mlsanityData to 7 Oct 2026

Cell Attention Networks

arXiv 2209.08179 ↗First posted 16 Sep 2022cs.LG cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Since their introduction, graph attention networks achieved outstanding results in graph representation learning tasks. However, these networks consider only pairwise relationships among nodes and then they are not able to fully exploit higher-order interactions present in many real world data-sets. In this paper, we introduce Cell Attention Networks (CANs), a neural architecture operating on data defined over the vertices of a graph, representing the graph as the 1-skeleton of a cell complex introduced to capture higher order interactions. In particular, we exploit the lower and upper neighborhoods, as encoded in the cell complex, to design two independent masked self-attention mechanisms, thus generalizing the conventional graph attention strategy. The approach used in CANs is hierarchical and it incorporates the following steps: i) a lifting algorithm that learns it edge features from it node features; ii) a cell attention mechanism to find the optimal combination of edge features over both lower and upper neighbors; iii) a hierarchical it edge pooling mechanism to extract a compact meaningful set of features. The experimental results show that CAN is a low complexity strategy that compares favorably with state of the art results on graph-based learning tasks.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 41 of its 78 references that are in the map. First posted on arXiv 16 Sep 2022.

Builds on

41 of 78 references.

References · 41

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  10. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  11. 2018Link Prediction Based on Graph Neural Networkscited by 829
  12. 2021How Attentive are Graph Attention Networks?cited by 818
29 more
  1. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  2. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  3. 2019Graph Neural Networks for Social Recommendationcited by 711
  4. 2019Graph Transformer Networkscited by 520
  5. 2018Hypergraph Neural Networkscited by 482
  6. 2019Self-Attention Graph Poolingcited by 421
  7. 2019Provably Powerful Graph Networkscited by 385
  8. 2018Invariant and Equivariant Graph Networkscited by 339
  9. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 312
  10. 2015Diffusion-Convolutional Neural Networkscited by 268
  11. 2021Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networkscited by 219
  12. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  13. 2022Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNscited by 208
  14. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  15. 2020Simplicial Neural Networkscited by 105
  16. 2018Towards Sparse Hierarchical Graph Classifierscited by 100
  17. 2019Topological Signal Processing over Simplicial Complexescited by 94
  18. 2021Neural Algorithmic Reasoningcited by 92
  19. 2014Propagation Kernelscited by 88
  20. 2021Principled Simplicial Neural Networks for Trajectory Predictioncited by 77
  21. 2019Hyper-SAGNN: a self-attention based graph neural network for hypergraphscited by 69
  22. 2020Cell Complex Neural Networkscited by 66
  23. 2022Simplicial Attention Networkscited by 40
  24. 2020EdgeNets:Edge Varying Graph Neural Networkscited by 36
  25. 2021Topological Signal Processing over Cell Complexescited by 23
  26. 2016Two's company, three (or more) is a simplex: Algebraic-topological tools for understanding higher-order structure in neural datacited by 22
  27. 2022Simplicial Attention Neural Networkscited by 21
  28. 2016Cliques and Cavities in the Human Connectomecited by 11
  29. 2014Amortized tildeO(|V|)-Delay Algorithm for Listing Chordless Cycles in Undirected Graphscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 8; 2024: 15; 2025: 6; 2026: 3.

34 papers.

Sort:

By area:

  1. 2024Position: Topological Deep Learning is the New Frontier for Relational Learningcited by 65
  2. 2023Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networkscited by 43
  3. 2023Probabilistically Rewired Message-Passing Neural Networkscited by 26
  4. 2024TopoBench: A Framework for Benchmarking Topological Deep Learningcited by 24
  5. 2024TopoX: A Suite of Python Packages for Machine Learning on Topological Domainscited by 22
  6. 2024E(n) Equivariant Topological Neural Networkscited by 22
  7. 2023Tangent Bundle Convolutional Learning: from Manifolds to Cellular Sheaves and Backcited by 21
  8. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  9. 2023From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Modulecited by 19
  10. 2024TopoTune : A Framework for Generalized Combinatorial Complex Neural Networkscited by 18
  11. 2024Probabilistic Graph Rewiring via Virtual Nodescited by 15
  12. 2024Topological Neural Networks go Persistent, Equivariant, and Continuouscited by 15
22 more
  1. 2023CIN++: Enhancing Topological Message Passingcited by 14
  2. 2024Attending to Topological Spaces: The Cellular Transformercited by 11
  3. 2025Copresheaf Topological Neural Networks: A Generalized Deep Learning Frameworkcited by 11
  4. 2022Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Backcited by 9
  5. 2023ICML 2023 Topological Deep Learning Challenge : Design and Resultscited by 7
  6. 2022Pooling Strategies for Simplicial Convolutional Networkscited by 5
  7. 2023Representing Edge Flows on Graphs via Sparse Cell Complexescited by 5
  8. 2024Higher-Order Topological Directionality and Directed Simplicial Neural Networkscited by 5
  9. 2024Demystifying Higher-Order Graph Neural Networkscited by 4
  10. 2023Zoo Guide to Network Embeddingcited by 2
  11. 2024Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breakingcited by 2
  12. 2024Molecular topological deep learning for polymer property predictioncited by 2
  13. 2025Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passingcited by 2
  14. 2025On the Sheafification of Higher-Order Message Passingcited by 1
  15. 2024CW-CNN & CW-AN: Convolutional Networks and Attention Networks for CW-Complexescited by 0
  16. 2024Higher-order Cross-structural Embedding Model for Time Series Analysiscited by 0
  17. 2025Topological Neural Networks over the Aircited by 0
  18. 2025Directed Semi-Simplicial Learning with Applications to Brain Activity Decodingcited by 0
  19. 2025Higher-Order Graph Databasescited by 0
  20. 2026Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answeringcited by 0
  21. 2026TopoU-Net: a U-Net architecture for topological domainscited by 0
  22. 2026Periodic Topological Deep Learning for Polymer Design and Discoverycited by 0