no code implementations • 13 Apr 2024 • Avinab Saha, Shashank Gupta, Sravan Kumar Ankireddy, Karl Chahine, Joydeep Ghosh
To address these, we introduce Video-TCAV, by building on TCAV for Image Classification tasks, which aims to quantify the importance of specific concepts in the decision-making process of Video Action Recognition models.
no code implementations • 1 Apr 2024 • Hsing-Huan Chung, Shravan Chaudhari, Yoav Wald, Xing Han, Joydeep Ghosh
We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel categories in attributed graphs under subpopulation shifts.
1 code implementation • 28 Mar 2024 • Song Wang, Yiliang Zhou, Ziqiang Han, Cui Tao, Yunyu Xiao, Ying Ding, Joydeep Ghosh, Yifan Peng
Data accuracy is essential for scientific research and policy development.
no code implementations • 27 Feb 2024 • Disha Makhija, Joydeep Ghosh, Yejin Kim
To overcome this obstacle, in this work, we propose a novel framework for collaborative learning of HTE estimators across institutions via Federated Learning.
no code implementations • 13 Jun 2023 • Disha Makhija, Joydeep Ghosh, Nhat Ho
Moreover, the need for uncertainty quantification and data privacy constraints are often particularly amplified for clients that have limited local data.
1 code implementation • 3 Dec 2022 • Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh, Byron C. Wallace
However, while fine-tuning sparse, interpretable representations improves accuracy on downstream tasks, it destroys the semantics of the dimensions which were enforced in pre-training.
no code implementations • 12 Oct 2022 • Shubham Sharma, Alan H. Gee, Jette Henderson, Joydeep Ghosh
The ability to quickly examine combinations of the most promising gradient directions as well as to incorporate additional user-defined constraints allows us to generate multiple counterfactual explanations that are sparse, realistic, and robust to input manipulations.
no code implementations • 10 Oct 2022 • Shubham Sharma, Jette Henderson, Joydeep Ghosh
In this paper, we propose FEAMOE, a novel "mixture-of-experts" inspired framework aimed at learning fairer, more explainable/interpretable models that can also rapidly adjust to drifts in both the accuracy and the fairness of a classifier.
1 code implementation • 27 Jun 2022 • Xing Han, Ziyang Tang, Joydeep Ghosh, Qiang Liu
The modified score inherits the spirit of split conformal methods, which is simple and efficient and can scale to high dimensional settings.
no code implementations • 27 May 2022 • Xing Han, Tongzheng Ren, Jing Hu, Joydeep Ghosh, Nhat Ho
To attain this goal, each time series is first assigned the forecast for its cluster representative, which can be considered as a "shrinkage prior" for the set of time series it represents.
no code implementations • 25 May 2022 • Disha Makhija, Nhat Ho, Joydeep Ghosh
As the field advances, two key challenges that still remain to be addressed are: (1) system heterogeneity - variability in the compute and/or data resources present on each client, and (2) lack of labeled data in certain federated settings.
no code implementations • 15 Feb 2022 • Disha Makhija, Xing Han, Nhat Ho, Joydeep Ghosh
With growing concerns regarding data privacy and rapid increase in data volume, Federated Learning(FL) has become an important learning paradigm.
no code implementations • 22 Dec 2021 • Xing Han, Jing Hu, Joydeep Ghosh
We conduct a comprehensive evaluation of both point and quantile forecasts for hierarchical time series (HTS), including public data and user records from a large financial software company.
no code implementations • 13 Dec 2021 • Diego Garcia-Olano, Yasumasa Onoe, Joydeep Ghosh
In this work, we empirically study how and whether such methods, applied in a bi-modal setting, can improve an existing VQA system's performance on the KBVQA task.
no code implementations • 29 Sep 2021 • Xing Han, Jing Hu, Joydeep Ghosh
We introduce a mixture of heterogeneous experts framework called MECATS, which simultaneously forecasts the values of a set of time series that are related through an aggregation hierarchy.
2 code implementations • Findings (ACL) 2021 • Diego Garcia-Olano, Yasumasa Onoe, Ioana Baldini, Joydeep Ghosh, Byron C. Wallace, Kush R. Varshney
Pre-trained language models induce dense entity representations that offer strong performance on entity-centric NLP tasks, but such representations are not immediately interpretable.
