Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multimodal Graph Neural Network for Recommendation with Dynamic De-redundancy and Modality-Guided Feature De-noisy

Feng Mo, Lin Xiao, Qiya Song, Xieping Gao, Eryao Liang

TL;DR

Modality-guided global feature purifiers for each modality to alleviate the impact of modality noise and MGNM is a two-fold guiding mechanism eliminating modality features that are irrelevant to user preferences and captures complex relationships within the modality.

Abstract

Graph neural networks (GNNs) have become crucial in multimodal recommendation tasks because of their powerful ability to capture complex relationships between neighboring nodes. However, increasing the number of propagation layers in GNNs can lead to feature redundancy, which may negatively impact the overall 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 for Recommendation (MGNM) with Dynamic De-redundancy and Modality-Guided Feature De-noisy, which is divided into local and global interaction. Initially, in the local interaction process,we integrate a dynamic de-redundancy (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.

Multimodal Graph Neural Network for Recommendation with Dynamic De-redundancy and Modality-Guided Feature De-noisy

TL;DR

Modality-guided global feature purifiers for each modality to alleviate the impact of modality noise and MGNM is a two-fold guiding mechanism eliminating modality features that are irrelevant to user preferences and captures complex relationships within the modality.

Abstract

Graph neural networks (GNNs) have become crucial in multimodal recommendation tasks because of their powerful ability to capture complex relationships between neighboring nodes. However, increasing the number of propagation layers in GNNs can lead to feature redundancy, which may negatively impact the overall 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 for Recommendation (MGNM) with Dynamic De-redundancy and Modality-Guided Feature De-noisy, which is divided into local and global interaction. Initially, in the local interaction process,we integrate a dynamic de-redundancy (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.

Paper Structure

This paper contains 27 sections, 30 equations, 1 figure, 6 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional GNNs Recommendation
  4. Single-modal GNNs for Recommendation
  5. Visual Modeling
  6. Textual Modeling
  7. Problem Description
  8. Proposed Method
  9. Local Interaction
  10. Global Interaction
  11. Prediction
  12. Experiments
  13. Experimental Settings
  14. Datasets
  15. Implementation Details
  16. ...and 12 more sections

Figures (1)

  • Figure 1: Illustration of the proposed model. It is structured into global and local interaction. Firstly, global interaction leverages modality features to guide the elimination of redundant information irrelevant to user preferences. Secondly, a trainable transformation matrix captures complex relationships within the modality, providing global preference information. For local interaction, the model addresses feature redundancy from GNNs by penalizing over correlated features. Predictions are made by calculating the weighted sum of global and local interaction information. This approach captures both global and local user interests, offering a comprehensive characterization of user preferences.