Efficient Image Gallery Representations at Scale Through Multi-Task Learning

Published in SIGIR ‘20 by Benjamin Gutelman, Pavel Levin

Paper: https://dl.acm.org/doi/abs/10.1145/3397271.3401433

Image galleries provide a rich source of diverse information about a product which can be leveraged across many recommendation and retrieval applications. We study the problem of building a universal image gallery encoder through multi-task learning (MTL) approach and demonstrate that it is indeed a practical way to achieve generalizability of learned representations to new downstream tasks. Additionally, we analyze the relative predictive performance of MTL-trained solutions against optimal and substantially more expensive solutions, and find signals that MTL can be a useful mechanism to address sparsity in low-resource binary tasks.