mlsanityData to 7 Oct 2026

Diss-l-ECT: Dissecting Graph Data with Local Euler Characteristic Transforms

arXiv 2410.02622 ↗First posted 3 Oct 2024cs.LG math.ATcited by 6

Not on the map. Why?

Abstract (arXiv)

The Euler Characteristic Transform (ECT) is an efficiently-computable geometrical-topological invariant that characterizes the global shape of data. In this paper, we introduce the Local Euler Characteristic Transform (ℓ-ECT), a novel extension of the ECT particularly designed to enhance expressivity and interpretability in graph representation learning. Unlike traditional Graph Neural Networks (GNNs), which may lose critical local details through aggregation, the ℓ-ECT provides a lossless representation of local neighborhoods. This approach addresses key limitations in GNNs by preserving nuanced local structures while maintaining global interpretability. Moreover, we construct a rotation-invariant metric based on ℓ-ECTs for spatial alignment of data spaces. Our method exhibits superior performance compared to standard GNNs on a variety of node-classification tasks, while also offering theoretical guarantees that demonstrate its effectiveness.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 50 of its 67 references that are in the map. First posted on arXiv 3 Oct 2024.

Builds on

50 of 67 references.

References · 50

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Layer Normalizationcited by 5,579
  6. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  11. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  12. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
38 more
  1. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  2. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  3. 2019Multi-scale Attributed Node Embeddingcited by 543
  4. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  5. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  6. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 361
  7. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  8. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 309
  9. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  10. 2023A Survey on Oversmoothing in Graph Neural Networkscited by 246
  11. 2020Can Graph Neural Networks Count Substructures?cited by 235
  12. 2021Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networkscited by 219
  13. 2020Graph Neural Networks with Heterophilycited by 202
  14. 2022Finding Global Homophily in Graph Neural Networks When Meeting Heterophilycited by 179
  15. 2022How Powerful are Spectral Graph Neural Networkscited by 169
  16. 2022Revisiting Heterophily For Graph Neural Networkscited by 169
  17. 2023On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topologycited by 163
  18. 2021Weisfeiler and Leman go Machine Learning: The Story so farcited by 121
  19. 2020Simplicial Neural Networkscited by 105
  20. 2021Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patternscited by 95
  21. 2023On the Expressive Power of Geometric Graph Neural Networkscited by 89
  22. 2021Topological Graph Neural Networkscited by 86
  23. 2023Everything is Connected: Graph Neural Networkscited by 85
  24. 2021GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophilycited by 84
  25. 2023Attending to Graph Transformerscited by 81
  26. 2019Graph Filtration Learningcited by 68
  27. 2024Position: Topological Deep Learning is the New Frontier for Relational Learningcited by 65
  28. 2020Graph Kernels: State-of-the-Art and Future Challengescited by 63
  29. 2019Learning metrics for persistence-based summaries and applications for graph classificationcited by 57
  30. 2021Improving Graph Neural Networks with Simple Architecture Designcited by 41
  31. 2021Simplicial Convolutional Neural Networkscited by 40
  32. 2023Curvature Filtrations for Graph Generative Model Evaluationcited by 18
  33. 2023Differentiable Euler Characteristic Transforms for Shape Classificationcited by 18
  34. 2023Simplicial Representation Learning with Neural k-Formscited by 18
  35. 2024Topological Neural Networks go Persistent, Equivariant, and Continuouscited by 15
  36. 2022Modeling the Machine Learning Multiversecited by 11
  37. 2022Topological Singularity Detection at Multiple Scalescited by 11
  38. 2024Mapping the Multiverse of Latent Representationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 3.

6 papers.

  1. 2024Point Cloud Synthesis Using Inner Product Transformscited by 2
  2. 2025LEAP: Local ECT-Based Learnable Positional Encodings for Graphscited by 2
  3. 2025On topological descriptors for graph productscited by 2
  4. 2026Global and Local Topology-Aware Attention with Persistent Homology and Euler Biases for Time-Series Forecastingcited by 0
  5. 2026Geometry-Aware Simplicial Message Passingcited by 0
  6. 2026Encoding the Euler Characteristic Transformcited by 0