Learning Graph Cellular Automata | Daniele Grattarola

Join the Learning on Graphs and Geometry Reading Group: hannes-stark.com/logag-readin...
Paper "Learning Graph Cellular Automata": arxiv.org/abs/2110.14237
Abstract: Cellular automata (CA) are a class of computational models that exhibit rich dynamics emerging from the local interaction of cells arranged in a regular lattice. In this work we focus on a generalised version of typical CA, called graph cellular automata (GCA), in which the lattice structure is replaced by an arbitrary graph. In particular, we extend previous work that used convolutional neural networks to learn the transition rule of conventional CA and we use graph neural networks to learn a variety of transition rules for GCA. First, we present a general-purpose architecture for learning GCA, and we show that it can represent any arbitrary GCA with finite and discrete state space. Then, we test our approach on three different tasks: 1) learning the transition rule of a GCA on a Voronoi tessellation; 2) imitating the behaviour of a group of flocking agents; 3) learning a rule that converges to a desired target state.
Authors: Daniele Grattarola, Lorenzo Livi, Cesare Alippi
Twitter Hannes: / hannesstaerk
Twitter Dominique: / dom_beaini
Twitter Valence Discovery: / valence_ai
Reading Group Slack: logag.slack.com/join/shared_i...
~
00:00 Intro
01:13 Cellular Automata
07:17 Graph Cellular Automata
10:17 Learning GCA
24:52 GNCA on Voronoi Tessellation
35:15 GNCA for Agent-Based Modelling
39:26 GNCA that converge to a fixed target
01:01:16 Future Research
01:03:32 Q&A

[@yidaweng8367]

Wolfram physics Model would be a more general model for this.

[@sedenions]

Next - hypergraph CAs