Cell Complex Neural Networks

by   Mustafa Hajij, et al.
Santa Clara University
University of South Florida

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 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 cell2vec, a generalization for node2vec.


page 1

page 2

page 3

page 4


CIN++: Enhancing Topological Message Passing

Graph Neural Networks (GNNs) have demonstrated remarkable success in lea...

Signal Processing on Cell Complexes

The processing of signals supported on non-Euclidean domains has attract...

Weisfeiler and Lehman Go Cellular: CW Networks

Graph Neural Networks (GNNs) are limited in their expressive power, stru...

Graph Neural Network for Cell Tracking in Microscopy Videos

We present a novel graph neural network (GNN) approach for cell tracking...

From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module

Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networ...

Topology preserving thinning for cell complexes

A topology preserving skeleton is a synthetic representation of an objec...

Please sign up or login with your details

Forgot password? Click here to reset