mlsanityData to 7 Oct 2026

Directed Graph Auto-Encoders

arXiv 2202.12449 ↗First posted 25 Feb 2022cs.LG cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

We introduce a new class of auto-encoders for directed graphs, motivated by a direct extension of the Weisfeiler-Leman algorithm to pairs of node labels. The proposed model learns pairs of interpretable latent representations for the nodes of directed graphs, and uses parameterized graph convolutional network (GCN) layers for its encoder and an asymmetric inner product decoder. Parameters in the encoder control the weighting of representations exchanged between neighboring nodes. We demonstrate the ability of the proposed model to learn meaningful latent embeddings and achieve superior performance on the directed link prediction task on several popular network datasets.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 25 Feb 2022.

Builds on

18 of 37 references.

References · 18

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  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. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  10. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  11. 2016Learning Convolutional Neural Networks for Graphscited by 314
  12. 2018Rethinking Knowledge Graph Propagation for Zero-Shot Learningcited by 87
6 more
  1. 2020Directed Graph Convolutional Networkcited by 73
  2. 2021Directed Acyclic Graph Neural Networkscited by 70
  3. 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 63
  4. 2019Spectral-based Graph Convolutional Network for Directed Graphscited by 38
  5. 2019Gravity-Inspired Graph Autoencoders for Directed Link Predictioncited by 28
  6. 2019edGNN: a Simple and Powerful GNN for Directed Labeled Graphscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 11; 2025: 6; 2026: 2.

22 papers.

Sort:

  1. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  2. 2023Breaking the Entanglement of Homophily and Heterophily in Semi-supervised Node Classificationcited by 19
  3. 2024Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedycited by 13
  4. 2024Conformal Load Prediction with Transductive Graph Autoencoderscited by 11
  5. 2024DUPLEX: Dual GAT for Complex Embedding of Directed Graphscited by 7
  6. 2024What Are Good Positional Encodings for Directed Graphs?cited by 7
  7. 2025Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embeddingcited by 7
  8. 2025Enhanced Route Planning with Calibrated Uncertainty Setcited by 5
  9. 2024DiRW: Path-Aware Digraph Learning for Heterophilycited by 3
  10. 2024Learning in Feature Spaces via Coupled Covariances: Asymmetric Kernel SVD and Nystr"om methodcited by 2
  11. 2024Towards Data-centric Machine Learning on Directed Graphs: a Surveycited by 2
  12. 2025Residual Reweighted Conformal Prediction for Graph Neural Networkscited by 2
10 more
  1. 2024A Benchmark on Directed Graph Representation Learning in Hardware Designscited by 1
  2. 2024Scale-aware Message Passing For Graph Node Classificationcited by 1
  3. 2022Rethinking the positive role of cluster structure in complex networks for link prediction taskscited by 0
  4. 2024GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstructioncited by 0
  5. 2024Multi-Class and Multi-Task Strategies for Neural Directed Link Predictioncited by 0
  6. 2025Rethinking Link Prediction for Directed Graphscited by 0
  7. 2025Toward Data-centric Directed Graph Learning: An Entropy-driven Approachcited by 0
  8. 2025Directed Link Prediction using GNN with Local and Global Feature Fusioncited by 0
  9. 2026MGKAN: Predicting Asymmetric Drug-Drug Interactions via a Multimodal Graph Kolmogorov-Arnold Networkcited by 0
  10. 2026Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphscited by 0