Simplified PCNet with Robustness
Not on the map. Why?
Abstract (arXiv)
Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs. However, they cannot generalize well to real-world graphs with different levels of homophily. In response, the Possion-Charlier Network (PCNet) citeli2024pc, the previous work, allows graph representation to be learned from heterophily to homophily. Although PCNet alleviates the heterophily issue, there remain some challenges in further improving the efficacy and efficiency. In this paper, we simplify PCNet and enhance its robustness. We first extend the filter order to continuous values and reduce its parameters. Two variants with adaptive neighborhood sizes are implemented. Theoretical analysis shows our model's robustness to graph structure perturbations or adversarial attacks. We validate our approach through semi-supervised learning tasks on various datasets representing both homophilic and heterophilic graphs.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 46 of its 61 references that are in the map. First posted on arXiv 6 Mar 2024.
Builds on
46 of 61 references.
References · 46
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
- 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
- 2020Simple and Deep Graph Convolutional Networkscited by 857
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
- 2019Heterogeneous Graph Attention Networkcited by 732
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
- 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
- 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
34 more
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2021GRAND: Graph Neural Diffusioncited by 258
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
- 2021BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximationcited by 195
- 2019Graph Neural Networks with convolutional ARMA filterscited by 185
- 2021Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networkscited by 182
- 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
- 2021Training Graph Neural Networks with 1000 Layerscited by 169
- 2022How Powerful are Spectral Graph Neural Networkscited by 169
- 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
- 2021PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equationscited by 106
- 2021Dirichlet Energy Constrained Learning for Deep Graph Neural Networkscited by 97
- 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
- 2022Convolutional Neural Networks on Graphs with Chebyshev Approximation, Revisitedcited by 87
- 2021Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?cited by 82
- 2021Graph Neural Networks Inspired by Classical Iterative Algorithmscited by 60
- 2018N-GCN: Multi-scale Graph Convolution for Semi-supervised Node Classificationcited by 54
- 2021Node Dependent Local Smoothing for Scalable Graph Learningcited by 45
- 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
- 2023Graph Neural Networks with Learnable and Optimal Polynomial Basescited by 36
- 2023Beyond Homophily: Reconstructing Structure for Graph-agnostic Clusteringcited by 29
- 2021Interpretable Stability Bounds for Spectral Graph Filterscited by 28
- 2023PC-Conv: Unifying Homophily and Heterophily with Two-fold Filteringcited by 28
- 2019On the Transferability of Spectral Graph Filterscited by 27
- 2022EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networkscited by 26
- 2021Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphscited by 18
- 2022Structure-Preserving Graph Representation Learningcited by 17
- 2021Self-supervised Consensus Representation Learning for Attributed Graphcited by 15
- 2023Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clusteringcited by 12
- 2022From Local to Global: Spectral-Inspired Graph Neural Networkscited by 11
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.