mlsanityData to 14 Oct 2026

Instance Discrimination for Link Prediction

arXiv 2605.20257 ↗First posted 18 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. However, fewer contributions have tackled the link prediction task. In this contribution, we propose to adapt existing methods to this context. We first provide a rigorous evaluation of existing self-supervised models in the field of link prediction, showing that the main performance depends on the augmentation process (like in computer vision). We then propose a new structural augmentation based on the community structure that is relevant for link prediction. Our main contribution introduces two new models, L-GRACE and L-BGRL, based on link representations instead of node representations, which improve the performance of the existing methods, especially on unattributed graphs, and we show that they perform on par with the state of the art, both in supervised and self-supervised contexts.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

31 of 48 references.

References · 31

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  6. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  8. 2016Variational Graph Auto-Encoderscited by 1,382
  9. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  12. 2018Link Prediction Based on Graph Neural Networkscited by 832
19 more
  1. 2020Deep Graph Contrastive Representation Learningcited by 539
  2. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  3. 2021Graph Self-Supervised Learning: A Surveycited by 289
  4. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
  5. 2020Line Graph Neural Networks for Link Predictioncited by 89
  6. 2021Graph Barlow Twins: A self-supervised representation learning framework for graphscited by 85
  7. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  8. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  9. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 69
  10. 2023Neural Common Neighbor with Completion for Link Predictioncited by 64
  11. 2019Stacking Models for Nearly Optimal Link Prediction in Complex Networkscited by 35
  12. 2021Graph Communal Contrastive Learningcited by 34
  13. 2013Efficient Monte Carlo and greedy heuristic for the inference of stochastic block modelscited by 29
  14. 2023Revisiting Link Prediction: A Data Perspectivecited by 29
  15. 2023Pure Message Passing Can Estimate Common Neighbor for Link Predictioncited by 18
  16. 2022Line Graph Contrastive Learning for Link Predictioncited by 13
  17. 2022Link Prediction with Non-Contrastive Learningcited by 11
  18. 2023CSGCL: Community-Strength-Enhanced Graph Contrastive Learningcited by 7
  19. 2024Community-Invariant Graph Contrastive Learningcited by 4

Built on by

Not cited yet.