Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing

3 Feb 2023  ·  Yunchong Song, Chenghu Zhou, Xinbing Wang, Zhouhan Lin ·

Most graph neural networks follow the message passing mechanism. However, it faces the over-smoothing problem when multiple times of message passing is applied to a graph, causing indistinguishable node representations and prevents the model to effectively learn dependencies between farther-away nodes. On the other hand, features of neighboring nodes with different labels are likely to be falsely mixed, resulting in the heterophily problem. In this work, we propose to order the messages passing into the node representation, with specific blocks of neurons targeted for message passing within specific hops. This is achieved by aligning the hierarchy of the rooted-tree of a central node with the ordered neurons in its node representation. Experimental results on an extensive set of datasets show that our model can simultaneously achieve the state-of-the-art in both homophily and heterophily settings, without any targeted design. Moreover, its performance maintains pretty well while the model becomes really deep, effectively preventing the over-smoothing problem. Finally, visualizing the gating vectors shows that our model learns to behave differently between homophily and heterophily settings, providing an explainable graph neural model.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Actor Ordered GNN Accuracy 37.99 ± 1.00 # 9
Node Classification Chameleon Ordered GNN Accuracy 72.28±2.29 # 22
Node Classification Cornell Ordered GNN Accuracy 87.03±4.73 # 5
Node Classification Squirrel Ordered GNN Accuracy 62.44±1.96 # 21
Node Classification Texas Ordered GNN Accuracy 86.22±4.12 # 22
Node Classification Wisconsin Ordered GNN Accuracy 88.04±3.63 # 19

Methods


No methods listed for this paper. Add relevant methods here