Scalable Dynamic Embedding Size Search for Streaming Recommendation
Yunke Qu, Liang Qu, Tong Chen, Xiangyu Zhao, Quoc Viet Hung Nguyen, Hongzhi Yin

TL;DR
This paper introduces SCALL, a reinforcement learning-based method that adaptively adjusts embedding sizes in streaming recommender systems within a fixed memory budget, improving efficiency and scalability.
Contribution
It proposes a novel probabilistic sampling strategy and RL-based search paradigm for scalable, adaptive embedding size management in streaming recommendation scenarios.
Findings
Effective in maintaining performance within memory constraints
Adapts embedding sizes based on user/item frequency
Outperforms existing methods in empirical evaluations
Abstract
Recommender systems typically represent users and items by learning their embeddings, which are usually set to uniform dimensions and dominate the model parameters. However, real-world recommender systems often operate in streaming recommendation scenarios, where the number of users and items continues to grow, leading to substantial storage resource consumption for these embeddings. Although a few methods attempt to mitigate this by employing embedding size search strategies to assign different embedding dimensions in streaming recommendations, they assume that the embedding size grows with the frequency of users/items, which eventually still exceeds the predefined memory budget over time. To address this issue, this paper proposes to learn Scalable Lightweight Embeddings for streaming recommendation, called SCALL, which can adaptively adjust the embedding sizes of users/items within a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRecommender Systems and Techniques · Data Management and Algorithms · Data Stream Mining Techniques
MethodsSparse Evolutionary Training
