.png){kind=icon}
Return
DiffMBR: diffusion-guided GCN for multi-behavior recommendation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2026.105098.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
•
Present diffusion-guided structural reconstruction for noisy multi-behavior graphs.
•
Unify behavioral evolution modeling and global preference consistency in one framework.
•
Learn robust user representations via dual-path propagation and contrastive alignment.
•
Demonstrate state-of-the-art accuracy and sparsity robustness on three datasets.
Abstract
Current multi-behavior recommendation methods are often sensitive to noise and sparsity in auxiliary behaviors and comprehensively model users’ intrinsic behavioral habits. To address these limitations, we propose a diffusion-guided graph convolutional framework for robust multi-behavior recommendation, named DiffMBR. DiffMBR first introduces a dual-level structural diffusion mechanism to denoise and enhance both behavior-specific and unified interaction graphs. This process recovers reliable latent connections while suppressing noisy signals. Building on the refined graph structures, a dual-path propagation architecture is then used to capture personalized behavioral dependencies via cascade propagation, and behavior-invariant global preferences via consensus diffusion propagation. These complementary representations are further aligned through cross-view contrastive learning to obtain a unified and robust embedding. We conduct extensive experiments on three real-world multi-behavior datasets, Tmall, Taobao, and Beibei, showing that DiffMBR consistently outperforms various state-of-the-art methods. Notably, on the Taobao dataset, our model achieves relative improvements of 12.36% in Hit@10 and 25.31% in NDCG@10 over the strongest baseline. Additional experiments further illustrate the robustness and effectiveness of each component.
Keywords:
Multi-behavior recommendation
Diffusion model
Contrastive learning
Journal
I
IF:
6.9
Papers:
546
Citations:
0
Organization
Cited Papers
No cited papers available