mlsanityData to 7 Oct 2026

Link Prediction with Persistent Homology: An Interactive View

arXiv 2102.10255 ↗First posted 20 Feb 2021cs.LGcited by 37

Not on the map. Why?

Abstract (arXiv)

Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Builds on 28 of its 60 references that are in the map. First posted on arXiv 20 Feb 2021.

Builds on

28 of 60 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  7. 2018Link Prediction Based on Graph Neural Networkscited by 829
  8. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  9. 2015LINE: Large-scale Information Network Embeddingcited by 582
  10. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  11. 2018Deep Learning on Graphs: A Surveycited by 393
  12. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 237
16 more
  1. 2015Persistence Images: A Stable Vector Representation of Persistent Homologycited by 235
  2. 2019Topology-Preserving Deep Image Segmentationcited by 198
  3. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  4. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  5. 2019PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signaturescited by 125
  6. 2017Deep Learning with Topological Signaturescited by 113
  7. 2017Sliced Wasserstein Kernel for Persistence Diagramscited by 77
  8. 2014A Stable Multi-Scale Kernel for Topological Machine Learningcited by 74
  9. 2019Graph Filtration Learningcited by 68
  10. 2018A Topological Regularizer for Classifiers via Persistent Homologycited by 62
  11. 2019Learning metrics for persistence-based summaries and applications for graph classificationcited by 57
  12. 2020A Refined Laser Method and Faster Matrix Multiplicationcited by 56
  13. 2020Graph Geometry Interaction Learningcited by 55
  14. 2019Connectivity-Optimized Representation Learning via Persistent Homologycited by 43
  15. 2018Network Alignment by Discrete Ollivier-Ricci Flowcited by 14
  16. 2018Understanding and Predicting Links in Graphs: A Persistent Homology Perspectivecited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 5; 2023: 6; 2024: 14; 2025: 5; 2026: 1.

37 papers.

Sort:

By area:

  1. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  2. 2021Trigger Hunting with a Topological Prior for Trojan Detectioncited by 39
  3. 2021Topological Detection of Trojaned Neural Networkscited by 34
  4. 2021Cycle Representation Learning for Inductive Relation Predictioncited by 23
  5. 2021BScNets: Block Simplicial Complex Neural Networkscited by 21
  6. 2022On the effectiveness of persistent homologycited by 20
  7. 2023Embedding in Recommender Systems: A Surveycited by 19
  8. 2022Neural Approximation of Graph Topological Featurescited by 16
  9. 2023An Efficient Subgraph GNN with Provable Substructure Counting Powercited by 13
  10. 2024TopoGCL: Topological Graph Contrastive Learningcited by 13
  11. 2024Tensor-view Topological Graph Neural Networkcited by 12
  12. 2023Cycle Invariant Positional Encoding for Graph Representation Learningcited by 8
25 more
  1. 2024DE-HNN: An effective neural model for Circuit Netlist representationcited by 7
  2. 2022Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Predictioncited by 6
  3. 2025Enhancing Graph Representation Learning with Localized Topological Featurescited by 6
  4. 2024Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoningcited by 5
  5. 2024GEFL: Extended Filtration Learning for Graph Classificationcited by 5
  6. 2024KnowFormer: Revisiting Transformers for Knowledge Graph Reasoningcited by 5
  7. 2021Graph Embedding with Hierarchical Attentive Membershipcited by 4
  8. 2024Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysiscited by 4
  9. 2024Node Duplication Improves Cold-start Link Predictioncited by 4
  10. 2023Link Prediction without Graph Neural Networkscited by 3
  11. 2024Tensor-Fused Multi-View Graph Contrastive Learningcited by 3
  12. 2022On the Convergence of Optimizing Persistent-Homology-Based Lossescited by 2
  13. 2022Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunITcited by 2
  14. 2023Evaluating Link Prediction Explanations for Graph Neural Networkscited by 2
  15. 2024Mixup Barcodes: Quantifying Geometric-Topological Interactions between Point Cloudscited by 2
  16. 2024PHLP: Sole Persistent Homology for Link Prediction - Interpretable Feature Extractioncited by 2
  17. 2024When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learningcited by 2
  18. 2025Efficient Learning on Large Graphs using a Densifying Regularity Lemmacited by 2
  19. 2024Attribute-Enhanced Similarity Ranking for Sparse Link Predictioncited by 1
  20. 2025Transfer Learning for Temporal Link Predictioncited by 1
  21. 2025TMetaNet: Topological Meta-Learning Framework for Dynamic Link Predictioncited by 1
  22. 2025TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtrationcited by 1
  23. 2023Concept Prerequisite Relation Prediction by Using Permutation-Equivariant Directed Graph Neural Networkscited by 0
  24. 2024Scalar Function Topology Divergence: Comparing Topology of 3D Objectscited by 0
  25. 2026Scalable Topology-Preserving Graph Coarsening: Concepts and Algorithmscited by 0