Papers › Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition...
Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing
Jie Chen, Weiqi Liu, Zhizhong Huang, Junbin Gao, Junping Zhang, Jian Pu
The performance of GNNs degrades as they become deeper due to the over-smoothing. Among all the attempts to prevent over-smoothing, residual connection is one of the promising methods due to its simplicity. However, recent studies have shown that GNNs with residual connections only slightly slow down the degeneration. The reason why residual connections fail in GNNs is still unknown. In this paper, we investigate the forward and backward behavior of GNNs with residual connections from a novel path decomposition perspective. We find that the recursive aggregation of the median length paths from the binomial distribution of residual connection paths dominates output representation, resulting in over-smoothing as GNNs go deeper. Entangled propagation and weight matrices cause gradient smoothing and prevent GNNs with residual connections from optimizing to the identity mapping. Based on these findings, we present a Universal Deep GNNs (UDGNN) framework with cold-start adaptive residual connections (DRIVE) and feedforward modules. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art results over non-smooth heterophily datasets by simply stacking standard GNNs.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Node Classification | Actor | UDGNN (GCN) | Accuracy | 36.13 ± 1.21 | #40 of 62 | Archive leaderboard | report |
| Node Classification | Chameleon | UDGNN (GCN) | Accuracy | 74.53±1.19 | #15 of 61 | Archive leaderboard | report |
| Node Classification | Cornell | UDGNN (GCN) | Accuracy | 84.32±7.29 | #27 of 60 | Archive leaderboard | report |
| Node Classification | Squirrel | UDGNN (GCN) | Accuracy | 68.13±2.59 | #10 of 59 | Archive leaderboard | report |
| Node Classification | Texas | UDGNN (GCN) | Accuracy | 84.60±5.32 | #34 of 62 | Archive leaderboard | report |
| Node Classification | Wisconsin | UDGNN (GCN) | Accuracy | 87.64±3.74 | #27 of 63 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections