Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks

• URL: http://arxiv.org/abs/2006.15643v2
• Date: Thu, 13 Aug 2020 16:49:34 GMT
• Title: Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks
• Authors: Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra and Suhang Wang
• Abstract summary: Graph Convolutional Networks (GCNs) show promising results for semisupervised learning tasks on graphs. In this paper, we analyze GCNs in regard to the node degree distribution. We develop a novel Self-Supervised DegreeSpecific GCN (SL-DSGC) that mitigates the degree biases of GCNs.
• Score: 62.8504260693664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph Convolutional Networks (GCNs) show promising results for semi-supervised learning tasks on graphs, thus become favorable comparing with other approaches. Despite the remarkable success of GCNs, it is difficult to train GCNs with insufficient supervision. When labeled data are limited, the performance of GCNs becomes unsatisfying for low-degree nodes. While some prior work analyze successes and failures of GCNs on the entire model level, profiling GCNs on individual node level is still underexplored. In this paper, we analyze GCNs in regard to the node degree distribution. From empirical observation to theoretical proof, we confirm that GCNs are biased towards nodes with larger degrees with higher accuracy on them, even if high-degree nodes are underrepresented in most graphs. We further develop a novel Self-Supervised-Learning Degree-Specific GCN (SL-DSGC) that mitigate the degree-related biases of GCNs from model and data aspects. Firstly, we propose a degree-specific GCN layer that captures both discrepancies and similarities of nodes with different degrees, which reduces the inner model-aspect biases of GCNs caused by sharing the same parameters with all nodes. Secondly, we design a self-supervised-learning algorithm that creates pseudo labels with uncertainty scores on unlabeled nodes with a Bayesian neural network. Pseudo labels increase the chance of connecting to labeled neighbors for low-degree nodes, thus reducing the biases of GCNs from the data perspective. Uncertainty scores are further exploited to weight pseudo labels dynamically in the stochastic gradient descent for SL-DSGC. Experiments on three benchmark datasets show SL-DSGC not only outperforms state-of-the-art self-training/self-supervised-learning GCN methods, but also improves GCN accuracy dramatically for low-degree nodes.

Related papers

• What Do Graph Convolutional Neural Networks Learn? [0.0]
  Graph Convolutional Neural Networks (GCN) are a common variant of Graph neural networks (GNNs) Recent literature has highlighted that GCNs can achieve strong performance on heterophilous graphs under certain "special conditions" Our investigation on underlying graph structures of a dataset finds that a GCN's SSNC performance is significantly influenced by the consistency and uniqueness in neighborhood structure of nodes within a class.
  arXiv  Detail & Related papers  (2022-07-05T06:44:37Z)
• RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Network [102.27090022283208]
  Graph Convolutional Network (GCN) plays pivotal roles in many real-world applications. GCN often exhibits performance disparity with respect to node degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle.
  arXiv  Detail & Related papers  (2022-02-28T05:07:57Z)
• Multi-scale Graph Convolutional Networks with Self-Attention [2.66512000865131]
  Graph convolutional networks (GCNs) have achieved remarkable learning ability for dealing with various graph structural data. Over-smoothing phenomenon as a crucial issue of GCNs remains to be solved and investigated. We propose two novel multi-scale GCN frameworks by incorporating self-attention mechanism and multi-scale information into the design of GCNs.
  arXiv  Detail & Related papers  (2021-12-04T04:41:24Z)
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation [60.34028546202372]
  Some work shows that coupling is inferior to decoupling, which supports deep graph propagation better. Despite effectiveness, the working mechanisms of the decoupled GCN are not well understood. We propose a new label propagation method named propagation then training Adaptively (PTA), which overcomes the flaws of the decoupled GCN.
  arXiv  Detail & Related papers  (2020-10-23T13:57:39Z)
• DeeperGCN: All You Need to Train Deeper GCNs [66.64739331859226]
  Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Unlike Convolutional Neural Networks (CNNs), which are able to take advantage of stacking very deep layers, GCNs suffer from vanishing gradient, over-smoothing and over-fitting issues when going deeper. This paper proposes DeeperGCN that is capable of successfully and reliably training very deep GCNs.
  arXiv  Detail & Related papers  (2020-06-13T23:00:22Z)
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks [105.14867349802898]
  Graph Convolutional Network (GCN) stacks several layers and in each layer performs a PROPagation operation (PROP) and a TRANsformation operation (TRAN) for learning node representations over graph-structured data. GCNs tend to suffer performance drop when the model gets deep. We study performance degradation of GCNs by experimentally examining how stacking only TRANs or PROPs works.
  arXiv  Detail & Related papers  (2020-06-12T12:12:12Z)
• Unifying Graph Convolutional Neural Networks and Label Propagation [73.82013612939507]
  We study the relationship between LPA and GCN in terms of two aspects: feature/label smoothing and feature/label influence. Based on our theoretical analysis, we propose an end-to-end model that unifies GCN and LPA for node classification. Our model can also be seen as learning attention weights based on node labels, which is more task-oriented than existing feature-based attention models.
  arXiv  Detail & Related papers  (2020-02-17T03:23:13Z)

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.