RecD: session-aware feature deduplication across recommendation training

What changed

Coalesced session samples across logging, ETL and training, introducing inverse-keyed jagged tensors that share repeated feature values while retaining inverse mappings to their training examples.

Scientific scope

Coalesced session samples across logging, ETL and training, introducing inverse-keyed jagged tensors that share repeated feature values while retaining inverse mappings to their training examples. Deduplicates repeated features, not independent labels or arbitrary examples. Session grouping changes ordering and requires pipeline support; efficiency depends on actual session reuse and feature distributions. Reported storage, preprocessing and training gains are different metrics on selected industrial workloads.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Deduplicates repeated features, not independent labels or arbitrary examples. Session grouping changes ordering and requires pipeline support; efficiency depends on actual session reuse and feature distributions. Reported storage, preprocessing and training gains are different metrics on selected industrial workloads.

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.

• RecD: Deduplication for End-to-End Deep Learning Recommendation Model Training Infrastructure

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