mlsanityData to 7 Oct 2026

RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning

arXiv 2204.13846 ↗First posted 29 Apr 2022cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Graph contrastive learning has gained significant progress recently. However, existing works have rarely explored non-aligned node-node contrasting. In this paper, we propose a novel graph contrastive learning method named RoSA that focuses on utilizing non-aligned augmented views for node-level representation learning. First, we leverage the earth mover's distance to model the minimum effort to transform the distribution of one view to the other as our contrastive objective, which does not require alignment between views. Then we introduce adversarial training as an auxiliary method to increase sampling diversity and enhance the robustness of our model. Experimental results show that RoSA outperforms a series of graph contrastive learning frameworks on homophilous, non-homophilous and dynamic graphs, which validates the effectiveness of our work. To the best of our awareness, RoSA is the first work focuses on the non-aligned node-node graph contrastive learning problem. Our codes are available at: hrefhttps://github.com/ZhuYun97/RoSAtexttthttps://github.com/ZhuYun97/RoSA

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 27 of its 45 references that are in the map. First posted on arXiv 29 Apr 2022.

Builds on

27 of 45 references.

References · 27

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2017Inductive Representation Learning on Large Graphscited by 6,284
  9. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  10. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  11. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  12. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
15 more
  1. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  2. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  3. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  4. 2018Deep Graph Infomaxcited by 1,101
  5. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  6. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  7. 2019Adversarial Training for Free!cited by 638
  8. 2020Deep Graph Contrastive Representation Learningcited by 535
  9. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  10. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  11. 2020Graph Representation Learning via Graphical Mutual Information Maximizationcited by 217
  12. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  13. 2020Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learningcited by 90
  14. 2020Self-EMD: Self-Supervised Object Detection without ImageNetcited by 70
  15. 2015Homophily and missing links in citation networkscited by 21

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 1.

12 papers.

  1. 2024GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphscited by 58
  2. 2022Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented Viewcited by 54
  3. 2024Efficient Tuning and Inference for Large Language Models on Textual Graphscited by 54
  4. 2023SGL-PT: A Strong Graph Learner with Graph Prompt Tuningcited by 35
  5. 2023GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learningcited by 32
  6. 2025Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokenscited by 27
  7. 2024Towards Unified Multimodal Editing with Enhanced Knowledge Collaborationcited by 18
  8. 2023SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inferencecited by 9
  9. 2023CSGCL: Community-Strength-Enhanced Graph Contrastive Learningcited by 7
  10. 2023MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learningcited by 7
  11. 2024Meta-Reflection: A Feedback-Free Reflection Learning Frameworkcited by 2
  12. 2023Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Frameworkcited by 1