Tackling Over-Smoothing for General Graph Convolutional Networks

• URL: http://arxiv.org/abs/2008.09864v5
• Date: Sat, 9 Jul 2022 01:41:01 GMT
• Title: Tackling Over-Smoothing for General Graph Convolutional Networks
• Authors: Wenbing Huang, Yu Rong, Tingyang Xu, Fuchun Sun, Junzhou Huang
• Abstract summary: We study how general GCNs act with the increase in depth, including generic GCN, GCN with bias, ResGCN, and APPNP. We propose DropEdge to alleviate over-smoothing by randomly removing a certain number of edges at each training epoch.
• Score: 88.71154017107257
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Increasing the depth of GCN, which is expected to permit more expressivity, is shown to incur performance detriment especially on node classification. The main cause of this lies in over-smoothing. The over-smoothing issue drives the output of GCN towards a space that contains limited distinguished information among nodes, leading to poor expressivity. Several works on refining the architecture of deep GCN have been proposed, but it is still unknown in theory whether or not these refinements are able to relieve over-smoothing. In this paper, we first theoretically analyze how general GCNs act with the increase in depth, including generic GCN, GCN with bias, ResGCN, and APPNP. We find that all these models are characterized by a universal process: all nodes converging to a cuboid. Upon this theorem, we propose DropEdge to alleviate over-smoothing by randomly removing a certain number of edges at each training epoch. Theoretically, DropEdge either reduces the convergence speed of over-smoothing or relieves the information loss caused by dimension collapse. Experimental evaluations on simulated dataset have visualized the difference in over-smoothing between different GCNs. Moreover, extensive experiments on several real benchmarks support that DropEdge consistently improves the performance on a variety of both shallow and deep GCNs.

Related papers

• Graph Neural Networks Do Not Always Oversmooth [46.57665708260211]
  We study oversmoothing in graph convolutional networks (GCNs) by using their Gaussian process (GP) equivalence in the limit of infinitely many hidden features. We identify a new, non-oversmoothing phase: if the initial weights of the network have sufficiently large variance, GCNs do not oversmooth, and node features remain informative even at large depth.
  arXiv  Detail & Related papers  (2024-06-04T12:47:13Z)
• SkipNode: On Alleviating Performance Degradation for Deep Graph Convolutional Networks [84.30721808557871]
  We conduct theoretical and experimental analysis to explore the fundamental causes of performance degradation in deep GCNs. We propose a simple yet effective plug-and-play module, Skipnode, to overcome the performance degradation of deep GCNs.
  arXiv  Detail & Related papers  (2021-12-22T02:18:31Z)
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective [10.178145000390671]
  Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. We present a quantitative study on this observation and develop novel insights towards the deeper GCN.
  arXiv  Detail & Related papers  (2020-09-24T03:36:43Z)
• Simple and Deep Graph Convolutional Networks [63.76221532439285]
  Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Despite their success, most of the current GCN models are shallow, due to the em over-smoothing problem. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques.
  arXiv  Detail & Related papers  (2020-07-04T16:18:06Z)
• Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks [62.8504260693664]
  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.
  arXiv  Detail & Related papers  (2020-06-28T16:26:47Z)
• 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)

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.