Topological Representation Learning

Overview

The field studies how to encode and learn data structure that ordinary distances or pairwise graphs can miss, such as loops, connected components, and relations among groups of points. Common approaches use persistent homology and persistence diagrams, spectral features from graph or sheaf Laplacians, and neural networks on simplicial or cellular complexes; these can serve as input features, training objectives, or architectural building blocks. The goal is to make representations more faithful to underlying shape and connectivity, supporting tasks from graph and point-cloud learning to medical imaging and multimodal models. Results are promising across varied benchmarks, but computational cost and whether models learn genuine topology rather than dataset-specific combinatorial patterns remain open challenges.

Latest papers

CardsList

78 papers9 papers in the last four weeks, down 31% on the four weeks before. 0.1% of all new papers.

  1. Zero-Dimensional Attention Topology for Linguistic Acceptability

    Nov 17, 2026Saeed AlMarriTransformer AttentionTopological Representation Learning

  2. From Nodes to Pixels: Topological and Structural Two-View Graph Imaging

    Nov 10, 2026Md Joshem Uddin, Soham Changani, Sai Karthik Navuluru +2Graph Representation LearningTopological Representation Learning

  3. A Topological Encoder Decoder Framework for Temporal Graph Learning

    Nov 7, 2026Ronan Buck, Kiarash Shamsi, Tran Gia Bao Ngo +3Temporal GNNsGraph Generation

  4. TopoSHAP: Shapley for Explainable and Efficient Topological Deep Learning

    Nov 5, 2026Mathilde Papillon, Nina MiolaneSHAP Feature AttributionTopological Representation Learning

  5. TRiST: Topology-Reinforced Swin Transformer for Medical Image Analysis

    Nov 5, 2026Pengfei Gu, Huimin Li, Guangyu Meng +4Medical Image AnalysisTopological Representation Learning

  6. Message-passing graph persistence

    Nov 4, 2026Jorge Luiz Franco, Arthur Queiroz Moura, Moacir Ponti +1Persistent HomologyTopological Representation Learning

  7. HTCE: Homeomorphism-inspired Topological Cross-Scene Experience Canonicalization and Reuse for Object Navigation

    Nov 3, 2026Xiaoran Xu, Yupeng Wu, Tianyu Xue +4Object-Goal NavigationVision-Language Navigation

  8. Geometric Morphology Learning: Empowering Foundation Models from Structure to Spacetime Intelligence

    Nov 1, 2026Li Sun, Philip S. YuGeometric Representation LearningTopological Representation Learning

  9. Escaping the Phylogenetic Trap: Persistent Homology Enables Cross-Species Ion Channel Classification via Multimodal Graph Neural Networks

    Oct 21, 2026Arezoo Bybordi, Favour Achimba, Mariam Gelashvili +4OOD GeneralizationProtein Representation Learning

  10. Learning Topology-Aware Representations for Mechanics-Relevant TPMS Metamaterials

    Oct 14, 2026Songlin Duan, Shuo Yang, Yujia Zheng +1Topological Representation Learning3D Representation Learning

  11. Persistence Positional Encoding: A Minimal Transformer Recipe for Persistence Diagrams

    Oct 13, 2026Eunwoo Heo, Ganghyun Kim, Jaejun YooTopological Representation LearningPersistent Homology

  12. Batch Before You Lift: Scalable Topological Deep Learning on Large Graphs

    Oct 8, 2026David Leko, Luka Benić, Guillermo Bernárdez +3Graph PartitioningTopological Representation Learning

  13. Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction

    Oct 6, 2026Yiming Ren, Xiang Liu, Mustafa Hajij +2Materials Property PredictionMolecular Property Prediction

  14. Operational Abstractions of Neural Network Concepts via Topological Representations

    Oct 4, 2026Mathieu Pont, Christoph GarthDisentangled Representation LearningModel Editing

  15. Higher-Order Molecular Grammars for Generative and Foundation Models in Chemistry

    Oct 1, 2026Yiming Huang, Yujie Zeng, Vijay Prakash Dwivedi +4Graph Representation LearningMolecular Generation

  16. Graph Representation via Elements of Discrete Morse and Cobordism Theories

    Oct 1, 2026Jennifer Rozenblit, Chenguang Yang, Yuxin Liu +2Diffusion Model GuidanceTopological Representation Learning

  17. Higher-Order Positional Encodings for Graph Representation Learning

    Oct 1, 2026Caleb Stam, Aagrim Hoysal, Sanjukta KrishnagopalGraph Representation LearningPositional Encoding

  18. TopoEmbedX: A General Framework for Representation Learning on Topological Domains

    Sep 29, 2026Florian Frantzen, Ibrahem AlJabea, Ines Henriques-Cadby +3Topological Representation LearningGraph Embedding

  19. Topological Signatures of Cyber-Attack Classes in Natural Visibility Graph Representations of Network Traffic

    Sep 22, 2026Ali Melih Kanca, Ilker TurkerNetwork Intrusion DetectionGraph Classification

  20. Signed Graph Pre-Training and Prompt Learning

    Sep 22, 2026Zihan Mei, Rong Pan, Yuzhou Chen +1Prompt LearningGraph Representation Learning

  21. CableVLA: Simulation-Privileged Global-Local Representation Learning for Cable Routing

    Sep 22, 2026Zhifei Teng, Bo Feng, Xiang Zou +4Visuo-Tactile Representation LearningSim-to-Real Transfer

  22. COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules

    Sep 18, 2026Sushovan Majhi, Atish Mitra, Žiga Virk +1Topological Representation Learning

  23. Repurposing Unified Topological Signatures for Graph Representation Learning

    Sep 15, 2026Sanyam Sanjay Jain, Anshika Krishnatray, Aditya Sharma +1Graph Representation LearningGNN Expressivity

  24. Synergistic Fusion of Topological Structure and Temporal Semantics of Mobility for Urban Region Embedding

    Sep 8, 2026Namwoo Kim, Jeeyun Chang, Kanghoon Lee +1Feature Interaction ModelingGeospatial Representation Learning

  25. Topology-induced Operators Reveal Complementary Graph Representations without Training

    Sep 8, 2026Meng Qin, Jinqiang Cui, Hongwei Zheng +2Graph Representation LearningGraph Embedding

  26. Recovering topological information of light by topological learning

    Sep 6, 2026Benquan Wang, Trishita Das, Yuhan Peng +8Topological Representation LearningComputational Imaging

  27. Beyond Uniform Local Isometry and Topology: FactoMap for Disentangled Representations

    Aug 25, 2026Sohini Gupta, Michael Gao, Bahareh TolooshamsDisentangled Representation LearningLatent Space Geometry