Litcius/Paper detail

DMMD4SR: Diffusion Model-based Multi-level Multimodal Denoising for Sequential Recommendation

Weihai Lu, Yin Li

20258 citationsDOI

Abstract

Multimodal Sequential Recommendation (MMSR) leverages rich item features but often suffers from noisy representations derived from pre-trained models (PTMs). Existing methods neglect critical challenges: (1) domain shift between PTM training data and recommendation scenarios, (2) interest-agnostic noise within modalities (e.g., irrelevant background details), and (3) interaction uncertainty complicating modality fusion. To address these intertwined challenges, we propose DMMD4SR, a novel Diffusion Model-based Multi-level Multimodal Denoising framework for Sequential Recommendation. Inspired by the denoising power of diffusion models, DMMD4SR employs a progressive, multi-level strategy. It includes layers specifically designed to mitigate domain shift noise and context-aware interest-agnostic noise within modalities. Furthermore, an Uncertainty-Guided Modality Denoising Fusion Layer adaptively integrates the purified representations while accounting for interaction uncertainty. Extensive experiments on benchmark datasets demonstrate that DMMD4SR significantly outperforms state-of-the-art baselines, validating the effectiveness of our multi-level denoising approach. The code is available at https://github.com/luweihai/DMMD4SR.

Topics & Concepts

Noise reductionComputer scienceNoise (video)Artificial intelligenceBenchmark (surveying)Domain (mathematical analysis)Code (set theory)Modality (human–computer interaction)Machine learningPattern recognition (psychology)ModalitiesNoise measurementData miningVideo denoisingExploitSource codePower (physics)Sensor fusionAlgorithmSynthetic dataRecommender Systems and TechniquesImage Retrieval and Classification TechniquesAdvanced Data Compression Techniques
DMMD4SR: Diffusion Model-based Multi-level Multimodal Denoising for Sequential Recommendation | Litcius