Search Results for author: Joydeep Ghosh

Found 52 papers, 13 papers with code

Exploring Explainability in Video Action Recognition

no code implementations13 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.

Action Recognition Classification +2

Novel Node Category Detection Under Subpopulation Shift

no code implementations1 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.

Link Prediction

Federated Learning for Estimating Heterogeneous Treatment Effects

no code implementations27 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.

Decision Making Federated Learning +1

Privacy Preserving Bayesian Federated Learning in Heterogeneous Settings

no code implementations13 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.

Federated Learning Privacy Preserving +1

Intermediate Entity-based Sparse Interpretable Representation Learning

1 code implementation3 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.

counterfactual Representation Learning

FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanations

no code implementations12 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.

counterfactual Explanation Generation

FEAMOE: Fair, Explainable and Adaptive Mixture of Experts

no code implementations10 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.


Split Localized Conformal Prediction

1 code implementation27 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.

Conformal Prediction Density Estimation +2

Efficient Forecasting of Large Scale Hierarchical Time Series via Multilevel Clustering

no code implementations27 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.

Clustering Time Series +1

Federated Self-supervised Learning for Heterogeneous Clients

no code implementations25 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.

Federated Learning Representation Learning +1

Architecture Agnostic Federated Learning for Neural Networks

no code implementations15 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.

Federated Learning

Dynamic Combination of Heterogeneous Models for Hierarchical Time Series

no code implementations22 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.

Time Series Time Series Analysis

Improving and Diagnosing Knowledge-Based Visual Question Answering via Entity Enhanced Knowledge Injection

no code implementations13 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.

Common Sense Reasoning Knowledge Graph Embeddings +3

MECATS: Mixture-of-Experts for Probabilistic Forecasts of Aggregated Time Series

no code implementations29 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.

Time Series Time Series Analysis

Biomedical Interpretable Entity Representations

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.

Entity Disambiguation Representation Learning

Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series

1 code implementation25 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.

Time Series Time Series Analysis

Biased Models Have Biased Explanations

no code implementations20 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.

Attribute BIG-bench Machine Learning +1

Model-Agnostic Explanations using Minimal Forcing Subsets

no code implementations1 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?

BIG-bench Machine Learning Counterfactual Explanation +1

FaiR-N: Fair and Robust Neural Networks for Structured Data

no code implementations13 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.

Adversarial Robustness Attribute +1

Vehicular Multi-object Tracking with Persistent Detector Failures

4 code implementations25 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.


Learning More From Less: Towards Strengthening Weak Supervision for Ad-Hoc Retrieval

no code implementations19 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.

Learning-To-Rank Retrieval

On Single Source Robustness in Deep Fusion 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.

Self-Driving Cars

CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models

no code implementations20 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.

counterfactual Fairness

Explaining Deep Classification of Time-Series Data with Learned Prototypes

1 code implementation18 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.

Classification Decision Making +3

Interpreting Black Box Predictions using Fisher Kernels

no code implementations23 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.

Data Summarization

PIVETed-Granite: Computational Phenotypes through Constrained Tensor Factorization

no code implementations8 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.

Computational Phenotyping

xGEMs: Generating Examplars to Explain Black-Box Models

no code implementations22 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.

Measurement-wise Occlusion in Multi-object Tracking

no code implementations21 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.

Multi-Object Tracking Object +1

Nonparametric Bayesian Sparse Graph Linear Dynamical Systems

no code implementations21 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.

Time Series Time Series Analysis

Relaxed Oracles for Semi-Supervised Clustering

1 code implementation20 Nov 2017 Taewan Kim, Joydeep Ghosh

Pairwise "same-cluster" queries are one of the most widely used forms of supervision in semi-supervised clustering.


Semi-Supervised Active Clustering with Weak Oracles

1 code implementation11 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.


Optimal Alarms for Vehicular Collision Detection

1 code implementation16 Aug 2017 Michael Motro, Joydeep Ghosh, Chandra Bhat

An important application of intelligent vehicles is advance detection of dangerous events such as collisions.

BIG-bench Machine Learning

Boosting Variational Inference: an Optimization Perspective

no code implementations5 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.

Variational Inference

Scalable Greedy Feature Selection via Weak Submodularity

no code implementations8 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.

feature selection

Graphical RNN Models

no code implementations15 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.

Time Series Time Series Analysis

Preference Completion from Partial Rankings

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.

Matrix Completion

Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization

no code implementations2 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).

Information Projection and Approximate Inference for Structured Sparse Variables

no code implementations12 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.

ACDC: $α$-Carving Decision Chain for Risk Stratification

no code implementations16 Jun 2016 Yubin Park, Joyce Ho, Joydeep Ghosh

The resulting chain of decision rules yields a pure subset of the minority class examples.

Monotone Retargeting for Unsupervised Rank Aggregation with Object Features

no code implementations14 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.


Generalized Linear Models for Aggregated Data

no code implementations14 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.


Unified View of Matrix Completion under General Structural Constraints

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.

Matrix Completion

Nonparametric Bayesian Factor Analysis for Dynamic Count Matrices

no code implementations30 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.

Data Augmentation

Exponential Family Matrix Completion under Structural Constraints

no code implementations15 Sep 2015 Suriya Gunasekar, Pradeep Ravikumar, Joydeep Ghosh

We consider the matrix completion problem of recovering a structured matrix from noisy and partial measurements.

Matrix Completion

On Prior Distributions and Approximate Inference for Structured Variables

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.

A Constrained Matrix-Variate Gaussian Process for Transposable Data

no code implementations27 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.

Recommendation Systems

Perturbed Gibbs Samplers for Synthetic Data Release

no code implementations18 Dec 2013 Yubin Park, Joydeep Ghosh

We propose a categorical data synthesizer with a quantifiable disclosure risk.

Imputation regression

Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions

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.

Clustering Combinatorial Optimization +1

Cannot find the paper you are looking for? You can Submit a new open access paper.