no code implementations • 30 May 2024 • Hyo Jin Do, Rachel Ostrand, Justin D. Weisz, Casey Dugan, Prasanna Sattigeri, Dennis Wei, Keerthiram Murugesan, Werner Geyer
To address this issue, we conducted a scenario-based study (N=104) to systematically compare the impact of various design strategies for communicating factuality and source attribution on participants' ratings of trust, preferences, and ease in validating response accuracy.
1 code implementation • 3 Apr 2024 • Hussein Mozannar, Valerie Chen, Mohammed Alsobay, Subhro Das, Sebastian Zhao, Dennis Wei, Manish Nagireddy, Prasanna Sattigeri, Ameet Talwalkar, David Sontag
Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests.
no code implementations • 22 Mar 2024 • Erik Miehling, Manish Nagireddy, Prasanna Sattigeri, Elizabeth M. Daly, David Piorkowski, John T. Richards
Modern language models, while sophisticated, exhibit some inherent shortcomings, particularly in conversational settings.
no code implementations • 21 Mar 2024 • Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt, Ronny Luss, Amit Dhurandhar, Manish Nagireddy, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Werner Geyer, Soumya Ghosh
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
no code implementations • 19 Mar 2024 • Pierre Dognin, Jesus Rios, Ronny Luss, Inkit Padhi, Matthew D Riemer, Miao Liu, Prasanna Sattigeri, Manish Nagireddy, Kush R. Varshney, Djallel Bouneffouf
Developing value-aligned AI agents is a complex undertaking and an ongoing challenge in the field of AI.
no code implementations • 9 Mar 2024 • Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
no code implementations • 1 Mar 2024 • Zirui Yan, Dennis Wei, Dmitriy Katz-Rogozhnikov, Prasanna Sattigeri, Ali Tajer
First, the structural causal models (SCMs) are assumed to be unknown and drawn arbitrarily from a general class $\mathcal{F}$ of Lipschitz-continuous functions.
no code implementations • 20 Feb 2024 • Maohao Shen, Subhro Das, Kristjan Greenewald, Prasanna Sattigeri, Gregory Wornell, Soumya Ghosh
Addressing these challenges, we propose THERMOMETER, a calibration approach tailored to LLMs.
no code implementations • 9 Feb 2024 • J. Jon Ryu, Maohao Shen, Soumya Ghosh, Yuheng Bu, Prasanna Sattigeri, Subhro Das, Gregory W. Wornell
This paper explores a modern predictive uncertainty estimation approach, called evidential deep learning (EDL), in which a single neural network model is trained to learn a meta distribution over the predictive distribution by minimizing a specific objective function.
1 code implementation • NeurIPS 2023 • Hussein Mozannar, Jimin J Lee, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag
In this work, we propose to learn rules, grounded in data regions and described in natural language, that illustrate how the human should collaborate with the AI.
no code implementations • 4 Oct 2023 • Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.
1 code implementation • 30 Apr 2023 • Maohao Shen, Soumya Ghosh, Prasanna Sattigeri, Subhro Das, Yuheng Bu, Gregory Wornell
Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs.
no code implementations • 16 Feb 2023 • Abhin Shah, Maohao Shen, Jongha Jon Ryu, Subhro Das, Prasanna Sattigeri, Yuheng Bu, Gregory W. Wornell
To overcome this limitation, we propose a bootstrap-based algorithm that achieves the target level of fairness despite the uncertainty in sensitive attributes.
1 code implementation • 15 Jan 2023 • Hussein Mozannar, Hunter Lang, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag
We show that prior approaches can fail to find a human-AI system with low misclassification error even when there exists a linear classifier and rejector that have zero error (the realizable setting).
1 code implementation • 14 Dec 2022 • Maohao Shen, Yuheng Bu, Prasanna Sattigeri, Soumya Ghosh, Subhro Das, Gregory Wornell
It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures.
no code implementations • 13 Dec 2022 • Prasanna Sattigeri, Soumya Ghosh, Inkit Padhi, Pierre Dognin, Kush R. Varshney
The dropping of training points is done in principle, but in practice does not require the model to be refit.
no code implementations • 13 Oct 2022 • Sourya Basu, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Vijil Chenthamarakshan, Kush R. Varshney, Lav R. Varshney, Payel Das
We also provide a novel group-theoretic definition for fairness in NLG.