1 code implementation • 25 Feb 2021 • Xing Han, Sambarta Dasgupta, Joydeep Ghosh
In such applications, it is important that the forecasts, in addition to being reasonably accurate, are also consistent w. r. t one another.
no code implementations • 20 Dec 2020 • Aditya Jain, Manish Ravula, Joydeep Ghosh
We study fairness in Machine Learning (FairML) through the lens of attribute-based explanations generated for machine learning models.
no code implementations • 1 Nov 2020 • Xing Han, Joydeep Ghosh
How can we find a subset of training samples that are most responsible for a specific prediction made by a complex black-box machine learning model?
no code implementations • 13 Oct 2020 • Shubham Sharma, Alan H. Gee, David Paydarfar, Joydeep Ghosh
Fairness in machine learning is crucial when individuals are subject to automated decisions made by models in high-stake domains.
no code implementations • 13 Sep 2019 • Umang Bhatt, Alice Xiang, Shubham Sharma, Adrian Weller, Ankur Taly, Yunhan Jia, Joydeep Ghosh, Ruchir Puri, José M. F. Moura, Peter Eckersley
Yet there is little understanding of how organizations use these methods in practice.
4 code implementations • 25 Jul 2019 • Michael Motro, Joydeep Ghosh
Autonomous vehicles often perceive the environment by feeding sensor data to a learned detector algorithm, then feeding detections to a multi-object tracker that models object motions over time.
Robotics
5 code implementations • 22 Jul 2019 • Shalmali Joshi, Oluwasanmi Koyejo, Warut Vijitbenjaronk, Been Kim, Joydeep Ghosh
We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome.
no code implementations • 19 Jul 2019 • Dany Haddad, Joydeep Ghosh
Recent works have shown that it is possible to take advantage of the performance of these unsupervised methods to generate training data for learning-to-rank models.
1 code implementation • NeurIPS 2019 • Taewan Kim, Joydeep Ghosh
We investigate learning fusion algorithms that are robust against noise added to a single source.
no code implementations • 20 May 2019 • Shubham Sharma, Jette Henderson, Joydeep Ghosh
Given a model and an input instance, CERTIFAI uses a custom genetic algorithm to generate counterfactuals: instances close to the input that change the prediction of the model.
1 code implementation • 18 Apr 2019 • Alan H. Gee, Diego Garcia-Olano, Joydeep Ghosh, David Paydarfar
We improve upon existing models by optimizing for increased prototype diversity and robustness, visualize how these prototypes in the latent space are used by the model to distinguish classes, and show that prototypes are capable of learning features on two dimensional time-series data to produce explainable insights during classification tasks.
no code implementations • 23 Oct 2018 • Rajiv Khanna, Been Kim, Joydeep Ghosh, Oluwasanmi Koyejo
Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models.
no code implementations • 8 Aug 2018 • Jette Henderson, Bradley A. Malin, Joyce C. Ho, Joydeep Ghosh
It has been recently shown that sparse, nonnegative tensor factorization of multi-modal electronic health record data is a promising approach to high-throughput computational phenotyping.
no code implementations • 22 Jun 2018 • Shalmali Joshi, Oluwasanmi Koyejo, Been Kim, Joydeep Ghosh
This work proposes xGEMs or manifold guided exemplars, a framework to understand black-box classifier behavior by exploring the landscape of the underlying data manifold as data points cross decision boundaries.
no code implementations • 21 May 2018 • Michael Motro, Joydeep Ghosh
Handling object interaction is a fundamental challenge in practical multi-object tracking, even for simple interactive effects such as one object temporarily occluding another.
no code implementations • 21 Feb 2018 • Rahi Kalantari, Joydeep Ghosh, Mingyuan Zhou
A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is proposed to model sequentially observed multivariate data.
1 code implementation • 20 Nov 2017 • Taewan Kim, Joydeep Ghosh
Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering.
1 code implementation • 11 Sep 2017 • Taewan Kim, Joydeep Ghosh
For each weak oracle model, we show that a small query complexity is adequate for the effective $k$ means clustering with high probability.
