mlsanityData to 14 Oct 2026

Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning

arXiv 2510.22322 ↗First posted 25 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing k-nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph based mechanism. The code is publicly available at https://github.com/alijavidani/SSL-GraphNNCLR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 45 references that are in the map. First posted on arXiv 25 Oct 2025.

Builds on

36 of 45 references.

References · 36

  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. 2017Graph Attention Networkscited by 8,923
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2018How Powerful are Graph Neural Networks?cited by 4,393
  10. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  12. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
24 more
  1. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 877
  2. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  3. 2021With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representationscited by 326
  4. 2021Large-Scale Representation Learning on Graphs via Bootstrappingcited by 186
  5. 2021Efficient Self-supervised Vision Transformers for Representation Learningcited by 149
  6. 2020OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learningcited by 65
  7. 2022Patch-level Representation Learning for Self-supervised Vision Transformerscited by 60
  8. 2023Mixed Autoencoder for Self-supervised Visual Representation Learningcited by 38
  9. 2021Self-supervised Graph Neural Networks without explicit negative samplingcited by 25
  10. 2023Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regressioncited by 20
  11. 2024Dual Test-time Training for Out-of-distribution Recommender Systemcited by 16
  12. 2023Self-supervised Representation Learning From Random Data Projectorscited by 15
  13. 2021Self-Supervised Learning of Audio Representations from Permutations with Differentiable Rankingcited by 14
  14. 2022An Embedding-Dynamic Approach to Self-supervised Learningcited by 4
  15. 2023Probabilistic Self-supervised Learning via Scoring Rules Minimizationcited by 4
  16. 2024MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneckcited by 4
  17. 2024Beyond Pairwise Correlations: Higher-Order Redundancies in Self-Supervised Representation Learningcited by 4
  18. 2022Weak Augmentation Guided Relational Self-Supervised Learningcited by 3
  19. 2022Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyondcited by 3
  20. 2023Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learningcited by 3
  21. 2025Seeing the Whole in the Parts in Self-Supervised Representation Learningcited by 2
  22. 2023Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approachcited by 1
  23. 2024Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorizationcited by 1
  24. 2024LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognitioncited by 1

Built on by

Not cited yet.