no code implementations • 30 May 2020 • Yue Zhang, David Defazio, Arti Ramesh
In this work, we develop RelEx, a model-agnostic relational explainer to explain black-box relational models with only access to the outputs of the black-box.
no code implementations • 21 Feb 2020 • Yue Zhang, Arti Ramesh
The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years.
no code implementations • 21 Feb 2020 • Yue Zhang, Arti Ramesh
Further, our model is capable of learning latent characteristics in real-world networks via meaningful latent variables encoded as a complex combination of observed features and membership distributions.
no code implementations • 16 Dec 2019 • David DeFazio, Arti Ramesh
Along with the advent of deep neural networks came various methods of exploitation, such as fooling the classifier or contaminating its training data.