Graph Neural Networks Go Forward-Forward
This provides a biologically plausible and computationally advantageous alternative to backpropagation for graph neural networks, though it appears incremental as an extension of the Forward-Forward procedure to graphs.
The paper tackles the problem of training graph neural networks without backpropagation by introducing the Graph Forward-Forward algorithm, which uses forward passes only and shows effectiveness on 11 standard graph property prediction tasks.
We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows training graph neural networks with forward passes only, without backpropagation. Our method is agnostic to the message-passing scheme, and provides a more biologically plausible learning scheme than backpropagation, while also carrying computational advantages. With GFF, graph neural networks are trained greedily layer by layer, using both positive and negative samples. We run experiments on 11 standard graph property prediction tasks, showing how GFF provides an effective alternative to backpropagation for training graph neural networks. This shows in particular that this procedure is remarkably efficient in spite of combining the per-layer training with the locality of the processing in a GNN.