mlsanityData to 7 Oct 2026

Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs

arXiv 2103.14187 ↗First posted 26 Mar 2021cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have been extensively studied for prediction tasks on graphs. As pointed out by recent studies, most GNNs assume local homophily, i.e., strong similarities in local neighborhoods. This assumption however limits the generalizability power of GNNs. To address this limitation, we propose a flexible GNN model, which is capable of handling any graphs without being restricted by their underlying homophily. At its core, this model adopts a node attention mechanism based on multiple learnable spectral filters; therefore, the aggregation scheme is learned adaptively for each graph in the spectral domain. We evaluated the proposed model on node classification tasks over eight benchmark datasets. The proposed model is shown to generalize well to both homophilic and heterophilic graphs. Further, it outperforms all state-of-the-art baselines on heterophilic graphs and performs comparably with them on homophilic graphs.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

32 of 47 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,099
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2018Link Prediction Based on Graph Neural Networkscited by 829
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
20 more
  1. 2019Are Sixteen Heads Really Better than One?cited by 803
  2. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  3. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  4. 2015LINE: Large-scale Information Network Embeddingcited by 582
  5. 2019Multi-scale Attributed Node Embeddingcited by 543
  6. 2019Diffusion Improves Graph Learningcited by 414
  7. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  8. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  9. 2017struc2vec: Learning Node Representations from Structural Identitycited by 214
  10. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  11. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  12. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  13. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  14. 2019Graph Wavelet Neural Networkcited by 131
  15. 2017Learning Structural Node Embeddings Via Diffusion Waveletscited by 97
  16. 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
  17. 2020Non-Local Graph Neural Networkscited by 91
  18. 2018Flow Smoothing and Denoising: Graph Signal Processing in the Edge-Spacecited by 37
  19. 2016Autoregressive Moving Average Graph Filteringcited by 35
  20. 2017Filter Design for Autoregressive Moving Average Graph Filterscited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 7; 2024: 4; 2025: 2.

18 papers.

Sort:

  1. 2021How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implicationscited by 21
  2. 2023Homophily-oriented Heterogeneous Graph Rewiringcited by 18
  3. 2022Augmentation-Free Graph Contrastive Learning with Performance Guaranteecited by 16
  4. 2022Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graphcited by 14
  5. 2023GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networkscited by 12
  6. 2024Robust Graph Structure Learning under Heterophilycited by 11
  7. 2022Restructuring Graph for Higher Homophily via Adaptive Spectral Clusteringcited by 9
  8. 2023Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecastingcited by 8
  9. 2023Shape-aware Graph Spectral Learningcited by 6
  10. 2024Homophily-Related: Adaptive Hybrid Graph Filter for Multi-View Graph Clusteringcited by 6
  11. 2022Improving Your Graph Neural Networks: A High-Frequency Boostercited by 4
  12. 2023Spectral-Aware Augmentation for Enhanced Graph Representation Learningcited by 4
6 more
  1. 2023Framelet Message Passingcited by 3
  2. 2023GPatcher: A Simple and Adaptive MLP Model for Alleviating Graph Heterophilycited by 3
  3. 2024Simplified PCNet with Robustnesscited by 3
  4. 2025HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relationscited by 3
  5. 2025Divergent Paths: Separating Homophilic and Heterophilic Learning for Enhanced Graph-level Representationscited by 1
  6. 2024Graph as a feature: improving node classification with non-neural graph-aware logistic regressioncited by 0