MixDec Sampling: A Soft Link-based Sampling Method of Graph Neural Network for Recommendation

TL;DR

This paper introduces MixDec Sampling, a novel soft link-based sampling method for graph neural networks in recommendation systems, which enhances structural information utilization and benefits nodes with few neighbors.

Contribution

It proposes the first soft link-based sampling approach, combining Mixup and Decay modules to improve GNN training for recommendation tasks.

Findings

Significantly improves GNN-based recommendation performance

Enhances sampling for nodes with few neighbors

Consistently outperforms existing sampling methods

Abstract

Graph neural networks have been widely used in recent recommender systems, where negative sampling plays an important role. Existing negative sampling methods restrict the relationship between nodes as either hard positive pairs or hard negative pairs. This leads to the loss of structural information, and lacks the mechanism to generate positive pairs for nodes with few neighbors. To overcome limitations, we propose a novel soft link-based sampling method, namely MixDec Sampling, which consists of Mixup Sampling module and Decay Sampling module. The Mixup Sampling augments node features by synthesizing new nodes and soft links, which provides sufficient number of samples for nodes with few neighbors. The Decay Sampling strengthens the digestion of graph structure information by generating soft links for node embedding learning. To the best of our knowledge, we are the first to model sampling relationships between nodes by soft links in GNN-based recommender systems. Extensive experiments demonstrate that the proposed MixDec Sampling can significantly and consistently improve the recommendation performance of several representative GNN-based models on various recommendation benchmarks.