Topology-Driven Attribute Recovery for Attribute Missing Graph Learning in Social Internet of Things
This addresses a common issue in graph learning for SIoT applications, offering a robust solution for handling incomplete data, though it appears incremental as it builds on existing graph learning methods.
The paper tackles the problem of missing attributes in Attribute Missing Graphs (AMGs) within the Social Internet of Things by proposing the Topology-Driven Attribute Recovery (TDAR) framework, which significantly outperforms state-of-the-art methods in attribute reconstruction and downstream tasks.
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.