An Adaptive Graph Pre-training Framework for Localized Collaborative Filtering

TL;DR

This paper introduces ADAPT, an adaptive graph pre-training framework that enhances GNN-based recommendation systems by effectively addressing data sparsity and capturing both shared and unique graph features.

Contribution

The paper proposes a novel pre-training framework for GNN-based recommendations that does not require transferring embeddings and adapts to different user-item graphs.

Findings

ADAPT outperforms existing methods in recommendation accuracy.

The framework effectively captures both common and graph-specific knowledge.

Experimental results demonstrate its superiority across multiple datasets.

Abstract

Graph neural networks (GNNs) have been widely applied in the recommendation tasks and have obtained very appealing performance. However, most GNN-based recommendation methods suffer from the problem of data sparsity in practice. Meanwhile, pre-training techniques have achieved great success in mitigating data sparsity in various domains such as natural language processing (NLP) and computer vision (CV). Thus, graph pre-training has the great potential to alleviate data sparsity in GNN-based recommendations. However, pre-training GNNs for recommendations face unique challenges. For example, user-item interaction graphs in different recommendation tasks have distinct sets of users and items, and they often present different properties. Therefore, the successful mechanisms commonly used in NLP and CV to transfer knowledge from pre-training tasks to downstream tasks such as sharing learned embeddings or feature extractors are not directly applicable to existing GNN-based recommendations models. To tackle these challenges, we delicately design an adaptive graph pre-training framework for localized collaborative filtering (ADAPT). It does not require transferring user/item embeddings, and is able to capture both the common knowledge across different graphs and the uniqueness for each graph. Extensive experimental results have demonstrated the effectiveness and superiority of ADAPT.