mlsanityData to 7 Oct 2026

Directed Graph Convolutional Network

arXiv 2004.13970 ↗First posted 29 Apr 2020cs.LG stat.MLcited by 73

Not on the map. Why?

Abstract (arXiv)

Graph Convolutional Networks (GCNs) have been widely used due to their outstanding performance in processing graph-structured data. However, the undirected graphs limit their application scope. In this paper, we extend spectral-based graph convolution to directed graphs by using first- and second-order proximity, which can not only retain the connection properties of the directed graph, but also expand the receptive field of the convolution operation. A new GCN model, called DGCN, is then designed to learn representations on the directed graph, leveraging both the first- and second-order proximity information. We empirically show the fact that GCNs working only with DGCNs can encode more useful information from graph and help achieve better performance when generalized to other models. Moreover, extensive experiments on citation networks and co-purchase datasets demonstrate the superiority of our model against the state-of-the-art methods.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 19; 2024: 13; 2025: 12; 2026: 7.

73 papers.

Sort:

  1. 2021MagNet: A Neural Network for Directed Graphscited by 104
  2. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  3. 2021Space-Time-Separable Graph Convolutional Network for Pose Forecastingcited by 84
  4. 2023A Fractional Graph Laplacian Approach to Oversmoothingcited by 45
  5. 2022MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplaciancited by 28
  6. 2023From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyondcited by 26
  7. 2022SigMaNet: One Laplacian to Rule Them Allcited by 23
  8. 2022Directed Graph Auto-Encoderscited by 22
  9. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  10. 2022PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphscited by 18
  11. 2022Geometric Scattering on Measure Spacescited by 17
  12. 2024Spatio-Spectral Graph Neural Networkscited by 17
38 more
  1. 2021DIGRAC: Digraph Clustering Based on Flow Imbalancecited by 15
  2. 2022Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphscited by 15
  3. 2021RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Datacited by 14
  4. 2021WGCN: Graph Convolutional Networks with Weighted Structural Featurescited by 12
  5. 2022A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphscited by 11
  6. 2023Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Predictioncited by 10
  7. 2022Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videoscited by 9
  8. 2021D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learningcited by 8
  9. 2023Best Practices for 2-Body Pose Forecastingcited by 8
  10. 2023Graph Neural Networks based Log Anomaly Detection and Explanationcited by 8
  11. 2022A Simple Yet Effective SVD-GCN for Directed Graphscited by 7
  12. 2023Learning Dynamic Graph Embeddings with Neural Controlled Differential Equationscited by 7
  13. 2024What Are Good Positional Encodings for Directed Graphs?cited by 7
  14. 2022Recommending Related Products Using Graph Neural Networks in Directed Graphscited by 6
  15. 2024Commute Graph Neural Networkscited by 5
  16. 2024Higher-Order Topological Directionality and Directed Simplicial Neural Networkscited by 5
  17. 2023Signed Directed Graph Contrastive Learning with Laplacian Augmentationcited by 4
  18. 2023Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trickcited by 4
  19. 2023Local Structure-aware Graph Contrastive Representation Learningcited by 4
  20. 2023Graph Learning in 4D: a Quaternion-valued Laplacian to Enhance Spectral GCNscited by 4
  21. 2021Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systemscited by 3
  22. 2024Improving Graph Neural Networks by Learning Continuous Edge Directionscited by 3
  23. 2022A Graph Convolution for Signed Directed Graphscited by 2
  24. 2024Retinal Vessel Segmentation with Deep Graph and Capsule Reasoningcited by 2
  25. 2024Towards Data-centric Machine Learning on Directed Graphs: a Surveycited by 2
  26. 2025Sheaves Reloaded: A Directional Awakeningcited by 2
  27. 2021Asymmetric Graph Representation Learningcited by 1
  28. 2022Interactive Visual Pattern Search on Graph Data via Graph Representation Learningcited by 1
  29. 2022Open World Learning Graph Convolution for Latency Estimation in Routing Networkscited by 1
  30. 2023A Network Science perspective of Graph Convolutional Networks: A surveycited by 1
  31. 2023GRANDE: a neural model over directed multigraphs with application to anti-money launderingcited by 1
  32. 2023Can Directed Graph Neural Networks be Adversarially Robust?cited by 1
  33. 2023A Simple and Scalable Graph Neural Network for Large Directed Graphscited by 1
  34. 2023BHGNN-RT: Network embedding for directed heterogeneous graphscited by 1
  35. 2024A Benchmark on Directed Graph Representation Learning in Hardware Designscited by 1
  36. 2024Haar-Laplacian for directed graphscited by 1
  37. 2024Scale-aware Message Passing For Graph Node Classificationcited by 1
  38. 2025Incorporating graph neural network into route choice modelcited by 1

50 most cited of 73 All 73 (JSON)