1 code implementation • 16 Aug 2017 • Michael Motro, Joydeep Ghosh, Chandra Bhat
An important application of intelligent vehicles is advance detection of dangerous events such as collisions.
no code implementations • 5 Aug 2017 • Francesco Locatello, Rajiv Khanna, Joydeep Ghosh, Gunnar Rätsch
Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one.
no code implementations • 8 Mar 2017 • Rajiv Khanna, Ethan Elenberg, Alexandros G. Dimakis, Sahand Negahban, Joydeep Ghosh
Furthermore, we show that a bounded submodularity ratio can be used to provide data dependent bounds that can sometimes be tighter also for submodular functions.
no code implementations • 15 Dec 2016 • Ashish Bora, Sugato Basu, Joydeep Ghosh
Many time series are generated by a set of entities that interact with one another over time.
no code implementations • NeurIPS 2016 • Suriya Gunasekar, Oluwasanmi Koyejo, Joydeep Ghosh
We propose a novel and efficient algorithm for the collaborative preference completion problem, which involves jointly estimating individualized rankings for a set of entities over a shared set of items, based on a limited number of observed affinity values.
no code implementations • 2 Aug 2016 • Shalmali Joshi, Suriya Gunasekar, David Sontag, Joydeep Ghosh
This work proposes a new algorithm for automated and simultaneous phenotyping of multiple co-occurring medical conditions, also referred as comorbidities, using clinical notes from the electronic health records (EHRs).
no code implementations • 12 Jul 2016 • Rajiv Khanna, Joydeep Ghosh, Russell Poldrack, Oluwasanmi Koyejo
Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables.
no code implementations • 16 Jun 2016 • Yubin Park, Joyce Ho, Joydeep Ghosh
The resulting chain of decision rules yields a pure subset of the minority class examples.
no code implementations • 14 May 2016 • Avradeep Bhowmik, Joydeep Ghosh
Learning the true ordering between objects by aggregating a set of expert opinion rank order lists is an important and ubiquitous problem in many applications ranging from social choice theory to natural language processing and search aggregation.
no code implementations • 14 May 2016 • Avradeep Bhowmik, Joydeep Ghosh, Oluwasanmi Koyejo
We consider a limiting case of generalized linear modeling when the target variables are only known up to permutation, and explore how this relates to permutation testing; a standard technique for assessing statistical dependency.
no code implementations • NeurIPS 2015 • Suriya Gunasekar, Arindam Banerjee, Joydeep Ghosh
In this paper, we present a unified analysis of matrix completion under general low-dimensional structural constraints induced by {\em any} norm regularization.
no code implementations • 30 Dec 2015 • Ayan Acharya, Joydeep Ghosh, Mingyuan Zhou
A gamma process dynamic Poisson factor analysis model is proposed to factorize a dynamic count matrix, whose columns are sequentially observed count vectors.
no code implementations • 15 Sep 2015 • Suriya Gunasekar, Pradeep Ravikumar, Joydeep Ghosh
We consider the matrix completion problem of recovering a structured matrix from noisy and partial measurements.
no code implementations • NeurIPS 2014 • Oluwasanmi O. Koyejo, Rajiv Khanna, Joydeep Ghosh, Russell Poldrack
In cases where this projection is intractable, we propose a family of parameterized approximations indexed by subsets of the domain.
no code implementations • 27 Apr 2014 • Oluwasanmi Koyejo, Cheng Lee, Joydeep Ghosh
Transposable data represents interactions among two sets of entities, and are typically represented as a matrix containing the known interaction values.
no code implementations • 18 Dec 2013 • Yubin Park, Joydeep Ghosh
We propose a categorical data synthesizer with a quantifiable disclosure risk.
no code implementations • 26 Sep 2013 • Oluwasanmi Koyejo, Joydeep Ghosh
We present a novel approach for constrained Bayesian inference.
1 code implementation • JMLR 2002 • Alexander Strehl, Joydeep Ghosh
We evaluate the effectiveness of cluster ensembles in three qualitatively different application scenarios: (i) where the original clusters were formed based on non-identical sets of features, (ii) where the original clustering algorithms worked on non-identical sets of objects, and (iii) where a common data-set is used and the main purpose of combining multiple clusterings is to improve the quality and robustness of the solution.