When Do We Need Graph Neural Networks for Node Classification?
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by additionally making use of graph structure based on the relational inductive bias (edge bias), rather than treating the nodes as collections of independent and identically distributed (i.i.d.) samples. Though GNNs are believed to outperform basic NNs in real-world tasks, it is found that in some cases, GNNs have little performance gain or even underperform graph-agnostic NNs. To identify these cases, based on graph signal processing and statistical hypothesis testing, we propose two measures which analyze the cases in which the edge bias in features and labels does not provide advantages. Based on the measures, a threshold value can be given to predict the potential performance advantages of graph-aware models over graph-agnostic models.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 28 references that are in the map. First posted on arXiv 30 Oct 2022.
Builds on
16 of 28 references.
References · 16
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2019Simplifying Graph Convolutional Networkscited by 1,470
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
- 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
- 2022Revisiting Heterophily For Graph Neural Networkscited by 169
- 2020Non-Local Graph Neural Networkscited by 91
- 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
- 2021New Benchmarks for Learning on Non-Homophilous Graphscited by 81
4 more
- 2019Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networkscited by 62
- 2014Signal Recovery on Graphs: Variation Minimizationcited by 26
- 2020Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designscited by 25
- 2020Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networkscited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.