GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems
This work addresses efficiency and quality challenges in sequential recommender systems, offering a practical solution for real-time applications, though it appears incremental by building on existing GRU and positional encoding methods.
The paper tackled the problem of high computational costs and slow inference in transformer-based sequential recommender systems by introducing GLINT-RU, a lightweight model using gated recurrent units, which achieved superior prediction accuracy and inference speed in experiments on three datasets.
Transformer-based models have gained significant traction in sequential recommender systems (SRSs) for their ability to capture user-item interactions effectively. However, these models often suffer from high computational costs and slow inference. Meanwhile, existing efficient SRS approaches struggle to embed high-quality semantic and positional information into latent representations. To tackle these challenges, this paper introduces GLINT-RU, a lightweight and efficient SRS leveraging a single-layer dense selective Gated Recurrent Units (GRU) module to accelerate inference. By incorporating a dense selective gate, GLINT-RU adaptively captures temporal dependencies and fine-grained positional information, generating high-quality latent representations. Additionally, a parallel mixing block infuses fine-grained positional features into user-item interactions, enhancing both recommendation quality and efficiency. Extensive experiments on three datasets demonstrate that GLINT-RU achieves superior prediction accuracy and inference speed, outperforming baselines based on RNNs, Transformers, MLPs, and SSMs. These results establish GLINT-RU as a powerful and efficient solution for SRSs.