SimDiffRec augments user sequences by replacing items at high-confidence diffusion positions with the model's top prediction and using averaged similar-item embeddings as noise, reporting consistent but unverified gains across five recommendation benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SimDiffRec: Semantic Similarity-Guided Diffusion for Contrastive Sequential Recommendation
SimDiffRec augments user sequences by replacing items at high-confidence diffusion positions with the model's top prediction and using averaged similar-item embeddings as noise, reporting consistent but unverified gains across five recommendation benchmarks.