Interact2Vec -- An efficient neural network-based model for simultaneously learning users and items embeddings in recommender systems

2025-06-27

AI Summary

Learning low-dimensional user-item embeddings solely from implicit feedback in high-dimensional sparse recommendation data remains challenging. Method: This paper proposes a novel neural collaborative filtering model that innovatively integrates contrastive learning—borrowed from NLP—and dynamic negative sampling to enable joint, end-to-end optimization of user and item embeddings. The approach requires neither explicit ratings nor auxiliary side information, thereby significantly improving training efficiency under resource-constrained conditions. Contribution/Results: Evaluated on multiple public benchmarks, the model consistently ranks second or third in recommendation accuracy while reducing average training time by 274%. Moreover, the learned embeddings demonstrate superior performance on downstream tasks, confirming their strong generalization capability and computational efficiency.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Natural Language Processing: Learning & Optimization for NLP
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Over the past decade, recommender systems have experienced a surge in popularity. Despite notable progress, they grapple with challenging issues, such as high data dimensionality and sparseness. Representing users and items as low-dimensional embeddings learned via neural networks has become a leading solution. However, while recent studies show promising results, many approaches rely on complex architectures or require content data, which may not always be available. This paper presents Interact2Vec, a novel neural network-based model that simultaneously learns distributed embeddings for users and items while demanding only implicit feedback. The model employs state-of-the-art strategies that natural language processing models commonly use to optimize the training phase and enhance the final embeddings. Two types of experiments were conducted regarding the extrinsic and intrinsic quality of the model. In the former, we benchmarked the recommendations generated by Interact2Vec's embeddings in a top-$N$ ranking problem, comparing them with six other recommender algorithms. The model achieved the second or third-best results in 30% of the datasets, being competitive with other recommenders, and has proven to be very efficient with an average training time reduction of 274% compared to other embedding-based models. Later, we analyzed the intrinsic quality of the embeddings through similarity tables. Our findings suggest that Interact2Vec can achieve promising results, especially on the extrinsic task, and is an excellent embedding-generator model for scenarios of scarce computing resources, enabling the learning of item and user embeddings simultaneously and efficiently.

Problem

• Learning user and item embeddings efficiently in recommender systems
• Addressing high data dimensionality and sparseness challenges
• Reducing training time while maintaining competitive recommendation quality

Innovation

• Neural network-based user and item embeddings
• Uses only implicit feedback data
• Optimizes training with NLP strategies