Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
Mingyuan Fan, Weiguang Han, Daixin Wang +3
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domain…
cs.LG2025
IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification
Zhixun Li, Dingshuo Chen, Tong Zhao +5
Graph Neural Networks (GNNs) have achieved great success in dealing with non-Euclidean graph-structured data and have been widely deployed in many real-world applications. However,…
cs.LG2024
Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancement
Yakun Wang, Daixin Wang, Hongrui Liu +4
Link prediction, as a fundamental task for graph neural networks (GNNs), has boasted significant progress in varied domains. Its success is typically influenced by the expressive p…