Graph SSL

SSL: Self-Supervised Learning

Ask about this topic

Overview

Graph self-supervised learning studies how to learn useful node, edge, and whole-graph representations from graph structure and features when labeled examples are scarce. Common approaches include contrastive learning across augmented graph views, masked graph autoencoders, and predictive objectives that learn to predict representations across time or graph scales. These representations are evaluated on tasks such as node classification, link prediction, graph classification, dynamic-graph anomaly detection, and molecular property prediction. A key challenge is making pretraining transfer reliably: augmentations can remove meaningful structural signals, and gains on one dataset or task do not guarantee robustness across domains or graph types.

Latest papers

CardsList

63 papers6 papers in the last four weeks, up 100% on the four weeks before. 0.0% of all new papers.

  1. M-JEPA: Predictive Self-Supervised Learning for Molecular Graphs with Scaffold-Shift Evaluation on Tox21

    Oct 18, 2026Karthik Iyer, Nasser SabarGraph SSLMolecular Representation Learning

    Department of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3086, Australia

  2. Complementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph Learning

    Oct 6, 2026Qingying Hao, Zikang Chen, Chuxuan Hu +4Graph Neural NetworksGraph Representation Learning

    ShanghaiTech University Shanghai, China · University of Illinois Urbana-Champaign Urbana, Illinois, USA · The Pennsylvania State University University Park, Pennsylvania, USA

  3. LEON: Location Embeddings from OSM Neighborhoods via Hexagonal Graph Masked Autoencoders

    Oct 4, 2026Szymon Soltysiak, Radoslaw Malek, Jedrzej Kusnierz +3Masked AutoencodersGeospatial Representation Learning

    Department of Artificial Intelligence, Wroclaw University of Science and Technology, Wroclaw, Poland

  4. Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs

    Oct 2, 2026Md Abrar Jahin, Taufikur Rahman Fuad, Md Rizwan ParvezDynamic Graph LearningGraph SSL

    University of Southern California · Islamic University of Technology · Qatar Computing Research Institute (QCRI)

  5. Learning the Latent Structure: A Feature-Centric Approach to Graph Data Augmentation

    Oct 1, 2026Yu Song, Zhigang Hua, Yan Xie +5Graph Data AugmentationData Augmentation

    Michigan State University · Meta

  6. Temporal Heterogeneous Graph Pretraining for Relational Deep Learning

    Sep 28, 2026Yixin Peng, Er Jin, Diego Collarana +1Temporal GNNsHeterogeneous GNNs

    RWTH Aachen University, Aachen, Germany · Fraunhofer FIT, Sankt Augustin, Germany

  7. Phenomenon-Graph JEPA: Label-Efficient Representation Learning for Contactless Cardiorespiratory Sensing

    Sep 26, 2026Constantino Álvarez Casado, Nhi Nguyen, Mohammad Rakibur Rahman +4Self-Supervised Time Series Representation LearningJoint-Embedding Predictive Architecture

    Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Finland · Candour Ltd, Oulu, Finland

  8. Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction

    Sep 15, 2026Kishalay DasGraph SSLMaterials Property Prediction

  9. Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints

    Sep 14, 2026Gwang-Hyeon Yun, Jong-Hoon Park, Bing Hu +3Graph SSLHierarchical Representation Learning

    Yonsei University · Wonju-si, Republic of Korea · University of Waterloo +1

  10. ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation

    Aug 30, 2026Yitong Han, Wei Gao, Yi Zhao +3User ModelingRepresentation Learning

    School of Computing and Information Systems, Singapore Management University, Singapore · Institute of Advanced Intelligence and Computing, A*STAR, Singapore

  11. Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?

    Aug 26, 2026Fumiaki Kimino, Ryoma SatoGraph Representation LearningText-Attributed Graph Learning

    SOKENDAI · National Institute of Informatics · National Institute of Informatics, SOKENDAI

  12. SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation

    Aug 25, 2026Ben Lagnese, Manas GaurGraph Retrieval-Augmented GenerationGraph-Based Retrieval

    University of Maryland, Baltimore County (UMBC), Baltimore, MD, USA

  13. Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognition

    Aug 23, 2026Ioannis N. Ziogas, Leontios J. Hadjileontiadis, Ahsan H. Khandoker +1Emotion RecognitionGraph Neural Networks

    Dpt. of Electrical and Computer Eng. Aristotle University of Thessaloniki Thessaloniki, Greece

  14. When Graph-JEPA Learns the Wrong Thing: Diagnosing and Repairing Category-Conditional Collapse

    Aug 20, 2026Gollam Rabby, Sören AuerRepresentation CollapseJoint-Embedding Predictive Architecture

