mlsanityData to 7 Oct 2026

A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

arXiv 2210.10993 ↗First posted 20 Oct 2022cs.LG eess.SPcited by 11

Not on the map. Why?

Abstract (arXiv)

Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective information. Although research shows that spectral GCNNs can be enhanced by framelet-based filtering, the massive majority of such research only considers undirected graphs. In this paper, we introduce Framelet-MagNet, a magnetic framelet-based spectral GCNN for directed graphs (digraphs). The model applies the framelet transform to digraph signals to form a more sophisticated representation for filtering. Digraph framelets are constructed with the complex-valued magnetic Laplacian, simultaneously leading to signal processing in both real and complex domains. We empirically validate the predictive power of Framelet-MagNet over a range of state-of-the-art models in node classification, link prediction, and denoising.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

19 of 28 references.

References · 19

  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. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2019Multi-scale Attributed Node Embeddingcited by 543
  9. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  10. 2017Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Rankingcited by 332
  11. 2019Graph Wavelet Neural Networkcited by 131
  12. 2021MagNet: A Neural Network for Directed Graphscited by 104
7 more
  1. 2020Directed Graph Convolutional Networkcited by 73
  2. 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 63
  3. 2021How Framelets Enhance Graph Neural Networkscited by 46
  4. 2019Spectral-based Graph Convolutional Network for Directed Graphscited by 38
  5. 2016Magnetic eigenmaps for community detection in directed networkscited by 22
  6. 2020Decimated Framelet System on Graphs and Fast G-Framelet Transformscited by 17
  7. 2022A Simple Yet Effective SVD-GCN for Directed Graphscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 6; 2025: 2.

11 papers.

  1. 2023How Curvature Enhance the Adaptation Power of Framelet GCNscited by 13
  2. 2023Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyondcited by 13
  3. 2024DUPLEX: Dual GAT for Complex Embedding of Directed Graphscited by 7
  4. 2024Commute Graph Neural Networkscited by 5
  5. 2024Unleash Graph Neural Networks from Heavy Tuningcited by 2
  6. 2024When Graph Neural Networks Meet Dynamic Mode Decompositioncited by 2
  7. 2024Towards Data-centric Machine Learning on Directed Graphs: a Surveycited by 2
  8. 2024Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuningcited by 1
  9. 2022Generalized Laplacian Regularized Framelet Graph Neural Networkscited by 0
  10. 2025Rethinking Link Prediction for Directed Graphscited by 0
  11. 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approachcited by 0