most citedThe Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field

3 citations · 7 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG20242 cited

The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs

Kun Wang, Guibin Zhang, Xinnan Zhang +6

Graph Neural Networks (GNNs) have become pivotal tools for a range of graph-based learning tasks. Notably, most current GNN architectures operate under the assumption of homophily,…

cs.LG2024

Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts

Kun Wang, Hao Wu, Guibin Zhang +5

In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames.…

cs.LG20241 cited

EXGC: Bridging Efficiency and Explainability in Graph Condensation

Junfeng Fang, Xinglin Li, Yongduo Sui +5

Graph representation learning on vast datasets, like web data, has made significant strides. However, the associated computational and storage overheads raise concerns. In sight of…

cs.LG20241 cited

Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness

Guibin Zhang, Yanwei Yue, Kun Wang +7

Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational challenges when applied to large-scale graphs. A promising solution is to remove non-essen…

cs.LG20233 cited

The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field

Kun Wang, Guohao Li, Shilong Wang +6

Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoot…