Adaptive Dual Prompting: Hierarchical Debiasing for Fairness-aware Graph Neural Networks

• URL: http://arxiv.org/abs/2510.23469v1
• Date: Mon, 27 Oct 2025 16:07:36 GMT
• Title: Adaptive Dual Prompting: Hierarchical Debiasing for Fairness-aware Graph Neural Networks
• Authors: Yuhan Yang, Xingbo Fu, Jundong Li,
• Abstract summary: We propose an Adaptive Dual Prompting (ADPrompt) framework that enhances fairness for adapting pre-trained GNN models to downstream tasks.<n>We conduct extensive experiments on four datasets with four pre-training strategies to evaluate the performance of ADPrompt.
• Score: 48.53089517358632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, pre-training Graph Neural Networks (GNNs) through self-supervised learning on unlabeled graph data has emerged as a widely adopted paradigm in graph learning. Although the paradigm is effective for pre-training powerful GNN models, the objective gap often exists between pre-training and downstream tasks. To bridge this gap, graph prompting adapts pre-trained GNN models to specific downstream tasks with extra learnable prompts while keeping the pre-trained GNN models frozen. As recent graph prompting methods largely focus on enhancing model utility on downstream tasks, they often overlook fairness concerns when designing prompts for adaptation. In fact, pre-trained GNN models will produce discriminative node representations across demographic subgroups, as downstream graph data inherently contains biases in both node attributes and graph structures. To address this issue, we propose an Adaptive Dual Prompting (ADPrompt) framework that enhances fairness for adapting pre-trained GNN models to downstream tasks. To mitigate attribute bias, we design an Adaptive Feature Rectification module that learns customized attribute prompts to suppress sensitive information at the input layer, reducing bias at the source. Afterward, we propose an Adaptive Message Calibration module that generates structure prompts at each layer, which adjust the message from neighboring nodes to enable dynamic and soft calibration of the information flow. Finally, ADPrompt jointly optimizes the two prompting modules to adapt the pre-trained GNN while enhancing fairness. We conduct extensive experiments on four datasets with four pre-training strategies to evaluate the performance of ADPrompt. The results demonstrate that our proposed ADPrompt outperforms seven baseline methods on node classification tasks.

Related papers

• Unsupervised Prompting for Graph Neural Networks [3.2752005091619076]
  We introduce a challenging problem setup to evaluate GNN prompting methods.<n>We propose a fully unsupervised prompting method based on consistency regularization through pseudo-labeling.<n>Our unsupervised approach outperforms the state-of-the-art prompting methods that have access to labels.
  arXiv  Detail & Related papers  (2025-05-22T17:03:20Z)
• Edge Prompt Tuning for Graph Neural Networks [40.62424370491229]
  We propose EdgePrompt, a simple yet effective graph prompt tuning method from the perspective of edges.<n>Our method is compatible with prevalent GNN architectures pre-trained under various pre-training strategies.
  arXiv  Detail & Related papers  (2025-03-02T06:07:54Z)
• A Unified Graph Selective Prompt Learning for Graph Neural Networks [20.595782116049428]
  Graph Prompt Feature (GPF) has achieved remarkable success in adapting pre-trained models for Graph Neural Networks (GNNs) We propose a new unified Graph Selective Prompt Feature learning (GSPF) for GNN fine-tuning.
  arXiv  Detail & Related papers  (2024-06-15T04:36:40Z)
• GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels [81.93520935479984]
  We study a new problem, GNN model evaluation, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs. We propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference. Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model.
  arXiv  Detail & Related papers  (2023-10-23T05:51:59Z)
• Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias [72.33336385797944]
  We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias.<n>We show that LD significantly outperforms state-of-the-art methods on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2023-09-26T13:09:43Z)
• Universal Prompt Tuning for Graph Neural Networks [10.250964386142819]
  We introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy. GPF operates on the input graph's feature space and can theoretically achieve an equivalent effect to any form of prompting function. Our method significantly outperforms existing specialized prompt-based tuning methods when applied to models utilizing the pre-training strategy they specialize in.
  arXiv  Detail & Related papers  (2022-09-30T05:19:27Z)
• Analyzing the Effect of Sampling in GNNs on Individual Fairness [79.28449844690566]
  Graph neural network (GNN) based methods have saturated the field of recommender systems. We extend an existing method for promoting individual fairness on graphs to support mini-batch, or sub-sample based, training of a GNN. We show that mini-batch training facilitate individual fairness promotion by allowing for local nuance to guide the process of fairness promotion in representation learning.
  arXiv  Detail & Related papers  (2022-09-08T16:20:25Z)
• MentorGNN: Deriving Curriculum for Pre-Training GNNs [61.97574489259085]
  We propose an end-to-end model named MentorGNN that aims to supervise the pre-training process of GNNs across graphs. We shed new light on the problem of domain adaption on relational data (i.e., graphs) by deriving a natural and interpretable upper bound on the generalization error of the pre-trained GNNs.
  arXiv  Detail & Related papers  (2022-08-21T15:12:08Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.