Research map / Graph learning / Graph self-supervised learning

Adaptive Feature Propagation for Attribute-Missing Graph Clustering

NeurIPS 2026 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes an adaptive feature propagation method for attribute-missing graph clustering that accounts for unreliable nodes during attribute imputation.

Problem

Attribute-missing graph clustering (AMGC), where only some nodes have complete attributes and others are partially missing, and existing feature propagation methods assume uniform node contributions, letting unreliable nodes degrade imputation.

Approach

Moves beyond uniform feature propagation by adaptively weighting nodes according to reliability so that unreliable nodes contribute less to recovering missing attributes before clustering.

Experimental setup

Builds on: feature propagation

Closest papers by meaning

• Attribute-Missing Graph Clustering Network (AAAI 2024 · similarity 0.93)
• Attribute-Missing Multi-view Graph Clustering (CVPR 2025 · similarity 0.91)
• Scalable Attribute-Missing Graph Clustering via Neighborhood Differentiation (ICML 2025 · similarity 0.89)
• Propagate and Inject: Revisiting Propagation-Based Feature Imputation for Graphs with Partially Observed Features (ICML 2025 · similarity 0.89)
• Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering (NeurIPS 2025 · similarity 0.88)
• THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.87)