Uncertainty-aware Consistency Learning for Cold-Start Item Recommendation

TL;DR

This paper introduces UCC, a novel uncertainty-aware consistency learning framework that enhances cold-start item recommendation by aligning cold and warm item embeddings using user-item interaction data, improving overall recommendation performance.

Contribution

The paper proposes a new framework that leverages uncertainty-aware consistency learning to simultaneously improve cold and warm item recommendations without auxiliary features.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Achieves an average performance improvement of 27.6%.

Effectively aligns cold and warm item embeddings using uncertainty modeling.

Abstract

Graph Neural Network (GNN)-based models have become the mainstream approach for recommender systems. Despite the effectiveness, they are still suffering from the cold-start problem, i.e., recommend for few-interaction items. Existing GNN-based recommendation models to address the cold-start problem mainly focus on utilizing auxiliary features of users and items, leaving the user-item interactions under-utilized. However, embeddings distributions of cold and warm items are still largely different, since cold items' embeddings are learned from lower-popularity interactions, while warm items' embeddings are from higher-popularity interactions. Thus, there is a seesaw phenomenon, where the recommendation performance for the cold and warm items cannot be improved simultaneously. To this end, we proposed a Uncertainty-aware Consistency learning framework for Cold-start item recommendation (shorten as UCC) solely based on user-item interactions. Under this framework, we train the teacher model (generator) and student model (recommender) with consistency learning, to ensure the cold items with additionally generated low-uncertainty interactions can have similar distribution with the warm items. Therefore, the proposed framework improves the recommendation of cold and warm items at the same time, without hurting any one of them. Extensive experiments on benchmark datasets demonstrate that our proposed method significantly outperforms state-of-the-art methods on both warm and cold items, with an average performance improvement of 27.6%.