BeLightRec: A lightweight recommender system enhanced with BERT

2025-03-26

AI Summary

To address the limitation of collaborative filtering (CF) in recommender systems—its neglect of item semantic information—this paper proposes a lightweight dual-path graph neural recommendation model. Methodologically, it is the first to explicitly integrate CF interaction signals with BERT-encoded semantic similarity signals derived from item names and descriptions within a GCN framework, designing a dual-path similarity co-modeling mechanism, along with multi-source signal weighting and model lightweighting strategies. Contributions include: (1) establishing a complementary co-paradigm that synergistically unifies semantic and interaction signals; and (2) achieving a favorable trade-off between accuracy and efficiency—yielding average improvements of 12.7% in Recall@10 and NDCG@10 over pure CF baselines across multiple public datasets, while reducing inference latency by 38%. Empirical results validate the effectiveness of semantic enhancement in boosting CF performance.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Graph-based Machine Learning
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The trend of data mining using deep learning models on graph neural networks has proven effective in identifying object features through signal encoders and decoders, particularly in recommendation systems utilizing collaborative filtering methods. Collaborative filtering exploits similarities between users and items from historical data. However, it overlooks distinctive information, such as item names and descriptions. The semantic data of items should be further mined using models in the natural language processing field. Thus, items can be compared using text classification, similarity assessments, or identifying analogous sentence pairs. This research proposes combining two sources of item similarity signals: one from collaborative filtering and one from the semantic similarity measure between item names and descriptions. These signals are integrated into a graph convolutional neural network to optimize model weights, thereby providing accurate recommendations. Experiments are also designed to evaluate the contribution of each signal group to the recommendation results.

Problem

• Combining collaborative filtering and semantic similarity for recommendations
• Enhancing item comparison using text classification and similarity
• Optimizing model weights in graph neural networks for accuracy

Innovation

• Combines collaborative filtering with semantic similarity
• Integrates signals into graph convolutional network
• Optimizes model weights for accurate recommendations