VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
This addresses data sparsity and popularity bias in recommendation systems, though it is incremental as it builds on existing graph-based and LLM methods.
The paper tackles data sparsity and popularity bias in recommendation systems by proposing a data augmentation framework that uses LLMs to generate synthetic user-item interactions via majority-voting reranking, integrated with graph contrastive learning. Experiments show it improves accuracy and reduces bias, outperforming baselines.
Recommendation systems often suffer from data sparsity caused by limited user-item interactions, which degrade their performance and amplify popularity bias in real-world scenarios. This paper proposes a novel data augmentation framework that leverages Large Language Models (LLMs) and item textual descriptions to enrich interaction data. By few-shot prompting LLMs multiple times to rerank items and aggregating the results via majority voting, we generate high-confidence synthetic user-item interactions, supported by theoretical guarantees based on the concentration of measure. To effectively leverage the augmented data in the context of a graph recommendation system, we integrate it into a graph contrastive learning framework to mitigate distributional shift and alleviate popularity bias. Extensive experiments show that our method improves accuracy and reduces popularity bias, outperforming strong baselines.