A rank-aware block decomposition for linear and bilinear operations in recommender models (FM, DCNv2, attention, FC) reduces redundant context feature computation to once per request with identity-equivalent results, plus rDCN variant for deeper layers.
Request-only optimization for recommendation systems
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.IR 4roles
background 1polarities
background 1representative citing papers
SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
Introduces versioned late materialization to eliminate data redundancy in ultra-long sequence training for DLRMs by storing histories once and reconstructing via pointers at training time.
citing papers explorer
-
Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems
A rank-aware block decomposition for linear and bilinear operations in recommender models (FM, DCNv2, attention, FC) reduces redundant context feature computation to once per request with identity-equivalent results, plus rDCN variant for deeper layers.
-
Similar Users-Augmented Interest Network
SUIN improves CTR prediction by augmenting target user sequences with similar users' behaviors via embedding-based retrieval, user-specific position encoding, and user-aware target attention.
-
A Survey on Generative Recommendation: Data, Model, and Tasks
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks and efficiency.
-
Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale
Introduces versioned late materialization to eliminate data redundancy in ultra-long sequence training for DLRMs by storing histories once and reconstructing via pointers at training time.