MixRec: Individual and Collective Mixing Empowers Data Augmentation for Recommender Systems
Yi Zhang, Yiwen Zhang
TL;DR
MixRec tackles data sparsity in recommender systems by introducing dual-mixing data augmentation and dual-mixing contrastive learning. It generates two kinds of views—individual mixing and collective mixing—via convex combinations of embeddings, with coefficients drawn from Beta(alpha, alpha) and Dirichlet distributions, and optimizes a multi-task objective that combines the main ranking loss with auxiliary contrastive signals. The approach uses a lightweight encoder (e.g., LightGCN) and maintains linear-time data augmentation, enabling easy integration with existing models. Empirical results on four real datasets demonstrate consistent gains in Recall@20 and NDCG@20, along with favorable efficiency and sparsity-robustness, underscoring MixRec's practicality for scalable recommendation systems.
Abstract
The core of the general recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by difficult-to-access interaction data severely limits the effectiveness of recommender systems. Faced with such a dilemma, various types of self-supervised learning methods have been introduced into recommender systems in an attempt to alleviate the data sparsity through distribution modeling or data augmentation. However, most data augmentation relies on elaborate manual design, which is not only not universal, but the bloated and redundant augmentation process may significantly slow down model training progress. To tackle these limitations, we propose a novel Dual Mixing-based Recommendation Framework (MixRec) to empower data augmentation as we wish. Specifically, we propose individual mixing and collective mixing, respectively. The former aims to provide a new positive sample that is unique to the target (user or item) and to make the pair-wise recommendation loss benefit from it, while the latter aims to portray a new sample that contains group properties in a batch. The two mentioned mixing mechanisms allow for data augmentation with only one parameter that does not need to be set multiple times and can be done in linear time complexity. Besides, we propose the dual-mixing contrastive learning to maximize the utilization of these new-constructed samples to enhance the consistency between pairs of positive samples. Experimental results on four real-world datasets demonstrate the advantages of MixRec in terms of effectiveness, simplicity, efficiency, and scalability.