New GNN architecture

Co-operative Graph Neural Networks

A large majority of Graph Neural Networks (GNNs) follow the message-passing paradigm, where node states are updated based on aggregated neighbour messages. In this post, we describe Co-operative GNNs (Co-GNNs), a new type of message-passing architecture where every node is viewed as a player that can choose to either ‘listen’, ‘broadcast’, ‘listen & broadcast’, or to ‘isolate.’ Standard message passing is a special case where every node ‘listens & broadcasts’ to all neighbours. We show that Co-GNNs are asynchronous, more expressive, and can address common plights of standard message-passing GNNs such as over-squashing and over-smoothing.

Illustration of node actions in Co-GNNs: standard, listen, broadcast, and isolate. Image credit: DALL-E 3.

This post was co-authored with Ben Finkelshtein, Ismail Ceylan, and Xingyue Huang and is based on the paper B. Finkelshtein et al., Cooperative Graph Neural Networks (2023) arXiv:2310.01267.