7 papers
ReMath: Benchmarking Theorem Retrieval in Research-Level Mathematics
Zicheng Lyu, Wenjie Yang, Shengzhong Zhang +1
Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof rea…
Rethinking Multi-Label Node Classification: Do Tuned Classic GNNs Suffice?
Yuxuan Xiao, Shengzhong Zhang
Multi-label node classification (MLNC) has recently been addressed by increasingly complex label-aware designs that explicitly model node-label interactions and inter-label depende…
Geometric Imbalance in Semi-Supervised Node Classification
Liang Yan, Shengzhong Zhang, Bisheng Li +6
Class imbalance in graph data presents a significant challenge for effective node classification, particularly in semi-supervised scenarios. In this work, we formally introduce the…
Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning
Jiaxing Guo, Wenjie Yang, Shengzhong Zhang +4
Outcome-rewarded Large Language Models (LLMs) have demonstrated remarkable success in mathematical problem-solving. However, this success often masks a critical issue: models frequ…
Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
Liang Yan, Gengchen Wei, Chen Yang +2
This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanc…
Your Graph Recommender is Provably a Single-view Graph Contrastive Learning
Wenjie Yang, Shengzhong Zhang, Jiaxing Guo +1
Graph recommender (GR) is a type of graph neural network (GNNs) encoder that is customized for extracting information from the user-item interaction graph. Due to its strong perfor…