FROG: Effective Friend Recommendation in Online Games via Modality-aware User Preferences

2025-04-13

AI Summary

To address the insufficient joint modeling of multimodal user features (e.g., images, text) and social graph structure in online gaming friend recommendation, this paper proposes an end-to-end graph neural network framework. The method uniquely unifies three critical aspects: (1) high-order structural proximity in the friendship graph; (2) modality-specific pairwise user relevance; and (3) local and global cross-modal preferences. It achieves fine-grained cross-modal–graph joint representation learning via integration of multimodal encoders, a hierarchical graph attention mechanism, and a modality-aware preference disentanglement module. Deployed in Tencent’s live production system, the framework improves friend-addition rate by 18.7% and offline AUC by 5.2%, significantly outperforming existing state-of-the-art methods.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Due to the convenience of mobile devices, the online games have become an important part for user entertainments in reality, creating a demand for friend recommendation in online games. However, none of existing approaches can effectively incorporate the multi-modal user features (emph{e.g.}, images and texts) with the structural information in the friendship graph, due to the following limitations: (1) some of them ignore the high-order structural proximity between users, (2) some fail to learn the pairwise relevance between users at modality-specific level, and (3) some cannot capture both the local and global user preferences on different modalities. By addressing these issues, in this paper, we propose an end-to-end model extsc{FROG} that better models the user preferences on potential friends. Comprehensive experiments on both offline evaluation and online deployment at kw{Tencent} have demonstrated the superiority of extsc{FROG} over existing approaches.

Problem

• Incorporating multi-modal user features with friendship graph structural information
• Addressing high-order structural proximity and modality-specific pairwise relevance
• Capturing both local and global user preferences across different modalities

Innovation

• Incorporates multi-modal user features with graph structure
• Learns pairwise relevance at modality-specific level
• Captures both local and global user preferences