Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation

2025-08-14

AI Summary

To address the challenge of jointly modeling outfit compatibility and personalized recommendation in fashion e-commerce, this paper proposes the Fashion Graph Attention Network (FGAT). FGAT constructs a three-level user-outfit-item graph structure and integrates multimodal visual and textual features; it employs graph attention mechanisms to dynamically weight inter-node interactions, thereby unifying fine-grained item compatibility modeling and user preference learning. Unlike prior approaches that treat compatibility and personalization separately, FGAT is the first framework to jointly optimize compatibility constraints and personalized ranking within a single architecture. Experiments on the POG dataset demonstrate that FGAT significantly outperforms state-of-the-art baselines—including HFGN—across key metrics: Accuracy, Hit Rate@10, Recall@10, and NDCG@10. These results validate the effectiveness of FGAT’s multi-granularity interaction representation and its end-to-end joint modeling capability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Combinatorial Optimization
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The rapid expansion of the fashion industry and the growing variety of products have made it challenging for users to find compatible items on e-commerce platforms. Effective fashion recommendation systems are crucial for filtering irrelevant items and suggesting suitable ones. However, simultaneously addressing outfit compatibility and personalized recommendations remains a significant challenge, as these aspects are often treated independently in existing studies, often overlooking the complex interactions between items and user preferences. This research introduces a new framework named FGAT, inspired by the HFGN model, which leverages graph neural networks and graph attention mechanisms to tackle this issue. The proposed framework constructs a three-tier hierarchical graph of users, outfits, and items, integrating visual and textual features to simultaneously model outfit compatibility and user preferences. A graph attention mechanism dynamically weights node importance during representation propagation, enabling the capture of key interactions and generating precise representations for both user preferences and outfit compatibility. Evaluated on the POG dataset, FGAT outperforms baseline models such as HFGN, achieving improved results in precision, HR, recall, NDCG, and accuracy.These results demonstrate that combining multimodal visual-textual features with a hierarchical graph structure and attention mechanisms significantly enhances the accuracy and efficiency of personalized fashion recommendation systems.

Problem

• Addresses outfit compatibility and personalized recommendations simultaneously
• Models complex interactions between items and user preferences
• Enhances accuracy of fashion recommendation systems

Innovation

• Hybrid-Hierarchical Fashion Graph Attention Network
• Three-tier hierarchical graph integration
• Dynamic graph attention weighting mechanism