Socially Aware Music Recommendation: A Multi-Modal Graph Neural Networks for Collaborative Music Consumption and Community-Based Engagement

TL;DR

This paper introduces a multi-modal graph neural network for socially aware music recommendation, integrating lyrics, audio, visual data, and social relationships to improve personalization and community engagement.

Contribution

It proposes a fusion-free deep mutual learning approach within a heterogeneous graph structure, effectively combining multiple data modalities and social information for enhanced recommendations.

Findings

Outperforms existing methods on benchmark datasets

Demonstrates robustness against missing modalities

Validates effectiveness through ablation studies

Abstract

This study presents a novel Multi-Modal Graph Neural Network (MM-GNN) framework for socially aware music recommendation, designed to enhance personalization and foster community-based engagement. The proposed model introduces a fusion-free deep mutual learning strategy that aligns modality-specific representations from lyrics, audio, and visual data while maintaining robustness against missing modalities. A heterogeneous graph structure is constructed to capture both user-song interactions and user-user social relationships, enabling the integration of individual preferences with social influence. Furthermore, emotion-aware embeddings derived from acoustic and textual signals contribute to emotionally aligned recommendations. Experimental evaluations on benchmark datasets demonstrate that MM-GNN significantly outperforms existing state-of-the-art methods across various performance metrics. Ablation studies further validate the critical impact of each model component, confirming the effectiveness of the framework in delivering accurate and socially contextualized music recommendations.