| AI Fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias RKE Bellamy, K Dey, M Hind, SC Hoffman, S Houde, K Kannan, P Lohia, ... IBM Journal of Research and Development, 2018 | 743* | 2018 |
| Optimized pre-processing for discrimination prevention F Calmon, D Wei, B Vinzamuri, K Natesan Ramamurthy, KR Varshney Advances in neural information processing systems 30, 2017 | 592 | 2017 |
| Sparsity-driven synthetic aperture radar imaging: Reconstruction, autofocusing, moving targets, and compressed sensing M Çetin, I Stojanović, NÖ Önhon, K Varshney, S Samadi, WC Karl, ... IEEE Signal Processing Magazine 31 (4), 27-40, 2014 | 262 | 2014 |
| One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques V Arya, RKE Bellamy, PY Chen, A Dhurandhar, M Hind, SC Hoffman, ... arXiv preprint arXiv:1909.03012, 2019 | 257 | 2019 |
| Method for market risk assessment for healthcare applications S Mahatma, A Mojsilovic, KN Ramamurthy, KR Varshney, D Wei, ... US Patent App. 14/699,482, 2016 | 253 | 2016 |
| FactSheets: Increasing trust in AI services through supplier's declarations of conformity M Arnold, RKE Bellamy, M Hind, S Houde, S Mehta, A Mojsilović, R Nair, ... IBM Journal of Research and Development 63 (4/5), 6: 1-6: 13, 2019 | 243 | 2019 |
| Sparse representation in structured dictionaries with application to synthetic aperture radar KR Varshney, M Çetin, JW Fisher, AS Willsky IEEE Transactions on Signal Processing 56 (8), 3548-3561, 2008 | 204 | 2008 |
| On the safety of machine learning: Cyber-physical systems, decision sciences, and data products KR Varshney, H Alemzadeh Big data 5 (3), 246-255, 2017 | 170 | 2017 |
| Invariant risk minimization games K Ahuja, K Shanmugam, K Varshney, A Dhurandhar International Conference on Machine Learning, 145-155, 2020 | 128 | 2020 |
| Fairness GAN: Generating datasets with fairness properties using a generative adversarial network P Sattigeri, SC Hoffman, V Chenthamarakshan, KR Varshney IBM Journal of Research and Development 63 (4/5), 3: 1-3: 9, 2019 | 126* | 2019 |
| The effect of extremist violence on hateful speech online A Olteanu, C Castillo, J Boy, K Varshney Proceedings of the international AAAI conference on web and social media 12 (1), 2018 | 119 | 2018 |
| Engineering safety in machine learning KR Varshney 2016 Information Theory and Applications Workshop (ITA), 1-5, 2016 | 117 | 2016 |
| Exact rule learning via boolean compressed sensing D Malioutov, K Varshney International conference on machine learning, 765-773, 2013 | 91 | 2013 |
| TED: Teaching AI to explain its decisions M Hind, D Wei, M Campbell, NCF Codella, A Dhurandhar, A Mojsilović, ... Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, 123-129, 2019 | 85 | 2019 |
| A big data approach to computational creativity: The curious case of Chef Watson LR Varshney, F Pinel, KR Varshney, D Bhattacharjya, A Schörgendorfer, ... IBM Journal of Research and Development 63 (1), 7: 1-7: 18, 2019 | 81* | 2019 |
| Collaborative kalman filtering for dynamic matrix factorization JZ Sun, D Parthasarathy, KR Varshney IEEE Transactions on Signal Processing 62 (14), 3499-3509, 2014 | 81 | 2014 |
| Teaching AI agents ethical values using reinforcement learning and policy orchestration R Noothigattu, D Bouneffouf, N Mattei, R Chandra, P Madan, ... IBM Journal of Research and Development 63 (4/5), 2: 1-2: 9, 2019 | 77* | 2019 |
| Bias mitigation post-processing for individual and group fairness PK Lohia, KN Ramamurthy, M Bhide, D Saha, KR Varshney, R Puri Icassp 2019-2019 ieee international conference on acoustics, speech and …, 2019 | 65 | 2019 |
| Is there a trade-off between fairness and accuracy? a perspective using mismatched hypothesis testing S Dutta, D Wei, H Yueksel, PY Chen, S Liu, K Varshney International Conference on Machine Learning, 2803-2813, 2020 | 64* | 2020 |
| Dynamic matrix factorization: A state space approach JZ Sun, KR Varshney, K Subbian 2012 IEEE International Conference on Acoustics, Speech and Signal …, 2012 | 62 | 2012 |
Aleksandra MojsilovicIBM ResearchVerified email at us.ibm.com
