Dynamic De-Redundancy and Modality-Guided Feature De-Noisy for Multimodal Recommendation

Graph Neural Networks (GNNs), due to their advanced capability in extracting high-order neighbor relationships, have become essential in multimodal recommendation tasks. However, augmenting the number of propagation layers in GNNs can result in feature redundancy, which may degrade the final recommendation performance. In addition, the existing recommendation task method directly maps the preprocessed multimodal features to the low-dimensional space, which will bring the noise unrelated to user preference, thus affecting the representation ability of the model. To tackle the aforementioned challenges, we propose Multimodal Graph Neural Network (MGNM) for Recommendation with Dynamic De-Redundancy (DDR) and Modality-Guided Feature De-Noisy, which is divided into local and global interaction. Initially, in the local interaction process, we integrate a DDR loss function which is achieved by utilizing the product of the feature coefficient matrix and the feature matrix as a penalization factor. It reduces the feature redundancy effects of multimodal and behavioral features caused by the stacking of multiple GNN layers. Subsequently, in the global interaction process, we developed modality-guided global feature purifiers for each modality to alleviate the impact of modality noise. It is a two-fold guiding mechanism eliminating modality features that are irrelevant to user preferences and captures complex relationships within the modality. Experimental results demonstrate that MGNM achieves superior performance on multimodal information denoising and removal of redundant information compared to the state-of-the-art methods.