87 citations · 395 across the 49 of their papers we have counts for
9 papers · 1 filter
Test Time Training for Supervised Causal Learning
Zizhen Deng, Jiaru Zhang, Rui Ding +5
Supervised Causal Learning (SCL) has shown promise in causal discovery by framing it as a supervised learning problem. However, it suffers from significant out-of-distribution gene…
Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning
Hanbing Liu, Lang Cao, Yuanyi Ren +5
Large language models (LLMs) show strong reasoning abilities but often produce unnecessarily long explanations that reduce efficiency. Although reinforcement learning (RL) has been…
Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning
Jiaru Zhang, Rui Ding, Qiang Fu +6
Causal discovery is a structured prediction task that aims to predict causal relations among variables based on their data samples. Supervised Causal Learning (SCL) is an emerging…
Scalable Differentiable Causal Discovery in the Presence of Latent Confounders with Skeleton Posterior (Extended Version)
Pingchuan Ma, Rui Ding, Qiang Fu +4
Differentiable causal discovery has made significant advancements in the learning of directed acyclic graphs. However, its application to real-world datasets remains restricted due…
Robust Mid-Pass Filtering Graph Convolutional Networks
Jincheng Huang, Lun Du, Xu Chen +3
Graph convolutional networks (GCNs) are currently the most promising paradigm for dealing with graph-structure data, while recent studies have also shown that GCNs are vulnerable t…
Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach
Wendong Bi, Lun Du, Qiang Fu +3
Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data. A lot of GNNs perform well on homophily graphs while having unsatisfactory performance on…
Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima
Hengyu Liu, Qiang Fu, Lun Du +4
Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training. Learning rate schedules are widely used in real practice to…
MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
Wendong Bi, Lun Du, Qiang Fu +3
Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors. Recently, some studies have discussed the…
Neuron with Steady Response Leads to Better Generalization
Qiang Fu, Lun Du, Haitao Mao +4
Regularization can mitigate the generalization gap between training and inference by introducing inductive bias. Existing works have already proposed various inductive biases from…