Dou, Baokun Wang, Yun Zhu +11
User targeting, the process of selecting targeted users from a pool of candidates for non-expert marketers, has garnered substantial attention with the advancements in digital mark…
Graph Triple Attention Network: A Decoupled Perspective
Xiaotang Wang, Yun Zhu, Haizhou Shi +2
Graph Transformers (GTs) have recently achieved significant success in the graph domain by effectively capturing both long-range dependencies and graph inductive biases. However, t…
Meta-Reflection: A Feedback-Free Reflection Learning Framework
Yaoke Wang, Yun Zhu, Xintong Bao +7
Despite the remarkable capabilities of large language models (LLMs) in natural language understanding and reasoning, they often display undesirable behaviors, such as generating ha…
Bridging Local Details and Global Context in Text-Attributed Graphs
Yaoke Wang, Yun Zhu, Wenqiao Zhang +3
Representation learning on text-attributed graphs (TAGs) is vital for real-world applications, as they combine semantic textual and contextual structural information. Research in t…