1 code implementation • 26 Aug 2022 • Burak Varici, Karthikeyan Shanmugam, Prasanna Sattigeri, Ali Tajer
Two linear mechanisms, one soft intervention and one observational, are assumed for each node, giving rise to $2^N$ possible interventions.
1 code implementation • 8 Aug 2022 • Paula Harder, Alex Hernandez-Garcia, Venkatesh Ramesh, Qidong Yang, Prasanna Sattigeri, Daniela Szwarcman, Campbell Watson, David Rolnick
In order to conserve physical quantities, here we introduce methods that guarantee statistical constraints are satisfied by a deep learning downscaling model, while also improving their performance according to traditional metrics.
no code implementations • 14 Jul 2022 • Samuel C. Hoffman, Kahini Wadhawan, Payel Das, Prasanna Sattigeri, Karthikeyan Shanmugam
In this work, we provide a simple algorithm that relies on perturbation experiments on latent codes of a pre-trained generative autoencoder to uncover a causal graph that is implied by the generative model.
no code implementations • Entropy 2022 • Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory W. Wornell, Leonid Karlinsky and Rogerio Schmidt Feris
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant.
1 code implementation • NeurIPS 2021 • Burak Varici, Karthikeyan Shanmugam, Prasanna Sattigeri, Ali Tajer
This paper considers the problem of estimating the unknown intervention targets in a causal directed acyclic graph from observational and interventional data.
1 code implementation • 28 Oct 2021 • Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee, Subhro Das, Rameswar Panda, Prasanna Sattigeri, Gregory W. Wornell
Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient.
no code implementations • 24 Sep 2021 • 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 Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
1 code implementation • 2 Jun 2021 • Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy, Jiri Navratil, Prasanna Sattigeri, Kush R. Varshney, Yunfeng Zhang
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.
1 code implementation • 1 Jun 2021 • Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh, Prasanna Sattigeri
Accurate quantification of model uncertainty has long been recognized as a fundamental requirement for trusted AI.
1 code implementation • ICCV 2021 • Assaf Arbelle, Sivan Doveh, Amit Alfassy, Joseph Shtok, Guy Lev, Eli Schwartz, Hilde Kuehne, Hila Barak Levi, Prasanna Sattigeri, Rameswar Panda, Chun-Fu Chen, Alex Bronstein, Kate Saenko, Shimon Ullman, Raja Giryes, Rogerio Feris, Leonid Karlinsky
In this work, we focus on the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained detector.
Ranked #1 on Phrase Grounding on Visual Genome
no code implementations • ICLR 2021 • Yue Meng, Rameswar Panda, Chung-Ching Lin, Prasanna Sattigeri, Leonid Karlinsky, Kate Saenko, Aude Oliva, Rogerio Feris
Temporal modelling is the key for efficient video action recognition.
no code implementations • 1 Jan 2021 • Seungwook Han, Akash Srivastava, Cole Lincoln Hurwitz, Prasanna Sattigeri, David Daniel Cox
First, we generate images in low-frequency bands by training a sampler in the wavelet domain.
no code implementations • 30 Dec 2020 • Joshua Lee, Yuheng Bu, Prasanna Sattigeri, Rameswar Panda, Gregory Wornell, Leonid Karlinsky, Rogerio Feris
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant.
no code implementations • 15 Nov 2020 • Umang Bhatt, Javier Antorán, Yunfeng Zhang, Q. Vera Liao, Prasanna Sattigeri, Riccardo Fogliato, Gabrielle Gauthier Melançon, Ranganath Krishnan, Jason Stanley, Omesh Tickoo, Lama Nachman, Rumi Chunara, Madhulika Srikumar, Adrian Weller, Alice Xiang
Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders.
