Understanding GNNs and Homophily in Dynamic Node Classification
Not on the map. Why?
Abstract (arXiv)
Homophily, as a measure, has been critical to increasing our understanding of graph neural networks (GNNs). However, to date this measure has only been analyzed in the context of static graphs. In our work, we explore homophily in dynamic settings. Focusing on graph convolutional networks (GCNs), we demonstrate theoretically that in dynamic settings, current GCN discriminative performance is characterized by the probability that a node's future label is the same as its neighbors' current labels. Based on this insight, we propose dynamic homophily, a new measure of homophily that applies in the dynamic setting. This new measure correlates with GNN discriminative performance and sheds light on how to potentially design more powerful GNNs for dynamic graphs. Leveraging a variety of dynamic node classification datasets, we demonstrate that popular GNNs are not robust to low dynamic homophily. Going forward, our work represents an important step towards understanding homophily and GNN performance in dynamic node classification.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 29 Apr 2025.
Builds on
31 of 56 references.
References · 31
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2018How Powerful are Graph Neural Networks?cited by 4,355
- 2017Neural Message Passing for Quantum Chemistrycited by 3,460
- 2019Simplifying Graph Convolutional Networkscited by 1,470
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
- 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
- 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
- 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
19 more
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
- 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
- 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
- 2020Graph Neural Networks with Heterophilycited by 202
- 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
- 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 137
- 2016Motifs in Temporal Networkscited by 101
- 2017Dynamic Graph Convolutional Networkscited by 83
- 2022Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyondcited by 60
- 2018GC-LSTM: Graph Convolution Embedded LSTM for Dynamic Link Predictioncited by 47
- 2013The Anatomy of a Scientific Rumorcited by 22
- 2021DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Datacited by 17
- 2023On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networkscited by 13
- 2023TouchUp-G: Improving Feature Representation through Graph-Centric Finetuningcited by 12
- 2024On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networkscited by 10
- 2013Modeling Information Propagation with Survival Theorycited by 9
- 2024Unveiling the Impact of Local Homophily on GNN Fairness: In-Depth Analysis and New Benchmarkscited by 6
- 2017Complex Contagions: A Decade in Reviewcited by 4
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.