Cell Complex Neural Networks

Abstract

Cell complexes are topological spaces constructed from simple blocks called cells. They generalize graphs, simplicial complexes, and polyhedral complexes that form important domains for practical applications. They also provide a combinatorial formalism that allows the inclusion of complicated relationships of restrictive structures such as graphs and meshes. In this paper, we propose \textbf{Cell Complexes Neural Networks (CXNs)}, a general, combinatorial and unifying construction for performing neural network-type computations on cell complexes. We introduce an inter-cellular message passing scheme on cell complexes that takes the topology of the underlying space into account and generalizes message passing scheme to graphs. Finally, we introduce a unified cell complex encoder-decoder framework that enables learning representation of cells for a given complex inside the Euclidean spaces. In particular, we show how our cell complex autoencoder construction can give, in the special case \textbf{cell2vec}, a generalization for node2vec.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• Spectral Networks and Locally Connected Networks on Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Fast Graph Representation Learning with PyTorch Geometric
• How Powerful are Graph Neural Networks?
• Simplex2Vec embeddings for community detection in simplicial complexes
• A Survey on Graph Neural Networks for Knowledge Graph Completion

Cited by in corpus (5)

• Dirac signal processing of higher-order topological signals
• Signal Processing on Cell Complexes
• Turing patterns on discrete topologies: from networks to higher-order structures
• Cell Attention Networks
• Dirac-Equation Signal Processing: Physics Boosts Topological Machine Learning