AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations

Citations Over TimeTop 1% of 2021 papers

Abstract

Deep learning-based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimension of categorical variables (e.g., user/item identifiers) and meaningfully transform them in the low-dimensional space. The majority of existing DLRSs empirically pre-define a fixed and unified dimension for all user/item embeddings. It is evident from recent researches that different embedding sizes are highly desired for different users/items according to their frequency. However, manually selecting embedding sizes in recommender systems can be very challenging due to a large number of users/items and the dynamic nature of their frequency. Thus, in this paper, we propose an AutoML based end-to-end framework (AutoEmb), enabling various embedding dimensions according to the frequency in an automated and dynamic manner. To be specific, we first enhance a typical DLRS to allow various embedding dimensions; then, we propose an end-to-end differentiable framework that can automatically select different embedding dimensions according to user/item frequency; finally, we propose an AutoML based optimization algorithm in a streaming recommendation setting. The experimental results based on widely used benchmark datasets demonstrate the effectiveness of the AutoEmb framework.

Related Papers

• → An Accurate Identifier Renaming Prediction and Suggestion Approach(2023)20 cited
• → Recommender systems: models, challenges and opportunities(2023)5 cited
• → Handling an inconsistently coded categorical variable in a longitudinal dataset with cat2cat(2023)1 cited
• → Hybrid-based Research Article Recommender System(2023)3 cited
• → Advanced Recommender Systems(2018)1 cited