mlsanityData to 14 Oct 2026

Joint Behavior-guided and Modality-coherence Conditional Graph Diffusion Denoising for Multi Modal Recommendation

arXiv 2604.03654 ↗First posted 4 Apr 2026cs.IRcited by 0

On the map: Diffusion models → Diffusion recommenders

Abstract (arXiv)

In recent years, multimodal recommendation has received significant attention and achieved remarkable success in GCN-based recommendation methods. However, there are two key challenges here: (1) There is a significant amount of redundant information in multimodal features that is unrelated to user preferences. Directly injecting multimodal features into the interaction graph can affect the collaborative feature learning between users and items. (2) There are false negative and false positive behaviors caused by system errors such as accidental clicks and non-exposure. This feedback bias can affect the ranking accuracy of training sample pairs, thereby reducing the recommendation accuracy of the model. To address these challenges, this work proposes a Joint Behavior-guided and Modal-consistent Conditional Graph Diffusion Model (JBM-Diff) for joint denoising of multimodal features and user feedback. We design a diffusion model conditioned on collaborative features for each modal feature to remove preference-irrelevant information, and enhance the alignment between collaborative features and modal semantic information through multi-view message propagation and feature fusion. Finally, we detect the partial order consistency of sample pairs from a behavioral perspective based on learned modal preferences, set the credibility for sample pairs, and achieve data augmentation. Extensive experiments on three public datasets demonstrate the effectiveness of this work. Codes are available at https://github.com/pxcstart/JBMDiff.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion recommenders, one of 14 directions in Diffusion models. Builds on 27 of its 38 references that are in the map. First posted on arXiv 4 Apr 2026.

Builds on

27 of 38 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DiffMM: Multi-Modal Diffusion Model for Recommendation17 Jun
  2. 2023Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion31 Oct

Other references · 25

  1. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  2. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,027
  3. 2019Graph Neural Networks for Social Recommendationcited by 714
  4. 2019Neural Graph Collaborative Filteringcited by 661
  5. 2020Self-supervised Graph Learning for Recommendationcited by 305
  6. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  7. 2015VBPR: Visual Bayesian Personalized Ranking from Implicit Feedbackcited by 151
  8. 2022Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learningcited by 86
  9. 2020Denoising Implicit Feedback for Recommendationcited by 80
  10. 2021Mining Latent Structures for Multimedia Recommendationcited by 79
  11. 2021A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendationcited by 59
  12. 2021GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedbackcited by 58
13 more
  1. 2022Bootstrap Latent Representations for Multi-modal Recommendationcited by 55
  2. 2022A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendationcited by 54
  3. 2023LGMRec: Local and Global Graph Learning for Multimodal Recommendationcited by 38
  4. 2023Automated Self-Supervised Learning for Recommendationcited by 37
  5. 2022Self-Supervised Hypergraph Transformer for Recommender Systemscited by 32
  6. 2020Multi-Graph Convolution Collaborative Filteringcited by 27
  7. 2022Personalized Federated Recommendation via Joint Representation Learning, User Clustering, and Model Adaptationcited by 25
  8. 2022Self-Guided Learning to Denoise for Robust Recommendationcited by 24
  9. 2022Multi-view Intent Disentangle Graph Networks for Bundle Recommendationcited by 22
  10. 2021Learning Robust Recommenders through Cross-Model Agreementcited by 15
  11. 2023PerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Trainingcited by 12
  12. 2022HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendationscited by 7
  13. 2022Towards Communication Efficient and Fair Federated Personalized Sequential Recommendationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025IGDMRec: Behavior Conditioned Item Graph Diffusion for Multimodal Recommendation ↗
  2. 2025DiffCL: A Diffusion-Based Contrastive Learning Framework with Semantic Alignment for Multimodal Recommendations
  3. 2025Graph-based Diffusion Model for Collaborative Filtering
  4. 2024S-Diff: An Anisotropic Diffusion Model for Collaborative Filtering in Spectral Domain
  5. 2023Graph Signal Diffusion Model for Collaborative Filtering
  6. 2025Causal Inspired Multi Modal Recommendation
  7. 2024Collaborative Filtering Based on Diffusion Models: Unveiling the Potential of High-Order Connectivity
  8. 2025Diffusion-augmented Graph Contrastive Learning for Collaborative Filter