Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces

• URL: http://arxiv.org/abs/2211.00565v2
• Date: Wed, 2 Nov 2022 06:45:03 GMT
• Title: Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces
• Authors: Ashish Tiwari, Sresth Tosniwal, and Shanmuganathan Raman
• Abstract summary: Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. We argue that by learning graph representations across two spaces i.e., topology and feature space GCNs can address heterophily. We experimentally demonstrate the performance of the proposed GCN framework over semi-supervised node classification task.
• Score: 20.775165967590173
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the homophily assumption and have shown limited performance on the heterophilous graphs. While several methods have been developed with new architectures to address heterophily, we argue that by learning graph representations across two spaces i.e., topology and feature space GCNs can address heterophily. In this work, we experimentally demonstrate the performance of the proposed GCN framework over semi-supervised node classification task on both homophilous and heterophilous graph benchmarks by learning and combining representations across the topological and the feature spaces.

Related papers

• When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning [6.2167203720326025]
  Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. We define semantic heterophily and propose an innovative framework called Latent Graphs Guided Unsupervised Representation Learning (LatGRL) to handle this problem.
  arXiv  Detail & Related papers  (2024-09-01T10:25:06Z)
• Refining Latent Homophilic Structures over Heterophilic Graphs for Robust Graph Convolution Networks [23.61142321685077]
  Graph convolution networks (GCNs) are extensively utilized in various graph tasks to mine knowledge from spatial data. Our study marks the pioneering attempt to quantitatively investigate the GCN robustness over omnipresent heterophilic graphs for node classification. We present a novel method that aims to harden GCNs by automatically learning Latent Homophilic Structures over heterophilic graphs.
  arXiv  Detail & Related papers  (2023-12-27T05:35:14Z)
• Semantic Random Walk for Graph Representation Learning in Attributed Graphs [2.318473106845779]
  We propose a novel semantic graph representation (SGR) method to formulate the joint optimization of the two heterogeneous sources into a common high-order proximity based framework. Conventional embedding methods that consider high-order topology proximities can then be easily applied to the newly constructed graph to learn the representations of both node and attribute. The learned attribute embeddings can also effectively support some semantic-oriented inference tasks, helping to reveal the graph's deep semantic.
  arXiv  Detail & Related papers  (2023-05-11T02:35:16Z)
• Geometry Contrastive Learning on Heterogeneous Graphs [50.58523799455101]
  This paper proposes a novel self-supervised learning method, termed as Geometry Contrastive Learning (GCL) GCL views a heterogeneous graph from Euclidean and hyperbolic perspective simultaneously, aiming to make a strong merger of the ability of modeling rich semantics and complex structures. Extensive experiments on four benchmarks data sets show that the proposed approach outperforms the strong baselines.
  arXiv  Detail & Related papers  (2022-06-25T03:54:53Z)
• Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [102.9138736545956]
  Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies. In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
  arXiv  Detail & Related papers  (2022-04-30T12:57:02Z)
• Geometric Graph Representation Learning via Maximizing Rate Reduction [73.6044873825311]
  Learning node representations benefits various downstream tasks in graph analysis such as community detection and node classification. We propose Geometric Graph Representation Learning (G2R) to learn node representations in an unsupervised manner. G2R maps nodes in distinct groups into different subspaces, while each subspace is compact and different subspaces are dispersed.
  arXiv  Detail & Related papers  (2022-02-13T07:46:24Z)
• Heterogeneous Graph Neural Network with Multi-view Representation Learning [16.31723570596291]
  We propose a Heterogeneous Graph Neural Network with Multi-View Representation Learning (MV-HetGNN) for heterogeneous graph embedding. The proposed model consists of node feature transformation, view-specific ego graph encoding and auto multi-view fusion to thoroughly learn complex structural and semantic information for generating comprehensive node representations. Extensive experiments on three real-world heterogeneous graph datasets show that the proposed MV-HetGNN model consistently outperforms all the state-of-the-art GNN baselines in various downstream tasks.
  arXiv  Detail & Related papers  (2021-08-31T07:18:48Z)
• Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification [50.899576891296235]
  Convolutional neural networks have been widely applied to hyperspectral image classification. Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
  arXiv  Detail & Related papers  (2021-06-26T06:24:51Z)
• Is Homophily a Necessity for Graph Neural Networks? [50.959340355849896]
  Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. GNNs are widely believed to work well due to the homophily assumption ("like attracts like"), and fail to generalize to heterophilous graphs where dissimilar nodes connect. Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion. In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than
  arXiv  Detail & Related papers  (2021-06-11T02:44:00Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)

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.