    L3S Research Centre, Leibniz University Hannover, Hannover, Germany · TIB Leibniz Information Centre for Science and Technology, Hannover, Germany

  15. NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning

    Aug 5, 2026Tinghe Zhang, Jian Xu, Jiaheng Chen +3Graph Representation LearningGraph SSL

    1Northeastern University

  16. HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning

    Aug 1, 2026Ruichen Xu, Jingxiang Qu, Wenhan Gao +5Graph Representation LearningGraph SSL

    Department of Applied Mathematics and Statistics Stony Brook University Stony Brook, NY, USA · Department of Computer Science Stony Brook University Stony Brook, NY, USA · TikTok Bellevue, WA, USA +2

  17. CondPSE: A Polynomial-Filtered Structural Encoder with Conditional Modulation for Graphs

    Jul 28, 2026Woohyun Lee, Hogun ParkGraph Representation LearningGraph SSL

    Sungkyunkwan University Suwon, Republic of Korea

  18. Unsupervised Graph Representation Learning with Complementary View Alignment

    Jul 27, 2026Zengyi Wo, Shiyu Zhang, Qiyao Peng +2Graph Neural NetworksGraph Representation Learning

    Nanjing University, Nanjing, China · Tianjin University, Tianjin, China

  19. MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning

    Jul 27, 2026Tinghui Jin, Kedu Jin, Ying Li +8Graph SSLGraph Foundation Models

    School of Science, School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China · 2Sir Run Run Hospital, Nanjing Medical University, Nanjing, China · 3Jiangsu Key Laboratory of Carcinogenesis and Intervention, China Pharmaceutical University, Nanjing, China

  20. Masked Topology Modeling for Self-Supervised Learning on Parametric CAD

    Jul 22, 2026Heinrich Jiang, Jennifer JangGraph SSLParametric CAD Modeling

    StoryGold AI

  21. Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs

    Jul 20, 2026Huizhe Zhang, Yuchang Zhu, Huazhen Zhong +2Temporal GNNsGraph SSL

    Sun Yat-sen University Guangzhou, China · Sun Yat-sen University Zhuhai, China

  22. Node4All: Learning Node Representation Beyond Datasets

    Jul 19, 2026Dooho Lee, Jaemin YooGraph Representation LearningGraph SSL

    KAIST · Daejeon, Republic of Korea · Seoul National University +1

  23. ChemHyperMag: Physics-informed magnetic hypergraph learning improves molecular ADMET prediction

    Jul 19, 2026Hexiao Ding, Hongzhao Chen, Jing Lan +12Graph SSLPhysics-Informed ML

    Department of Health Technology and Informatics, Hong Kong Polytechnic University, Hong Kong SAR, China · University of Liverpool, Liverpool, United Kingdom · Shanghai Jiao Tong University, Shanghai, China +1

  24. LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration

    Jul 15, 2026Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati +2Spatial TranscriptomicsGraph SSL

    University of Houston · MD Anderson Cancer Center

  25. Canopy: A Heterograph Foundation Model for Metabolic Engineering

    Jul 7, 2026Jake Bowden, Laurence Legon, Satnam SuraeHeterogeneous GNNsGraph SSL

    Twig Bio, London, United Kingdom

  26. MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning

    Jul 3, 2026Yaniv Shulman, Shaghayegh Akbarpour, Jack B. MuirMasked AutoencodersGraph Representation Learning

    Fleet Space Technologies, Adelaide, Australia · Research School of Earth Sciences, Australian National University, Acton, Australia

  27. SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

    Jul 1, 2026Yuting Zhang, Yanbei Liu, Zhitao Xiao +3Graph Representation LearningGraph SSL

    School of Electronics and Information Engineering, Tiangong University, Tianjin, China · School of Life Sciences, Tiangong University, Tianjin, China · School of Electrical and Infomation Engineering, Tianjin University, Tianjin, China +1

  28. AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation

    Jun 30, 2026Bao Long Nguyen Huu, Atsushi HashimotoGraph Representation LearningGraph SSL

    OMRON Corporation · OMRON SINIC X Corporation

  29. GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks

    Jun 29, 2026Haoxin Sun, Yiqing Lin, Yajun Huang +3Language Model PretrainingGraph SSL

    Fudan University Shanghai, China · ByteDance Shanghai, China

  30. Progressive Self-Supervised Learning with Individualized Community Assignment for Brain Network Analysis

    Jun 29, 2026Hairui Chen, Yanwu Yang, Jianfeng Cao +3Self-Supervised LearningGraph SSL

    Harbin Institute of Technology at Shenzhen, Shenzhen, China · Peng Cheng Laboratory, Shenzhen, China · University of Tübingen, Tübingen, Germany +1