mlsanityData to 14 Oct 2026

Characterizing the Influence of Topology on Graph Learning Tasks

arXiv 2404.07493 ↗First posted 11 Apr 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the fundamental problem of understanding and analyzing how graph topology influences the performance of learning models on downstream tasks has not yet been well understood. In this paper, we propose a metric, TopoInf, which characterizes the influence of graph topology by measuring the level of compatibility between the topological information of graph data and downstream task objectives. We provide analysis based on the decoupled GNNs on the contextual stochastic block model to demonstrate the effectiveness of the metric. Through extensive experiments, we demonstrate that TopoInf is an effective metric for measuring topological influence on corresponding tasks and can be further leveraged to enhance graph learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 32 references that are in the map. First posted on arXiv 11 Apr 2024.

Builds on

27 of 32 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  9. 2020Simple and Deep Graph Convolutional Networkscited by 860
  10. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  11. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 680
  12. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 595
15 more
  1. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  2. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  3. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  4. 2020Graph Neural Networks with Heterophilycited by 202
  5. 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
  6. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  7. 2018Contextual Stochastic Block Modelscited by 134
  8. 2020Learning to Drop: Robust Graph Neural Network via Topological Denoisingcited by 127
  9. 2017Topology Adaptive Graph Convolutional Networkscited by 113
  10. 2020On the Equivalence of Decoupled Graph Convolution Network and Label Propagationcited by 49
  11. 2021Node Dependent Local Smoothing for Scalable Graph Learningcited by 45
  12. 2023Large Language Models as Topological Structure Enhancers for Text-Attributed Graphscited by 27
  13. 2022Simplified Graph Convolution with Heterophilycited by 17
  14. 2021Label Contrastive Coding based Graph Neural Network for Graph Classificationcited by 10
  15. 2021Measuring and Sampling: A Metric-guided Subgraph Learning Framework for Graph Neural Networkcited by 1

Built on by

Not cited yet.