mlsanityData to 14 Oct 2026

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction

arXiv 2508.21460 ↗First posted 29 Aug 2025cs.IR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

In click-through rate prediction, click-through rate prediction is used to model users' interests. However, most of the existing CTR prediction methods are mainly based on the ID modality. As a result, they are unable to comprehensively model users' multi-modal preferences. Therefore, it is necessary to introduce multi-modal CTR prediction. Although it seems appealing to directly apply the existing multi-modal fusion methods to click-through rate prediction models, these methods (1) fail to effectively disentangle commonalities and specificities across different modalities; (2) fail to consider the synergistic effects between modalities and model the complex interactions between modalities. To address the above issues, this paper proposes the Diffusion-based Multi-modal Synergy Interest Network (Diff-MSIN) framework for click-through prediction. This framework introduces three innovative modules: the Multi-modal Feature Enhancement (MFE) Module Synergistic Relationship Capture (SRC) Module, and the Feature Dynamic Adaptive Fusion (FDAF) Module. The MFE Module and SRC Module extract synergistic, common, and special information among different modalities. They effectively enhances the representation of the modalities, improving the overall quality of the fusion. To encourage distinctiveness among different features, we design a Knowledge Decoupling method. Additionally, the FDAF Module focuses on capturing user preferences and reducing fusion noise. To validate the effectiveness of the Diff-MSIN framework, we conducted extensive experiments using the Rec-Tmall and three Amazon datasets. The results demonstrate that our approach yields a significant improvement of at least 1.67% compared to the baseline, highlighting its potential for enhancing multi-modal recommendation systems. Our code is available at the following link: https://github.com/Cxx-0/Diff-MSIN.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 29 Aug 2025.

Builds on

33 of 51 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2016Wide & Deep Learning for Recommender Systemscited by 747
  4. 2017Deep Interest Network for Click-Through Rate Predictioncited by 544
  5. 2017Deep & Cross Network for Ad Click Predictionscited by 393
  6. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 338
  7. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 278
  8. 2018Efficient Low-rank Multimodal Fusion with Modality-Specific Factorscited by 270
  9. 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 177
  10. 2019Behavior Sequence Transformer for E-commerce Recommendation in Alibabacited by 130
  11. 2022Towards Universal Sequence Representation Learning for Recommender Systemscited by 121
  12. 2022Learning Vector-Quantized Item Representation for Transferable Sequential Recommenderscited by 112
21 more
  1. 2023DiffuRec: A Diffusion Model for Sequential Recommendationcited by 93
  2. 2023Diffusion Recommender Modelcited by 88
  3. 2021Mining Latent Structures for Multimedia Recommendationcited by 79
  4. 2019Neural News Recommendation with Attentive Multi-View Learningcited by 59
  5. 2021End-to-End User Behavior Retrieval in Click-Through RatePrediction Modelcited by 45
  6. 2023TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishoucited by 41
  7. 2023DiffKG: Knowledge Graph Diffusion Model for Recommendationcited by 41
  8. 2021Non-invasive Self-attention for Side Information Fusion in Sequential Recommendationcited by 39
  9. 2023Diffusion Augmentation for Sequential Recommendationcited by 38
  10. 2024Diffusion Models for Generative Outfit Recommendationcited by 29
  11. 2024Denoising Diffusion Recommender Modelcited by 28
  12. 2022ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterestcited by 23
  13. 2024Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insightscited by 23
  14. 2019Matching Images and Text with Multi-modal Tensor Fusion and Re-rankingcited by 20
  15. 2020Adversarial Multimodal Representation Learning for Click-Through Rate Predictioncited by 18
  16. 2023Adaptive Multi-Modalities Fusion in Sequential Recommendation Systemscited by 14
  17. 2023Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendationcited by 10
  18. 2021XCrossNet: Feature Structure-Oriented Learning for Click-Through Rate Predictioncited by 6
  19. 2024End-to-end training of Multimodal Model and ranking Modelcited by 6
  20. 2021Path-based Deep Network for Candidate Item Matching in Recommenderscited by 3
  21. 2024Deep Pattern Network for Click-Through Rate Predictioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026R3-REC: Reasoning-Driven Recommendation via Retrieval-Augmented LLMs over Multi-Granular Interest Signalscited by 1
  2. 2026Retrieval-Augmented Multimodal Model for Fake News Detectioncited by 0
  3. 2026MRAFnd: Multimodal Retrieval-Augmented Framework for Zero-Shot Fake News Detectioncited by 0
  4. 2026Anatomy of a Decision: Uncertainty-aware Hierarchical Intent Learning via Flow Matching for Multimodal Recommendationcited by 0