Graph Structure Learning

Ask about this topic

Overview

Graph structure learning studies how to infer or refine edges, weights, and higher-order connections when the network is unknown, noisy, changing, or poorly matched to a task. Methods range from sparse precision-matrix and Laplacian estimation and score-based directed acyclic graph learning to similarity-based construction, attention-driven rewiring, and task-aware bilevel optimization. Learned structures support tasks such as node classification, link prediction, time-series forecasting, recommendation, and biomedical analysis, including settings with scarce labels, multimodal features, or evolving relationships. A central tension is whether a graph should faithfully recover underlying dependencies or maximize downstream performance: task-driven rewiring can help prediction but may overfit, weaken interpretability, or fail to transfer across datasets.

Latest papers

CardsList

139 papers14 papers in the last four weeks, up 8% on the four weeks before. 0.1% of all new papers.

  1. RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation

    Mar 17, 2026Yixuan Huang, Jiawei Chen, Shengfan Zhang +1Graph Contrastive LearningCollaborative Filtering

    National University of Defense Technology, Changsha, China · Ant Group, Chongqing, China · Tsinghua University, Beijing, China

  2. Exploring Subnetwork Interactions in Heterogeneous Brain Network via Prior-Informed Graph Learning

    Mar 13, 2026Siyu Liu, Guangqi Wen, Peng Cao +4Brain Network AnalysisFunctional Connectivity

    Computer Science and Engineering, Northeastern University, Shenyang, China · Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, Shenyang, China · School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, China +5

  3. Learning Bayesian and Markov Networks with an Unreliable Oracle

    Mar 10, 2026Juha Harviainen, Pekka Parviainen, Vidya Sagar SharmaGraph Structure LearningBayesian Network Structure Learning

    University of Helsinki, Finland · University of Bergen, Norway · Indian Institute of Technology Madras, India

  4. Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis

    Mar 6, 2026Zongyu Shi, Laibin Zhang, Maoyin ChenGraph Neural NetworksFault Diagnosis

    Department of Automation, College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102299, China · Department of Safety Engineering, College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102299, China

  5. Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

    Mar 3, 2026Fengzhi Li, Liang Zhang, Yuan Zuo +5LLM Reasoning with GraphsZero-Shot Learning

    JIUTIAN Research, Beijing, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · MIIT Key Laboratory of Data and Decision Intelligence, Beihang University, Beijing, China +1

  6. Learning graph topology from metapopulation epidemic encoder-decoder

    Mar 2, 2026Xin Li, Jonathan Cohen, Shai Pilosof +1Graph Structure LearningSpatial Epidemic Modeling

    Faculty of Computer and Information Science, Ben-Gurion University of the Negev, Be’er Sheva, South District, Israel · Department of Life Sciences, Ben-Gurion University of the Negev, Be’er Sheva, South District, Israel · The Goldman Sonnenfeldt School of Sustainability and Climate Change, Ben-Gurion University of the Negev, Be’er Sheva, South District, Israel

  7. Learning Disease-Sensitive Latent Interaction Graphs From Noisy Cardiac Flow Measurements

    Feb 26, 2026Viraj Patel, Marko Grujic, Philipp Aigner +4Graph Structure LearningPhysics-Informed GNNs

    Department of Computer Science, University of Bath, Bath, UK · Christian Doppler Laboratory for Mechanical Circulatory Support, Department of Cardiac and Thoracic Aortic Surgery, Medical University of Vienna, Vienna, Austria · Department of Mechanical Engineering, University of Bath, Bath, UK

  8. RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection

    Feb 25, 2026Longlong Zhang, Xi Wang, Haotong Du +3Social Bot DetectionGraph Data Augmentation

    School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University · Shenzhen Research Institute, Northwestern Polytechnical University · School of Automation Science and Engineering, Xi’an Jiaotong University +1

  9. Causal Neighbourhood Learning for Invariant Graph Representations

    Feb 20, 2026Simi Job, Xiaohui Tao, Taotao Cai +2Graph Representation LearningCausal Representation Learning

    School of Science, Engineering and Digital Technologies, University of Southern Queensland, Australia. · School of Data Science, Lingnan University, Hong Kong.

  10. AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

    Feb 19, 2026Rong Fu, Chunlei Meng, Shuo Yin +2Graph Neural NetworksGraph Structure Learning

    Independent Researcher

  11. Including Node Textual Metadata in Laplacian-constrained Gaussian Graphical Models

    Feb 17, 2026Jianhua Wang, Killian Cressant, Pedro Braconnot Velloso +1Graph Structure LearningProbabilistic Graphical Models

    Université Paris-Nanterre, LEME, IUT Ville d’Avray, Ville d’Avray, France · Conservatoire National des Arts et Métiers, CNAM, Paris, France

  12. A Fast Binary Splitting Approach for Non-Adaptive Learning of Erdős--Rényi Graphs

    Nov 21, 2025Hoang Ta, Jonathan ScarlettGraph Structure Learning

    Department of Computer Science, School of Computing, National University of Singapore (NUS), Singapore 117417 · Department of Computer Science, Hanoi University of Science and Technology, Vietnam · Department of Computer Science, Department of Mathematics, and Institute of Data Science, NUS, Singapore 117417

  13. Design of Experiment for Discovering Directed Mixed Graph

    Sep 2, 2025Haijie Xu, Chen ZhangGraph Structure LearningCausal Discovery

    Department of Industrial Engineering Tsinghua University

  14. Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning

    Aug 20, 2025Jiafeng Xiong, Rizos SakellariouGraph Structure LearningTemporal GNNs

    Department of Computer Science, University of Manchester, UK

  15. Learning Latent Graph Geometry via Fixed-Point Schrödinger-Type Activation: A Theoretical Study

    Jul 27, 2025Dmitry Pasechnyuk-Vilensky, Martin TakáčGraph Structure LearningGraph Neural Networks

    MBZUAI, UAE

  16. Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming

    Jun 2, 2025Haruki Yokota, Hiroshi Higashi, Yuichi Tanaka +1Graph Structure LearningGraph Representation Learning

  17. LLaTA: Unlocking Graph Structure Learning with Tree-Guided Large Language Models

    Mar 27, 2025Zhihan Zhang, Xunkai Li, Hongchao Qin +2Graph Structure LearningText-Attributed Graph Learning

    Beijing Institute of Technology

  18. GLL: A Differentiable Graph Learning Layer for Neural Networks

    Dec 11, 2024Jason Brown, Bohan Chen, Harris Hardiman-Mostow +2Graph-Based Label PropagationGraph-Based Semi-Supervised Learning

    Department of Mathematics University of California, Los Angeles Los Angeles, CA 90095, USA · Computing + Mathematical Sciences (CMS) Department California Institute of Technology Pasadena, CA 91125, USA · School of Mathematics University of Minnesota Minneapolis, MN 55455, USA

  19. Time-Varying Graph Learning with Constraints on Graph Temporal Variation

    Jan 10, 2020Haruki Yokota, Koki Yamada, Yuichi Tanaka +1Graph Signal ProcessingGraph Structure Learning

    Graduate School of Engineering, The University of Osaka, Osaka 565-0871, Japan · Graduate School of Engineering, Tokyo University of Agriculture and Technology, Tokyo 184-8588, Japan · Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA 90089 USA