DLRM: mixed-feature recommendation and hybrid parallelism benchmark

What changed

Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study.

Scientific scope

Combined sparse categorical embeddings, dense-feature MLP processing, explicit feature interactions and a top predictor, with model-parallel embeddings and data-parallel dense layers for systems study. Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Integrates inherited factorization/MLP techniques rather than inventing recommendation. Public model/benchmark is not the complete confidential production recommender or every later optimized implementation. native BigBasin benchmarks do not certify user benefit, fairness or universal hardware superiority.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Deep Learning Recommendation Model for Personalization and Recommendation Systems

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction