mlsanityData to 14 Oct 2026

Directed Link Prediction using GNN with Local and Global Feature Fusion

arXiv 2506.20235 ↗First posted 25 Jun 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Link prediction is a classical problem in graph analysis with many practical applications. For directed graphs, recently developed deep learning approaches typically analyze node similarities through contrastive learning and aggregate neighborhood information through graph convolutions. In this work, we propose a novel graph neural network (GNN) framework to fuse feature embedding with community information. We theoretically demonstrate that such hybrid features can improve the performance of directed link prediction. To utilize such features efficiently, we also propose an approach to transform input graphs into directed line graphs so that nodes in the transformed graph can aggregate more information during graph convolutions. Experiments on benchmark datasets show that our approach outperforms the state-of-the-art in most cases when 30%, 40%, 50%, and 60% of the connected links are used as training data, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 111 references that are in the map. First posted on arXiv 25 Jun 2025.

Builds on

43 of 111 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  7. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  9. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  10. 2016Variational Graph Auto-Encoderscited by 1,382
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  12. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
31 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  2. 2020What Makes for Good Views for Contrastive Learning?cited by 846
  3. 2018Link Prediction Based on Graph Neural Networkscited by 832
  4. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  5. 2015LINE: Large-scale Information Network Embeddingcited by 582
  6. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2021Graph Contrastive Learning Automatedcited by 287
  9. 2020What Should Not Be Contrastive in Contrastive Learningcited by 226
  10. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 198
  11. 2020Line Graph Neural Networks for Link Predictioncited by 89
  12. 2022What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoderscited by 82
  13. 2014Curriculum Learning of Multiple Taskscited by 66
  14. 2022COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learningcited by 39
  15. 2019Stacking Models for Nearly Optimal Link Prediction in Complex Networkscited by 35
  16. 2019Gravity-Inspired Graph Autoencoders for Directed Link Predictioncited by 28
  17. 2022Modularity-Aware Graph Autoencoders for Joint Community Detection and Link Predictioncited by 22
  18. 2022Directed Graph Auto-Encoderscited by 22
  19. 2022HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classificationcited by 18
  20. 2017Network structure from rich but noisy datacited by 17
  21. 2021Correcting Exposure Bias for Link Recommendationcited by 17
  22. 2020Adversarial Directed Graph Embeddingcited by 12
  23. 2021An iterative clustering algorithm for the Contextual Stochastic Block Model with optimality guaranteescited by 10
  24. 2017Asymptotically efficient estimators for stochastic blockmodels: the naive MLE, the rank-constrained MLE, and the spectralcited by 9
  25. 2017Curriculum Learning of Visual Attribute Clusters for Multi-Task Classificationcited by 8
  26. 2023Graph Contrastive Learning with Generative Adversarial Networkcited by 8
  27. 2021Disentangling homophily, community structure and triadic closure in networkscited by 6
  28. 2021Collaborative Filtering Approach to Link Predictioncited by 4
  29. 2019A novel metric for community detectioncited by 1
  30. 2021Adaptive Similarity Function with Structural Features of Network Embedding for Missing Link Predictioncited by 1
  31. 2024Core-periphery Detection Based on Masked Bayesian Non-negative Matrix Factorizationcited by 1

Built on by

Not cited yet.