no code implementations • 6 Feb 2024 • O. Deniz Kose, Yanning Shen
Faced with the bias amplification in graph generation models that is brought to light in this work, we further propose a fair graph generation framework, FairWire, by leveraging our fair regularizer design in a generative model.
no code implementations • 22 Oct 2023 • O. Deniz Kose, Yanning Shen, Gonzalo Mateos
We show that the optimal design of said filters can be cast as a convex problem in the graph spectral domain.
no code implementations • 26 Mar 2023 • O. Deniz Kose, Yanning Shen
Although it is shown that the use of graph structures in learning results in the amplification of algorithmic bias, the influence of the attention design in GATs on algorithmic bias has not been investigated.
no code implementations • 20 Mar 2023 • O. Deniz Kose, Yanning Shen, Gonzalo Mateos
Graphs are mathematical tools that can be used to represent complex real-world systems, such as financial markets and social networks.
no code implementations • 20 May 2022 • O. Deniz Kose, Yanning Shen
In addition, it is empirically shown that the proposed framework leads to faster convergence compared to the naive baseline where no normalization is employed.
no code implementations • 21 Jan 2022 • O. Deniz Kose, Yanning Shen
Our analysis reveals that both nodal features and graph structure lead to bias in the obtained representations.