For modern recommender systems, the use of low-dimensional latent representations to embed users and items based on their observed interactions has become commonplace. However, many existing recommendation models are primarily designed for coarse-grained and homogeneous interactions, which limits their effectiveness in two critical dimensions. Firstly, these models fail to leverage the relational dependencies that exist across different types of user behaviors, such as page views, collects, comments, and purchases. Secondly, they struggle to capture the fine-grained latent factors that drive user interaction patterns. To address these limitations, we present a heterogeneous graph collaborative filtering model MixRec that excels at disentangling users' multi-behavior interaction patterns and uncovering the latent intent factors behind each behavior. Our model achieves this by incorporating intent disentanglement and multi-behavior modeling, facilitated by a parameterized heterogeneous hypergraph architecture. Furthermore, we introduce a novel contrastive learning paradigm that adaptively explores the advantages of self-supervised data augmentation, thereby enhancing the model's resilience against data sparsity and expressiveness with relation heterogeneity. To validate the efficacy of MixRec, we conducted extensive experiments on three public datasets. The results clearly demonstrate its superior performance, significantly outperforming various state-of-the-art baselines. Our model is open-sourced and available at: https://github.com/HKUDS/MixRec.

翻译：在现代推荐系统中，利用低维潜在表示基于观测到的交互行为嵌入用户和物品已成为普遍做法。然而，许多现有推荐模型主要针对粗粒度同质交互设计，这在两个关键维度上限制了其有效性。首先，这些模型未能利用不同类型用户行为（如页面浏览、收藏、评论、购买）间存在的关系依赖性。其次，它们难以捕捉驱动用户交互模式的细粒度潜在因素。为突破这些局限，本文提出异构图协同过滤模型MixRec，该模型擅长解耦用户的多行为交互模式，并揭示每种行为背后的潜在意图因子。我们通过参数化异质超图架构，结合意图解耦与多行为建模来实现这一目标。此外，我们引入了一种新颖的对比学习范式，能自适应探索自监督数据增强的优势，从而提升模型对数据稀疏性的鲁棒性及关系异质性下的表达能力。为验证MixRec的有效性，我们在三个公开数据集上进行了广泛实验。结果明确表明其卓越性能，显著优于多种最先进的基线模型。本模型已开源，访问地址为：https://github.com/HKUDS/MixRec。