Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures
About
This study utilizes community structures to address node degree biases in message-passing (MP) via learnable graph augmentations and novel graph transformers. Recent augmentation-based methods showed that MP neural networks often perform poorly on low-degree nodes, leading to degree biases due to a lack of messages reaching low-degree nodes. Despite their success, most methods use heuristic or uniform random augmentations, which are non-differentiable and may not always generate valuable edges for learning representations. In this paper, we propose Community-aware Graph Transformers, namely CGT, to learn degree-unbiased representations based on learnable augmentations and graph transformers by extracting within community structures. We first design a learnable graph augmentation to generate more within-community edges connecting low-degree nodes through edge perturbation. Second, we propose an improved self-attention to learn underlying proximity and the roles of nodes within the community. Third, we propose a self-supervised learning task that could learn the representations to preserve the global graph structure and regularize the graph augmentations. Extensive experiments on various benchmark datasets showed CGT outperforms state-of-the-art baselines and significantly improves the node degree biases. The source code is available at https://github.com/NSLab-CUK/Community-aware-Graph-Transformer.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Node Classification | Cora | Accuracy87.1 | 885 | |
| Node Classification | Citeseer | Accuracy76.59 | 804 | |
| Node Classification | Pubmed | Accuracy86.86 | 742 | |
| Node Classification | wikiCS | Accuracy84.61 | 198 | |
| Node Classification | Photo | Mean Accuracy95.73 | 165 | |
| Node Classification | Computers | Mean Accuracy91.45 | 143 | |
| Node Clustering | Computers | Conductance10.13 | 12 | |
| Node Clustering | Citeseer | C Metric5.4 | 12 | |
| Node Clustering | Photo | C Score9.71 | 12 | |
| Node Clustering | wikiCS | C Score21.68 | 12 |