no code implementations • 25 Oct 2020 • Akash Srivastava, Yamini Bansal, Yukun Ding, Cole Lincoln Hurwitz, Kai Xu, Bernhard Egger, Prasanna Sattigeri, Joshua B. Tenenbaum, Phuong Le, Arun Prakash R, Nengfeng Zhou, Joel Vaughan, Yaquan Wang, Anwesha Bhattacharyya, Kristjan Greenewald, David D. Cox, Dan Gutfreund
Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors.
no code implementations • 9 Sep 2020 • Seungwook Han, Akash Srivastava, Cole Hurwitz, Prasanna Sattigeri, David D. Cox
First, we generate images in low-frequency bands by training a sampler in the wavelet domain.
1 code implementation • NeurIPS 2020 • N. Joseph Tatro, Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai
Yet, current curve finding algorithms do not consider the influence of symmetry in the loss surface created by model weight permutations.
1 code implementation • ECCV 2020 • Yue Meng, Chung-Ching Lin, Rameswar Panda, Prasanna Sattigeri, Leonid Karlinsky, Aude Oliva, Kate Saenko, Rogerio Feris
Specifically, given a video frame, a policy network is used to decide what input resolution should be used for processing by the action recognition model, with the goal of improving both accuracy and efficiency.
1 code implementation • ECCV 2020 • Zhiqiang Tang, Yunhe Gao, Leonid Karlinsky, Prasanna Sattigeri, Rogerio Feris, Dimitris Metaxas
First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage.
no code implementations • 10 Jun 2020 • Sainyam Galhotra, Karthikeyan Shanmugam, Prasanna Sattigeri, Kush R. Varshney
In this work, we consider fairness in the integration component of data management, aiming to identify features that improve prediction without adding any bias to the dataset.
no code implementations • 27 Apr 2020 • Jayaraman J. Thiagarajan, Prasanna Sattigeri, Deepta Rajan, Bindya Venkatesh
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior.
1 code implementation • 15 Mar 2020 • Leonid Karlinsky, Joseph Shtok, Amit Alfassy, Moshe Lichtenstein, Sivan Harary, Eli Schwartz, Sivan Doveh, Prasanna Sattigeri, Rogerio Feris, Alexander Bronstein, Raja Giryes
Few-shot detection and classification have advanced significantly in recent years.
1 code implementation • ECCV 2020 • Moshe Lichtenstein, Prasanna Sattigeri, Rogerio Feris, Raja Giryes, Leonid Karlinsky
The field of Few-Shot Learning (FSL), or learning from very few (typically $1$ or $5$) examples per novel class (unseen during training), has received a lot of attention and significant performance advances in the recent literature.
no code implementations • 10 Feb 2020 • Bindya Venkatesh, Jayaraman J. Thiagarajan, Kowshik Thopalli, Prasanna Sattigeri
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled efficient inferencing.
no code implementations • ICLR 2020 • Akash Srivastava, Yamini Bansal, Yukun Ding, Bernhard Egger, Prasanna Sattigeri, Josh Tenenbaum, David D. Cox, Dan Gutfreund
In this work, we tackle a slightly more intricate scenario where the observations are generated from a conditional distribution of some known control variate and some latent noise variate.
no code implementations • NeurIPS 2019 • Joshua Lee, Prasanna Sattigeri, Gregory Wornell
However, for practical, privacy, or other reasons, in a variety of applications we may have no control over the individual source task training, nor access to source training samples.
no code implementations • 18 Nov 2019 • Shivashankar Subramanian, Ioana Baldini, Sushma Ravichandran, Dmitriy A. Katz-Rogozhnikov, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Kush R. Varshney, Annmarie Wang, Pradeep Mangalath, Laura B. Kleiman
More than 200 generic drugs approved by the U. S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer.
no code implementations • 29 Oct 2019 • Newton M. Kinyanjui, Timothy Odonga, Celia Cintas, Noel C. F. Codella, Rameswar Panda, Prasanna Sattigeri, Kush R. Varshney
We find that the majority of the data in the the two datasets have ITA values between 34. 5{\deg} and 48{\deg}, which are associated with lighter skin, and is consistent with under-representation of darker skinned populations in these datasets.
no code implementations • 25 Sep 2019 • N. Joseph Tatro, Pin-Yu Chen, Payel Das, Igor Melnyk, Prasanna Sattigeri, Rongjie Lai
Empirically, this initialization is critical for efficiently learning a simple, planar, low-loss curve between networks that successfully generalizes.
