CCE- is a Triton kernel implementation of cross-entropy loss with negative sampling that reduces memory by more than 10x and accelerates training by up to 2x for large-catalog sequential recommenders.
Climber: Toward efficient scaling laws for large recommendation models.arXiv preprint arXiv:2502.09888, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2representative citing papers
Empirical scaling of backbone, embeddings, and data shows largely independent additive gains, enabling a deployed model with 2.5x data and 8x compute that delivers +2.6% CVR improvement with minimal latency change.
citing papers explorer
-
Faster and Memory-Efficient Training of Sequential Recommendation Models for Large Catalogs
CCE- is a Triton kernel implementation of cross-entropy loss with negative sampling that reduces memory by more than 10x and accelerates training by up to 2x for large-catalog sequential recommenders.