Asymmetrical Attention Networks Fused Autoencoder for Debiased Recommendation

Popularity bias is a massive challenge for autoencoder-based models, which decreases the level of personalization and hurts the fairness of recommendations. User reviews reflect their preferences and help mitigate bias or unfairness in the recommendation. However, most existing works typically incorporate user (item) reviews into a long document and then use the same module to process the document in parallel. Actually, the set of user reviews is completely different from the set of item reviews. User reviews are heterogeneous in that they reflect a variety of items purchased by users, while item reviews are only related to the item itself and are thus typically homogeneous. In this article, a novel asymmetric attention network fused with autoencoders is proposed, which jointly learns representations from the user and item reviews and implicit feedback to perform recommendations. Specifically, we design an asymmetric attentive module to capture rich representations from user and item reviews, respectively, which solves data sparsity and explainable problems. Furthermore, to further address popularity bias, we apply a noise-contrastive estimation objective to learn high-quality de-popularity embedding via the decoder structure. A series of extensive experiments are conducted on four benchmark datasets to show that leveraging user review information can eliminate popularity bias and improve performance compared to various state-of-the-art recommendation techniques.

Automated summary

Popularity bias is a significant challenge for autoencoder-based models in recommendations, and incorporating user reviews can help mitigate this bias. However, most existing approaches treat user and item reviews as a homogeneous document, ignoring their heterogeneity. In this article, a novel asymmetric attention network fused with autoencoders is proposed to jointly learn representations from user and item reviews, addressing data sparsity and explainability issues. Additionally, a noise-contrastive estimation objective is applied to learn high-quality de-popularity embedding, further reducing popularity bias. Extensive experiments on benchmark datasets demonstrate that leveraging user review information can eliminate popularity bias and outperform state-of-the-art recommendation techniques.