aiqbench analysis
This paper introduces ADPrompt, a fairness-aware framework that addresses the overlooked bias in existing graph prompting methods by simultaneously suppressing sensitive attribute information and regulating structural information propagation. By integrating adaptive feature rectification with layer-wise message calibration, the approach effectively mitigates demographic disparities in Graph Neural Networks while maintaining strong performance on benchmark datasets. The work highlights a critical shift in the field toward balancing model efficacy with ethical considerations regarding attribute and structural bias in pre-trained GNNs.
Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias
arXiv:2510.23469v2 Announce Type: replace Abstract: Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs). However, an objective gap often remains between pre-training objectives and downstream tasks. To bridge this gap, graph prompting methods adapt frozen pre-trained GNNs to specific downstream tasks through learnable prompts. Despite its effectiveness, most existing graph prompting methods primarily focus on improving model performance and largely overlook fairness concerns. As downstream graph data inherently contains biases in both node attributes and graph structures, pre-trained GNNs may produce representations that differ across demographic subgroups. To address this limitation, we propose Adaptive Dual Prompting (ADPrompt), a fairness-aware graph prompting framework for adapting pre-trained GNNs. ADPrompt incorporates two complementary components: Adaptive Feature Rectification, which learns personalized attribute prompts to suppress sensitive information at the input level, and Adaptive Message Calibration, which introduces layer-wise structure prompts to dynamically regulate information propagation from neighboring nodes. By jointly optimizing these two modules, ADPrompt adapts the pre-trained GNN while mitigating both attribute-level and structural bias. Experiments on four benchmark datasets with multiple pre-training strategies demonstrate that ADPrompt consistently outperforms seven competitive baselines in node classification tasks.
Abstract:Self-supervised pre-training on unlabeled graph data has become a common paradigm for Graph Neural Networks (GNNs). However, an objective gap often remains between pre-training objectives and downstream tasks. To bridge this gap, graph prompting methods adapt frozen pre-trained GNNs to specific downstream tasks through learnable prompts. Despite its effectiveness, most existing graph prompting methods primarily focus on improving model performance and largely overlook fairness concerns. As downstream graph data inherently contains biases in both node attributes and graph structures, pre-trained GNNs may produce representations that differ across demographic subgroups. To address this limitation, we propose Adaptive Dual Prompting (ADPrompt), a fairness-aware graph prompting framework for adapting pre-trained GNNs. ADPrompt incorporates two complementary components: Adaptive Feature Rectification, which learns personalized attribute prompts to suppress sensitive information at the input level, and Adaptive Message Calibration, which introduces layer-wise structure prompts to dynamically regulate information propagation from neighboring nodes. By jointly optimizing these two modules, ADPrompt adapts the pre-trained GNN while mitigating both attribute-level and structural bias. Experiments on four benchmark datasets with multiple pre-training strategies demonstrate that ADPrompt consistently outperforms seven competitive baselines in node classification tasks.
Machine Learning (cs.LG)
arXiv:2510.23469 [cs.LG]
(or arXiv:2510.23469v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2510.23469 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 277 words
Related coverage
The current bottleneck is political will, not research
AI Alignment Forum · Jul 11, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · Sep 13, 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026