Research map / Graph learning / GNN architectures

Structural Fairness-aware Active Learning for Graph Neural Networks

ICLR 2024 · Graph learning › GNN architectures · approach: Graph structure learning

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 a fairness-aware active learning method for selecting labeled nodes to train GNNs for semi-supervised node classification.

Problem

GNNs for semi-supervised node classification depend on high-quality labeled nodes, which are often scarce; active learning on graphs faces unique challenges, including structural bias in node selection.

Approach

Active learning for GNNs that accounts for structural fairness when choosing which nodes to label, rather than selecting purely on data features; the abstract is truncated so the specific mechanism is not stated.

Closest papers by meaning

• Chasing Fairness in Graphs: A GNN Architecture Perspective (AAAI 2024 · similarity 0.90)
• On Generalized Degree Fairness in Graph Neural Networks (AAAI 2023 · similarity 0.89)
• Fair Graph Learning with Limited Sensitive Attribute Information (AAAI 2026 · similarity 0.89)
• Robust Offline Active Learning on Graphs (NeurIPS 2024 · similarity 0.89)
• Fair Graph U-Net: A Fair Graph Learning Framework Integrating Group and Individual Awareness (AAAI 2025 · similarity 0.88)
• On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks (ICML 2025 · similarity 0.88)