activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2025

Uncertainty-Aware Graph Structure Learning

Shen Han, Zhiyao Zhou, Jiawei Chen +6

Graph Neural Networks (GNNs) have become a prominent approach for learning from graph-structured data. However, their effectiveness can be significantly compromised when the graph…

cs.LG2024

Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding

Zhe Wang, Sheng Zhou, Jiawei Chen +5

Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has garnered significant research interest, largely due to its powerful capabilities in modeling compl…

cs.LG2024

Online Adversarial Knowledge Distillation for Graph Neural Networks

Can Wang, Zhe Wang, Defang Chen +3

Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both…

cs.LG2024

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

Weiqin Yang, Jiawei Chen, Xin Xin +5

Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant lim…

cs.LG2024

Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power

Zhe Wang, Tianjian Zhao, Zhen Zhang +5

Dynamic Graph Neural Networks (DyGNNs) have garnered increasing research attention for learning representations on evolving graphs. Despite their effectiveness, the limited express…

cs.LG2024

A Note on Knowledge Distillation Loss Function for Object Classification

Defang Chen

This research note provides a quick introduction to the knowledge distillation loss function used in object classification. In particular, we discuss its connection to a previously…