FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization

2025-10-13

AI Summary

To address the practical challenge of missing node features in real-world graph data, this paper proposes an end-to-end node embedding method that jointly optimizes structural preservation, label regularization, and semi-supervised propagation. The method introduces three key innovations: (1) a scalable modularity approximation for efficient unsupervised structural modeling; (2) an intra-class variance minimization constraint to enhance class discriminability; and (3) an attention-weighted random-walk-based label propagation mechanism that integrates topological context with class-aware information. This unified iterative framework ensures high-quality embeddings while significantly reducing computational overhead. Extensive experiments on multiple standard benchmarks demonstrate that the proposed approach achieves or surpasses state-of-the-art classification accuracy, with strong efficiency and scalability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Graph-based learning is a cornerstone for analyzing structured data, with node classification as a central task. However, in many real-world graphs, nodes lack informative feature vectors, leaving only neighborhood connectivity and class labels as available signals. In such cases, effective classification hinges on learning node embeddings that capture structural roles and topological context. We introduce a fast semi-supervised embedding framework that jointly optimizes three complementary objectives: (i) unsupervised structure preservation via scalable modularity approximation, (ii) supervised regularization to minimize intra-class variance among labeled nodes, and (iii) semi-supervised propagation that refines unlabeled nodes through random-walk-based label spreading with attention-weighted similarity. These components are unified into a single iterative optimization scheme, yielding high-quality node embeddings. On standard benchmarks, our method consistently achieves classification accuracy at par with or superior to state-of-the-art approaches, while requiring significantly less computational cost.

Problem

• Learning node embeddings from structural connectivity and limited labels
• Jointly optimizing structure preservation and class-aware regularization
• Achieving high accuracy with reduced computational cost in classification

Innovation

• Jointly optimizes structure preservation and label regularization
• Uses semi-supervised propagation with attention-weighted similarity
• Unifies three objectives in single iterative optimization scheme