Feb 19, 2024 · We propose a novel adapter-tuning framework that endows pre-trained graph models with provable fairness (called GraphPAR).
scholar.google.com › citations
May 13, 2024 · Pre-trained graph models (PGMs) aim to capture transferable inherent structural properties and apply them to different downstream tasks.
Pre-trained graph models (PGMs) aim to capture transferable inher- ent structural properties and apply them to different downstream.
To overcome these limitations, we propose a novel framework that endows pre-trained graph models with provable fairness (called GraphPAR). GraphPAR freezes the ...
Feb 20, 2024 · Extensive experiments on different real-world datasets demonstrate that GraphPAR achieves state-of-the-art prediction performance and fairness.
A novel adapter-tuning framework that endows pre-trained Graph models with Provable fAiRness (called GraphPAR), which freezes the parameters of PGMs and ...
A PyTorch implementation of "Endowing Pre-trained Graph Models with Provable Fairness" (WWW 2024) - BUPT-GAMMA/GraphPAR.
Mar 20, 2024 · "Endowing Pre-trained Graph Models with Provable Fairness Zhang Zhong Jian, Mengmei Zhang, Yue Yu, Cheng Yang, Jiawei Liu, Chuan Shi"
ISEDA, 2024. [C5] Endowing Pre-trained Graph Models with Provable Fairness. Zhongjian Zhang, Mengmei Zhang, Yue Yu, Cheng Yang, Jiawei Liu, ...
Co-authors ; Endowing Pre-trained Graph Models with Provable Fairness. Z Zhang, M Zhang, Y Yu, C Yang, J Liu, C Shi. Proceedings of the ACM on Web Conference ...