Mar 20, 2023 · In this paper, we design a fair graph filter that can be employed in a versatile manner for graph-based learning tasks.
Oct 22, 2023 · Our idea is to introduce predesigned graph filters within an ML pipeline to reduce a novel unsupervised bias measure, namely the correlation ...
The design of the proposed filter is based on a bias analysis and its optimality in mitigating bias compared to its fairness-agnostic counterpart is established ...
Jul 3, 2024 · The approach in [32] is to “edit” the input graph signal for fairness enhancement and does not focus on optimal filter design. Overall, our ...
Sep 7, 2024 · The design of the proposed filter is based on a bias analysis and its optimality in mitigating bias compared to its fairness-agnostic ...
Oct 22, 2024 · Our idea is to introduce predesigned graph filters within an ML pipeline to reduce a novel unsupervised bias measure, namely the correlation ...
We propose a fairness-aware graph contrastive learning framework named Tag-aware Graph Contrastive Learning (TAGCL).
Nov 5, 2024 · This paper examines the issue of fairness in the estimation of graphical models (GMs), particularly Gaussian, Covariance, and Ising models.
Jun 19, 2024 · A novel algorithm, FairGAT, which leverages a fairness-aware attention design, is developed based on the theoretical findings.