AttriReBoost: A Gradient-Free Propagation Optimization Method for Cold Start Mitigation in Attribute Missing Graphs

2025-01-01

AI Summary

Graph Neural Networks (GNNs) suffer from propagation bias in attributed graphs with missing node attributes, primarily due to cold-start issues for low-degree nodes and attribute reset during message passing. Method: This paper proposes a gradient-free feature propagation optimization framework. It redefines propagation boundary conditions to mitigate information sparsity, introduces learnable virtual edges to enhance global graph connectivity, and integrates graph signal processing for iterative attribute reconstruction. Contribution/Results: Theoretical analysis guarantees convergence, eliminating reliance on gradient-based optimization and local neighborhood aggregation—key limitations of prior methods. Extensive experiments on multiple real-world datasets show an average accuracy improvement of 5.11%. The framework processes a 2.49-million-node graph in just 16 seconds on a single GPU, demonstrating substantial gains in both computational efficiency and robustness to attribute incompleteness.

Technology Category

Machine Learning: Graph-based Machine LearningSearch and Optimization: Learning to SearchData Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSocial Networks and Social Media: Influence propagation, information diffusion, and the prediction on networksSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Missing attribute issues are prevalent in the graph learning, leading to biased outcomes in Graph Neural Networks (GNNs). Existing methods that rely on feature propagation are prone to cold start problem, particularly when dealing with attribute resetting and low-degree nodes, which hinder effective propagation and convergence. To address these challenges, we propose AttriReBoost (ARB), a novel method that incorporates propagation-based method to mitigate cold start problems in attribute-missing graphs. ARB enhances global feature propagation by redefining initial boundary conditions and strategically integrating virtual edges, thereby improving node connectivity and ensuring more stable and efficient convergence. This method facilitates gradient-free attribute reconstruction with lower computational overhead. The proposed method is theoretically grounded, with its convergence rigorously established. Extensive experiments on several real-world benchmark datasets demonstrate the effectiveness of ARB, achieving an average accuracy improvement of 5.11% over state-of-the-art methods. Additionally, ARB exhibits remarkable computational efficiency, processing a large-scale graph with 2.49 million nodes in just 16 seconds on a single GPU. Our code is available at https://github.com/limengran98/ARB.

Problem

• Graph Neural Networks
• Incomplete Information
• Data Sparsity

Innovation

• AttriReBoost
• Graph Neural Networks
• Virtual Connections