P
Prasanna Sattigeri
Researcher at IBM
Publications - 111
Citations - 3104
Prasanna Sattigeri is an academic researcher from IBM. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 21, co-authored 95 publications receiving 1842 citations. Previous affiliations of Prasanna Sattigeri include Arizona State University & California State University, Long Beach.
Papers
More filters
Posted Content
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Rachel K. E. Bellamy,Kuntal Dey,Michael Hind,Samuel C. Hoffman,Stephanie Houde,Kalapriya Kannan,Pranay Lohia,Jacquelyn A. Martino,Sameep Mehta,Aleksandra Mojsilovic,Seema Nagar,Karthikeyan Natesan Ramamurthy,John T. Richards,Diptikalyan Saha,Prasanna Sattigeri,Moninder Singh,Kush R. Varshney,Yunfeng Zhang +17 more
TL;DR: A new open source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license to help facilitate the transition of fairness research algorithms to use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.
Journal ArticleDOI
AI Fairness 360: An extensible toolkit for detecting and mitigating algorithmic bias
Rachel K. E. Bellamy,Kuntal Dey,Michael Hind,Samuel C. Hoffman,Stephanie Houde,Kalapriya Kannan,Pranay Lohia,Jacquelyn A. Martino,Shalin Mehta,Aleksandra Mojsilovic,Seema Nagar,K. Natesan Ramamurthy,John T. Richards,Debanjan Saha,Prasanna Sattigeri,Moninder Singh,Kush R. Varshney,Yunfeng Zhang +17 more
TL;DR: A new open-source Python toolkit for algorithmic fairness, AI Fairness 360 (AIF360), released under an Apache v2.0 license, to help facilitate the transition of fairness research algorithms for use in an industrial setting and to provide a common framework for fairness researchers to share and evaluate algorithms.
Proceedings Article
Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
TL;DR: The authors proposed a variational inference based approach to infer disentangled latent factors, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks, interpretability, etc.
Posted Content
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Vijay Arya,Rachel K. E. Bellamy,Pin-Yu Chen,Amit Dhurandhar,Michael Hind,Samuel C. Hoffman,Stephanie Houde,Q. Vera Liao,Ronny Luss,Aleksandra Mojsilovic,Sami Mourad,Pablo Pedemonte,Ramya Raghavendra,John T. Richards,Prasanna Sattigeri,Karthikeyan Shanmugam,Moninder Singh,Kush R. Varshney,Dennis Wei,Yunfeng Zhang +19 more
TL;DR: This work introduces AI Explainability 360, an open-source software toolkit featuring eight diverse and state-of-the-art explainability methods and two evaluation metrics, and provides a taxonomy to help entities requiring explanations to navigate the space of explanation methods.
Journal ArticleDOI
Fairness GAN: Generating datasets with fairness properties using a generative adversarial network
TL;DR: In this paper, the authors introduce the Fairness GAN, an approach for generating a dataset that is plausibly similar to a given multimedia dataset, but is more fair with respect to protected attributes in decision making.