Graph SSL

SSL: Self-Supervised Learning

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

68 papers2 papers in the last four weeks, down 71% on the four weeks before. 0.0% of all new papers.

  1. BRepA: Graph-Based B-Rep Pretraining for Unified CAD Understanding and Generation

    Nov 17, 2026Dekai Zhu, Zhaiyu Chen, Stefan Gavranovic +13D Representation LearningSelf-Supervised Pre-Training

  2. BiGSyn: A Bi-Level Heterogeneous Graph Contrastive Learning Framework for Interpretable Drug Synergy Prediction

    Nov 16, 2026Senquan Wang, Hui Fang, Haoran Nan +2Graph SSLHeterogeneous GNNs

  3. HyBridge: Bridge-Guided Self-Supervised Hyperbolic Hypergraph Representation Learning

    Nov 12, 2026So-Bin Jung, David Yoon Suk, Sang-Wook KimHypergraph LearningHyperbolic Representation Learning

  4. Efficient and Scalable Multi-View Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning

    Oct 31, 2026Hao Geng, Deqing Wang, Lihao Ge +5Graph SSLMasked Autoencoders

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

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

  6. 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

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

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

  8. Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs

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

  9. Temporal Heterogeneous Graph Pretraining for Relational Deep Learning

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

  10. 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

  11. 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

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

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

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

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

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

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

  15. 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

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

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

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

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

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

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

  19. Unsupervised Graph Representation Learning with Complementary View Alignment

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

  20. 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

  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

  22. Node4All: Learning Node Representation Beyond Datasets

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

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

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

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

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

  25. Canopy: A Heterograph Foundation Model for Metabolic Engineering

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

  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