1 code implementation • 9 Sep 2019 • Jayaraman J. Thiagarajan, Bindya Venkatesh, Prasanna Sattigeri, Peer-Timo Bremer
With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties.
2 code implementations • 6 Sep 2019 • Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
2 code implementations • 29 May 2019 • Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Yunfeng Zhang, Karthikeyan Shanmugam, Chun-Chen Tu
As the application of deep neural networks proliferates in numerous areas such as medical imaging, video surveillance, and self driving cars, the need for explaining the decisions of these models has become a hot research topic, both at the global and local level.
no code implementations • 30 Nov 2018 • Vidya Muthukumar, Tejaswini Pedapati, Nalini Ratha, Prasanna Sattigeri, Chai-Wah Wu, Brian Kingsbury, Abhishek Kumar, Samuel Thomas, Aleksandra Mojsilovic, Kush R. Varshney
Recent work shows unequal performance of commercial face classification services in the gender classification task across intersectional groups defined by skin type and gender.
no code implementations • NeurIPS 2018 • Abhishek Kumar, Prasanna Sattigeri, Kahini Wadhawan, Leonid Karlinsky, Rogerio Feris, William T. Freeman, Gregory Wornell
Deep neural networks, trained with large amount of labeled data, can fail to generalize well when tested with examples from a \emph{target domain} whose distribution differs from the training data distribution, referred as the \emph{source domain}.
13 code implementations • 3 Oct 2018 • Rachel K. E. Bellamy, Kuntal Dey, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Kalapriya Kannan, Pranay Lohia, Jacquelyn Martino, Sameep Mehta, Aleksandra Mojsilovic, Seema Nagar, Karthikeyan Natesan Ramamurthy, John Richards, Diptikalyan Saha, Prasanna Sattigeri, Moninder Singh, Kush R. Varshney, Yunfeng Zhang
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
no code implementations • 20 Sep 2018 • Jayaraman J. Thiagarajan, Deepta Rajan, Prasanna Sattigeri
The hypothesis that computational models can be reliable enough to be adopted in prognosis and patient care is revolutionizing healthcare.
no code implementations • 24 May 2018 • Prasanna Sattigeri, Samuel C. Hoffman, Vijil Chenthamarakshan, Kush R. Varshney
In this paper, we 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 allocative decision making.
no code implementations • 15 Nov 2017 • Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Andreas Spanias
To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrom kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings.
2 code implementations • ICLR 2018 • Abhishek Kumar, Prasanna Sattigeri, Avinash Balakrishnan
Disentangled representations, 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.
no code implementations • NeurIPS 2017 • Abhishek Kumar, Prasanna Sattigeri, P. Thomas Fletcher
Semi-supervised learning methods using Generative Adversarial Networks (GANs) have shown promising empirical success recently.
no code implementations • 28 Dec 2016 • Huan Song, Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Andreas Spanias
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data.
no code implementations • 14 Dec 2016 • Jayaraman J. Thiagarajan, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy, Bhavya Kailkhura
In this paper, we propose the use of quantile analysis to obtain local scale estimates for neighborhood graph construction.
no code implementations • 22 Nov 2016 • Jayaraman J. Thiagarajan, Bhavya Kailkhura, Prasanna Sattigeri, Karthikeyan Natesan Ramamurthy
In this paper, we take a step in the direction of tackling the problem of interpretability without compromising the model accuracy.
no code implementations • 15 Jun 2016 • Prasanna Sattigeri, Aurélie Lozano, Aleksandra Mojsilović, Kush R. Varshney, Mahmoud Naghshineh
Innovation is among the key factors driving a country's economic and social growth.