Similarity Caching: Theory and Algorithms

• Published in: IEEE/ACM transactions on networking Vol. 30; no. 2; pp. 475 - 486
• Main Authors: Neglia, Giovanni, Garetto, Michele, Leonardi, Emilio
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); IEEE/ACM
• Subjects: Algorithms; Caching; Computer Science; Content distribution networks; Costs; IEEE transactions; Machine learning; modeling; Multimedia; Multimedia systems; Networking and Internet Architecture; Recommender systems; Servers; Similarity; System effectiveness; Task analysis; Costs; Content distribution networks; modeling; Multimedia systems; Machine learning; Servers; Task analysis; Recommender systems; IEEE transactions
• ISSN: 1063-6692; 1558-2566
• DOI: 10.1109/TNET.2021.3126368

This paper focuses on similarity caching systems, in which a user request for an object <inline-formula> <tex-math notation="LaTeX">o </tex-math></inline-formula> that is not in the cache can be (partially) satisfied by a similar stored object <inline-formula> <tex-math notation="LaTeX">o' </tex-math></inline-formula>, at the cost of a loss of user utility. Similarity caching systems can be effectively employed in several application areas, like multimedia retrieval, recommender systems, genome study, and machine learning training/serving. However, despite their relevance, the behavior of such systems is far from being well understood. In this paper, we provide a first comprehensive analysis of similarity caching in the offline, adversarial, and stochastic settings. We show that similarity caching raises significant new challenges, for which we propose the first dynamic policies with some optimality guarantees. We evaluate the performance of our schemes under both synthetic and real request traces.