mlsanityData to 7 Oct 2026

Towards Data-centric Machine Learning on Directed Graphs: a Survey

arXiv 2412.01849 ↗First posted 28 Nov 2024cs.LG cs.AI cs.DBcited by 2

Not on the map. Why?

Abstract (arXiv)

In recent years, Graph Neural Networks (GNNs) have made significant advances in processing structured data. However, most of them primarily adopted a model-centric approach, which simplifies graphs by converting them into undirected formats and emphasizes model designs. This approach is inherently limited in real-world applications due to the unavoidable information loss in simple undirected graphs and the model optimization challenges that arise when exceeding the upper bounds of this sub-optimal data representational capacity. As a result, there has been a shift toward data-centric methods that prioritize improving graph quality and representation. Specifically, various types of graphs can be derived from naturally structured data, including heterogeneous graphs, hypergraphs, and directed graphs. Among these, directed graphs offer distinct advantages in topological systems by modeling causal relationships, and directed GNNs have been extensively studied in recent years. However, a comprehensive survey of this emerging topic is still lacking. Therefore, we aim to provide a comprehensive review of directed graph learning, with a particular focus on a data-centric perspective. Specifically, we first introduce a novel taxonomy for existing studies. Subsequently, we re-examine these methods from the data-centric perspective, with an emphasis on understanding and improving data representation. It demonstrates that a deep understanding of directed graphs and their quality plays a crucial role in model performance. Additionally, we explore the diverse applications of directed GNNs across 10+ domains, highlighting their broad applicability. Finally, we identify key opportunities and challenges within the field, offering insights that can guide future research and development in directed graph learning.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 74 of its 161 references that are in the map. First posted on arXiv 28 Nov 2024.

Builds on

74 of 161 references.

References · 74

  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. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2019Simplifying Graph Convolutional Networkscited by 1,470
  6. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  7. 2018Link Prediction Based on Graph Neural Networkscited by 829
  8. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  9. 2020A Note on Over-Smoothing for Graph Neural Networkscited by 245
  10. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 231
  11. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  12. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 199
38 more
  1. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  2. 2019DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversationcited by 184
  3. 2020Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networkscited by 152
  4. 2020A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sourcescited by 126
  5. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  6. 2021Global Self-Attention as a Replacement for Graph Convolutioncited by 113
  7. 2021MagNet: A Neural Network for Directed Graphscited by 104
  8. 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
  9. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  10. 2021Directed Acyclic Graph Network for Conversational Emotion Recognitioncited by 97
  11. 2019Graph Convolutional Networks with EigenPoolingcited by 94
  12. 2021Graph Neural Networks in Network Neurosciencecited by 91
  13. 2018SimGNN: A Neural Network Approach to Fast Graph Similarity Computationcited by 89
  14. 2020Line Graph Neural Networks for Link Predictioncited by 89
  15. 2023Edge Directionality Improves Learning on Heterophilic Graphscited by 88
  16. 2019Graph Transformer for Graph-to-Sequence Learningcited by 82
  17. 2022Graph Attention Multi-Layer Perceptroncited by 82
  18. 2019Hierarchical Graph Pooling with Structure Learningcited by 81
  19. 2021Graph-based Semi-supervised Learning: A Comprehensive Reviewcited by 79
  20. 2021Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysiscited by 75
  21. 2020Directed Graph Convolutional Networkcited by 73
  22. 2021Directed Acyclic Graph Neural Networkscited by 70
  23. 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 63
  24. 2024LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddingscited by 60
  25. 2024GOFA: A Generative One-For-All Model for Joint Graph Language Modelingcited by 56
  26. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  27. 2020Graph Neural Networks: Taxonomy, Advances and Trendscited by 48
  28. 2019Spectral-based Graph Convolutional Network for Directed Graphscited by 38
  29. 2021Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detectioncited by 34
  30. 2022COGMEN: COntextualized GNN based Multimodal Emotion recognitioNcited by 29
  31. 2023Provably Powerful Graph Neural Networks for Directed Multigraphscited by 24
  32. 2023Emerging Drug Interaction Prediction Enabled by Flow-based Graph Neural Network with Biomedical Networkcited by 24
  33. 2021Graph Contrastive Learning for Anomaly Detectioncited by 22
  34. 2022Directed Graph Auto-Encoderscited by 22
  35. 2023Data-centric Graph Learning: A Surveycited by 22
  36. 2024A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guidecited by 22
  37. 2022PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphscited by 20
  38. 2022Template based Graph Neural Network with Optimal Transport Distancescited by 20

50 most cited of 74 All 74 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Generating Directed Graphs with Dual Attention and Asymmetric Encodingcited by 3
  2. 2025Draw a Portrait of Your Graph Data: An Instance-Level Profiling Framework for Graph-Structured Datacited by 0