Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention

• URL: http://arxiv.org/abs/2504.15075v1
• Date: Mon, 21 Apr 2025 13:03:40 GMT
• Title: Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
• Authors: Van Thuy Hoang, Hyeon-Ju Jeon, O-Joun Lee,
• Abstract summary: In real-world graphs, high-degree nodes dominate message passing, causing a degree bias where low-degree nodes remain under-represented.<n>We propose a novel Degree Fairness Graph Transformer, named DegFairGT, to mitigate degree bias.<n>Our key idea is to exploit non-adjacent nodes with similar roles in the same community to generate informative edges under our augmentation.
• Score: 1.9019250262578853
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph Neural Networks (GNNs) update node representations through message passing, which is primarily based on the homophily principle, assuming that adjacent nodes share similar features. However, in real-world graphs with long-tailed degree distributions, high-degree nodes dominate message passing, causing a degree bias where low-degree nodes remain under-represented due to inadequate messages. The main challenge in addressing degree bias is how to discover non-adjacent nodes to provide additional messages to low-degree nodes while reducing excessive messages for high-degree nodes. Nevertheless, exploiting non-adjacent nodes to provide valuable messages is challenging, as it could generate noisy information and disrupt the original graph structures. To solve it, we propose a novel Degree Fairness Graph Transformer, named DegFairGT, to mitigate degree bias by discovering structural similarities between non-adjacent nodes through learnable structural augmentation and structural self-attention. Our key idea is to exploit non-adjacent nodes with similar roles in the same community to generate informative edges under our augmentation, which could provide informative messages between nodes with similar roles while ensuring that the homophily principle is maintained within the community. To enable DegFairGT to learn such structural similarities, we then propose a structural self-attention to capture the similarities between node pairs. To preserve global graph structures and prevent graph augmentation from hindering graph structure, we propose a Self-Supervised Learning task to preserve p-step transition probability and regularize graph augmentation. Extensive experiments on six datasets showed that DegFairGT outperformed state-of-the-art baselines in degree fairness analysis, node classification, and node clustering tasks.

Related papers

• Federated Graph Semantic and Structural Learning [54.97668931176513]
  This paper reveals that local client distortion is brought by both node-level semantics and graph-level structure. We postulate that a well-structural graph neural network possesses similarity for neighbors due to the inherent adjacency relationships. We transform the adjacency relationships into the similarity distribution and leverage the global model to distill the relation knowledge into the local model.
  arXiv  Detail & Related papers  (2024-06-27T07:08:28Z)
• Self-Attention Empowered Graph Convolutional Network for Structure Learning and Node Embedding [5.164875580197953]
  In representation learning on graph-structured data, many popular graph neural networks (GNNs) fail to capture long-range dependencies. This paper proposes a novel graph learning framework called the graph convolutional network with self-attention (GCN-SA) The proposed scheme exhibits an exceptional generalization capability in node-level representation learning.
  arXiv  Detail & Related papers  (2024-03-06T05:00:31Z)
• Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structures [2.5252594834159643]
  We propose Community-aware Graph Transformers (CGT) to learn degree-unbiased representations based on learnable augmentations and graph transformers. We first design a learnable graph augmentation to generate more within-community edges connecting low-degree nodes through edge perturbations. Second, we propose an improved self-attention to learn underlying proximity and the roles of nodes within the community.
  arXiv  Detail & Related papers  (2023-12-28T02:30:13Z)
• Marginal Nodes Matter: Towards Structure Fairness in Graphs [77.25149739933596]
  We propose textbfStructural textbfFair textbfGraph textbfNeural textbfNetwork (SFairGNN) to achieve structure fairness. Our experiments show SFairGNN can significantly improve structure fairness while maintaining overall performance in the downstream tasks.
  arXiv  Detail & Related papers  (2023-10-23T03:20:32Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Self-organization Preserved Graph Structure Learning with Principle of Relevant Information [72.83485174169027]
  PRI-GSL is a Graph Structure Learning framework for identifying the self-organization and revealing the hidden structure. PRI-GSL learns a structure that contains the most relevant yet least redundant information quantified by von Neumann entropy and Quantum Jensen-Shannon divergence.
  arXiv  Detail & Related papers  (2022-12-30T16:02:02Z)
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning [68.97378785686723]
  graph neural networks (GNNs) have greatly advanced the performance of node representation learning on graphs. A majority class of GNNs are only designed for homogeneous graphs, leading to inferior adaptivity to the more informative heterogeneous graphs. We propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
  arXiv  Detail & Related papers  (2021-04-04T23:31:39Z)
• Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
  We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification. For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes. Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-17T02:52:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.