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

TL;DR

Interact2Vec is an efficient neural network model that learns user and item embeddings from implicit feedback, outperforming many existing methods in speed and showing promising recommendation quality, especially in resource-constrained scenarios.

Contribution

The paper introduces Interact2Vec, a novel neural network model that simultaneously learns user and item embeddings using only implicit feedback, with improved efficiency and competitive recommendation performance.

Findings

Achieved second or third-best results in 30% of datasets for recommendation tasks.

Reduced training time by an average of 274% compared to other embedding models.

Demonstrated promising intrinsic and extrinsic quality of embeddings in experiments.

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.