no code implementations • 18 May 2023 • Arghya Datta, Subhrangshu Nandi, Jingcheng Xu, Greg Ver Steeg, He Xie, Anoop Kumar, Aram Galstyan
We formulate the model stability problem by studying how the predictions of a model change, even when it is retrained on the same data, as a consequence of stochasticity in the training process.
no code implementations • 1 Jun 2021 • Arghya Datta, S. Joshua Swamidass
This problem is aggravated across many domains where datasets are class imbalanced, with a minority class far rarer than the majority class.
1 code implementation • 29 Oct 2018 • Matthew K. Matlock, Arghya Datta, Na Le Dang, Kevin Jiang, S. Joshua Swamidass
Some of these algorithms depend on propagating information between distant nodes in a graph.