collaborators

9 papers

cs.LG2026

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…

cs.LG2026

Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC

Haolu Liu, Xiyue Wang, Xuanting Xie +2

The paper identifies that identical missing-data rates can hide large differences in the amount of fully observed samples, causing a vulnerability they call incompleteness divergen…

cs.LG2026

Provable Filter for Real-world Graph Clustering

Xuanting Xie, Erlin Pan, Zhao Kang +2

Graph clustering, an important unsupervised problem, has been shown to be more resistant to advances in Graph Neural Networks (GNNs). In addition, almost all clustering methods foc…

cs.AI2026

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-…

cs.LG2025

GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models

Zhibin Wang, Zhixing Zhang, Shuqi Wang +2

Graph Neural Networks (GNNs) have demonstrated impressive performance on task-specific benchmarks, yet their ability to generalize across diverse domains and tasks remains limited.…

cs.LG2025

Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering

Xuanting Xie, Bingheng Li, Erlin Pan +3

Attention mechanisms have become a cornerstone in modern neural networks, driving breakthroughs across diverse domains. However, their application to graph structured data, where c…