Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Union Subgraph Neural Networks

About

Graph Neural Networks (GNNs) are widely used for graph representation learning in many application domains. The expressiveness of vanilla GNNs is upper-bounded by 1-dimensional Weisfeiler-Leman (1-WL) test as they operate on rooted subtrees through iterative message passing. In this paper, we empower GNNs by injecting neighbor-connectivity information extracted from a new type of substructure. We first investigate different kinds of connectivities existing in a local neighborhood and identify a substructure called union subgraph, which is able to capture the complete picture of the 1-hop neighborhood of an edge. We then design a shortest-path-based substructure descriptor that possesses three nice properties and can effectively encode the high-order connectivities in union subgraphs. By infusing the encoded neighbor connectivities, we propose a novel model, namely Union Subgraph Neural Network (UnionSNN), which is proven to be strictly more powerful than 1-WL in distinguishing non-isomorphic graphs. Additionally, the local encoding from union subgraphs can also be injected into arbitrary message-passing neural networks (MPNNs) and Transformer-based models as a plugin. Extensive experiments on 18 benchmarks of both graph-level and node-level tasks demonstrate that UnionSNN outperforms state-of-the-art baseline models, with competitive computational efficiency. The injection of our local encoding to existing models is able to boost the performance by up to 11.09%. Our code is available at https://github.com/AngusMonroe/UnionSNN.

Jiaxing Xu, Aihu Zhang, Qingtian Bian, Vijay Prakash Dwivedi, Yiping Ke• 2023

Related benchmarks

TaskDatasetResultRank
Graph ClassificationPROTEINS
Accuracy78.9
1252
Graph ClassificationMUTAG
Accuracy93.6
1103
Graph ClassificationPTC-MR
Accuracy74.8
244
Graph ClassificationBZR
Accuracy92.4
165
Graph ClassificationCOX2
Accuracy87.6
161
Graph ClassificationD&D
Accuracy82.3
146
Graph ClassificationDHFR
Accuracy84.2
145
Graph ClassificationIMDB MULTI
Accuracy55
139
Graph Classificationimdb-binary
Accuracy79.1
127
Showing 9 of 9 rows

Other info

Follow for update