Mem-Rec: Memory Efficient Recommendation System using Alternative Representation. (arXiv:2305.07205v1 [cs.IR])

Deep learning-based recommendation systems (e.g., DLRMs) are widely used AI
models to provide high-quality personalized recommendations. Training data used
for modern recommendation systems commonly includes categorical features taking
on tens-of-millions of possible distinct values. These categorical tokens are
typically assigned learned vector representations, that are stored in large
embedding tables, on the order of 100s of GB. Storing and accessing these
tables represent a substantial burden in commercial deployments. Our work
proposes MEM-REC, a novel alternative representation approach for embedding …

ai models arxiv categorical data deep learning embedding features memory personalized personalized recommendations quality recommendation recommendations recommendation systems representation systems tables tokens training training data values vector