Retrieving GNN Architecture for Collaborative Filtering

Graph Neural Networks (GNNs) have been widely used in Collaborative Filtering (CF). However, when given a new recommendation scenario, the current options are either selecting from existing GNN architectures or employing Neural Architecture Search (NAS) to obtain a well-performing GNN model, both of which are expensive in terms of human expertise or computational resources.To address the problem, in this work,we propose a novel neural retrieval approach, dubbed RGCF, to search a well-performing architecture for GNN-based CF rapidly when handling new scenarios. Specifically, we design the neural retrieval approach based on meta-learning by developing two-level meta-features, ranking loss, and task-level data augmentation, and in a retrieval paradigm, RGCF can directly return a well-performing architecture given a new dataset (query), thus being efficient inherently. Experimental results on two mainstream tasks, i.e., rating prediction and item ranking, show that RGCF outperforms all models either by human-designed or NAS on two new datasets in terms of effectiveness and efficiency. Particularly, the efficiency improvement is significant, taking as an example that RGCF is 61.7-206.3x faster than a typical reinforcement learning based NAS approach on the two new datasets. Code and data are available at https://github.com/BUPT-GAMMA/RGCF.