RSAttAE: An Information-Aware Attention-based Autoencoder Recommender System

2025-02-10

AI Summary

Accurate user–movie rating prediction remains challenging due to sparse and noisy implicit interaction data. Method: This paper proposes an end-to-end collaborative filtering model that integrates an information-aware attention mechanism with an autoencoder, coupled with XGBoost for precise rating regression. Contribution/Results: Its core innovation lies in the first incorporation of a fine-grained attention mechanism into the autoencoder architecture, enabling dynamic weighting of user–item interaction representations during reconstruction and thereby enhancing implicit preference modeling. Evaluated on the MovieLens 100K dataset, the model achieves a 3.2% reduction in RMSE over state-of-the-art baselines, demonstrating the effectiveness of co-designing representation learning and regression components. The implementation is publicly available, establishing a new paradigm for high-performance, interpretable recommendation systems.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Data Mining & Knowledge Management: Recommender Systems
• Knowledge Representation and Reasoning: Preferences

Application Category

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

Abstract

Recommender systems play a crucial role in modern life, including information retrieval, the pharmaceutical industry, retail, and entertainment. The entertainment sector, in particular, attracts significant attention and generates substantial profits. This work proposes a new method for predicting unknown user-movie ratings to enhance customer satisfaction. To achieve this, we utilize the MovieLens 100K dataset. Our approach introduces an attention-based autoencoder to create meaningful representations and the XGBoost method for rating predictions. The results demonstrate that our proposal outperforms most of the existing state-of-the-art methods. Availability: github.com/ComputationIASBS/RecommSys

Problem

• Predicts unknown user-movie ratings
• Enhances customer satisfaction
• Outperforms existing recommendation methods

Innovation

• Attention-based Autoencoder for representations
• XGBoost for rating predictions
• MovieLens 100K dataset utilized