Profiling the Design Space for Graph Neural Networks based Collaborative Filtering

In recent years, Graph Neural Networks (GNNs) have been widely used in Collaborative Filtering (CF), one of the most popular methods in recommender systems. However, most existing works focus on designing an individual model architecture given a specific scenario, without studying the influences of different design dimensions. Thus, it remains a challenging problem to quickly obtain a top-performing model in a new recommendation scenario. To address the problem, in this work, we make the first attempt to profile the design space of GNN-based CF methods to enrich the understanding of different design dimensions as well as provide a novel paradigm of model design. Specifically, a unified framework of GNN-based CF is proposed, on top of which a design space is developed and evaluated by extensive experiments. Interesting findings on the impacts of different design dimensions on recommendation performance are obtained. Guided by the empirical findings, we further prune the design space to obtain a compact one containing a higher concentration of top-performing models. Empirical studies demonstrate its high quality and strong generalization ability.