Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Things

2025-01-17

AI Summary

To address the challenge of modeling attribute-missing graphs (AMGs) in social Internet-of-Things (IoT), this paper proposes Topology-Driven Attribute Recovery (TDAR), a robust framework that eliminates reliance on complete node attributes. TDAR introduces a novel dynamic weighted message-passing mechanism, jointly leveraging native graph topology for initial attribute pre-filling and embedding-space homophily regularization for adaptive weight refinement within a GNN architecture; a homophily constraint is further imposed to suppress noise propagation. This enables end-to-end, topology-aware attribute recovery on AMGs. Extensive experiments on multiple public datasets demonstrate that TDAR reduces attribute reconstruction error by up to 32.7% over state-of-the-art methods, while improving average accuracy on downstream node classification and link prediction tasks by 9.4%.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• 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
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

With the advancement of information technology, the Social Internet of Things (SIoT) has fostered the integration of physical devices and social networks, deepening the study of complex interaction patterns. Text Attribute Graphs (TAGs) capture both topological structures and semantic attributes, enhancing the analysis of complex interactions within the SIoT. However, existing graph learning methods are typically designed for complete attributed graphs, and the common issue of missing attributes in Attribute Missing Graphs (AMGs) increases the difficulty of analysis tasks. To address this, we propose the Topology-Driven Attribute Recovery (TDAR) framework, which leverages topological data for AMG learning. TDAR introduces an improved pre-filling method for initial attribute recovery using native graph topology. Additionally, it dynamically adjusts propagation weights and incorporates homogeneity strategies within the embedding space to suit AMGs' unique topological structures, effectively reducing noise during information propagation. Extensive experiments on public datasets demonstrate that TDAR significantly outperforms state-of-the-art methods in attribute reconstruction and downstream tasks, offering a robust solution to the challenges posed by AMGs. The code is available at https://github.com/limengran98/TDAR.

Problem

• Social Internet of Things
• Attribute Information Missing
• Complex Interaction

Innovation

• Topological-based Data Recovery
• Social Internet of Things
• Graph Attribute Reconstruction