NodeDiffRec uses a two-stage diffusion process to generate pseudo-items and interactions for recommender data augmentation, reporting SOTA gains on three sparse datasets.
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
REJECT 1representative citing papers
citing papers explorer
-
Beyond Interactions: Node-Level Graph Generation for Knowledge-Free Augmentation in Recommender Systems
NodeDiffRec uses a two-stage diffusion process to generate pseudo-items and interactions for recommender data augmentation, reporting SOTA gains on three sparse datasets.