Sharpness-Aware Graph Collaborative Filtering
This addresses performance issues in graph-based recommendation systems, but it is incremental as it adapts an existing sharpness-aware minimization technique to GNNs.
The paper tackles the problem of Graph Neural Networks (GNNs) in collaborative filtering performing poorly when training and test data distributions are misaligned and the challenge of selecting optimal minima during training. It proposes gSAM, a training schema that regularizes flatness in the weight loss landscape, showing experimental superiority.
Graph Neural Networks (GNNs) have achieved impressive performance in collaborative filtering. However, GNNs tend to yield inferior performance when the distributions of training and test data are not aligned well. Also, training GNNs requires optimizing non-convex neural networks with an abundance of local and global minima, which may differ widely in their performance at test time. Thus, it is essential to choose the minima carefully. Here we propose an effective training schema, called {gSAM}, under the principle that the \textit{flatter} minima has a better generalization ability than the \textit{sharper} ones. To achieve this goal, gSAM regularizes the flatness of the weight loss landscape by forming a bi-level optimization: the outer problem conducts the standard model training while the inner problem helps the model jump out of the sharp minima. Experimental results show the superiority of our gSAM.