Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation

TL;DR

This paper introduces a pre-training approach for Graph Neural Networks to better handle cold-start users and items in recommendation systems, improving embedding quality and adaptability.

Contribution

It proposes a novel pre-training framework with self-attention and adaptive neighbor sampling to enhance cold-start recommendation performance.

Findings

Pre-trained GNNs outperform original GNNs on embedding inference.

The method improves recommendation accuracy for cold-start users/items.

Experiments validate the effectiveness of the proposed approach.

Abstract

Cold-start problem is a fundamental challenge for recommendation tasks. Despite the recent advances on Graph Neural Networks (GNNs) incorporate the high-order collaborative signal to alleviate the problem, the embeddings of the cold-start users and items aren't explicitly optimized, and the cold-start neighbors are not dealt with during the graph convolution in GNNs. This paper proposes to pre-train a GNN model before applying it for recommendation. Unlike the goal of recommendation, the pre-training GNN simulates the cold-start scenarios from the users/items with sufficient interactions and takes the embedding reconstruction as the pretext task, such that it can directly improve the embedding quality and can be easily adapted to the new cold-start users/items. To further reduce the impact from the cold-start neighbors, we incorporate a self-attention-based meta aggregator to enhance the aggregation ability of each graph convolution step, and an adaptive neighbor sampler to select the effective neighbors according to the feedbacks from the pre-training GNN model. Experiments on three public recommendation datasets show the superiority of our pre-training GNN model against the original GNN models on user/item embedding inference and the recommendation task.