AÇAI: Ascent Similarity Caching with Approximate Indexes

Tareq Si Salem (1, 2) , Giovanni Neglia (2) , Damiano Carra (3)

1 UniCA - Université Côte d'Azur
2 NEO - Network Engineering and Operations
3 UNIVR - Università degli studi di Verona = University of Verona

Similarity search is a key operation in multimedia retrieval systems and recommender systems, and it will play an important role also for future machine learning and augmented reality applications. When these systems need to serve large objects with tight delay constraints, edge servers close to the end-user can operate as similarity caches to speed up the retrieval. In this paper we present AÇAI, a new similarity caching policy which improves on the state of the art by using (i) an (approximate) index for the whole catalog to decide which objects to serve locally and which to retrieve from the remote server, and (ii) a mirror ascent algorithm to update the set of local objects with strong guarantees even when the request process does not exhibit any statistical regularity.

Domaines: Informatique [cs]

Tareq Si Salem, Giovanni Neglia, Damiano Carra. AÇAI: Ascent Similarity Caching with Approximate Indexes. ITC 2021 - 33rd International Teletraffic Congress, Aug 2021, Avignon (virtual), France. ⟨hal-03376175⟩