RHEA: Reliability-Harmonized Reconstruction and Assignment for Robust Multimodal-Attributed Graph Clustering

2026-08-01

AI Summary

This work addresses the significant performance degradation of multimodal attributed graph clustering under attribute noise or missing data, primarily caused by existing methods overlooking node-level variations in modality reliability. To tackle this issue, we propose the RHEA framework, which introduces a novel node-level modality reliability estimation mechanism based on graph neighborhood consensus. This mechanism guides the reconstruction of unreliable or missing modalities and enables reliability-aware adaptive multimodal fusion. Furthermore, RHEA integrates reconstruction confidence into an optimal transport-based clustering objective and incorporates neighborhood consensus assignment distillation to enhance clustering consistency. Extensive experiments demonstrate that RHEA consistently outperforms the strongest baselines across four benchmark graphs under five types of attribute perturbations, with greater Normalized Mutual Information (NMI) gains observed as attribute quality deteriorates.

Abstract

Multimodal-attributed graphs (MAGs), whose nodes carry heterogeneous attributes such as text and images over a relational structure, have become a fundamental substrate for label-free entity grouping tasks, including community discovery and product segmentation. Existing MAG clustering methods effectively integrate complementary modalities when attributes are clean and complete, but degrade substantially under noisy or missing attributes because they implicitly assume equal modality reliability across all nodes. In practice, modality reliability is inherently node-specific: images may be corrupted or absent, while textual descriptions are incomplete or noisy. We argue that, under attribute homophily, graph neighborhoods naturally provide supervision-free evidence for estimating node-specific modality reliability. Based on this insight, we propose RHEA, a reliability-aware framework for MAG clustering that estimates node-specific modality reliability from neighborhood consensus and propagates this signal throughout the clustering pipeline. RHEA reconstructs unreliable or missing modalities from graph neighborhoods, adaptively weights modalities during reliability-aware fusion, and performs topology-aware optimal transport clustering with reliability-aware transport assignment and neighbor-consensus assignment distillation. Furthermore, the confidence of reconstructed representations is incorporated into the clustering objective, allowing uncertain reconstructions to contribute proportionally during optimization. Experiments on four MAG benchmarks under five attribute conditions show that RHEA consistently outperforms the strongest baseline, with NMI gains increasing as attribute quality deteriorates.

Problem

• multimodal-attributed graphs
• modality reliability
• noisy attributes
• missing attributes
• graph clustering

Innovation

• modality reliability
• neighborhood consensus
• reliability-aware fusion
• optimal transport clustering
• multimodal-attributed graph