Free Reads
Sign in to view your remaining parses.
Tag Filter
Diffusion Model-based Recommendation Systems
De-collapsing User Intent: Adaptive Diffusion Augmentation with Mixture-of-Experts for Sequential Recommendation
Diffusion Model-based Recommendation SystemsUser Intent Reconstruction in Sequential RecommendationSparse Data Augmentation MethodsMixture-of-Experts ArchitectureAdaptive Diffusion Augmentation Framework
The ADARec framework addresses data sparsity in sequential recommendation by utilizing a MixtureofExperts architecture to decouple coarse and finegrained user intents, effectively reconstructing intent hierarchies. Experiments show it outperforms existing methods on standard b
022
Towards A Tri-View Diffusion Framework for Recommendation
Published:11/25/2025
Diffusion Model-based Recommendation SystemsRecommendation Framework Maximizing Helmholtz Free EnergyAcceptance-Rejection Gumbel Sampling ProcessUser Preference Modeling and GenerationOptimization Methods for Diffusion Models
This paper introduces a triview diffusion framework for recommendations, integrating thermodynamic insights and maximizing Helmholtz free energy. It enhances optimization using a denoiser and AcceptanceRejection Gumbel Sampling, significantly improving recommendation system acc
05