Search Results for author: Abhishek Singh

Found 45 papers, 9 papers with code

PoinT-5: Pointer Network and T-5 based Financial Narrative Summarisation

no code implementations FNP (COLING) 2020 Abhishek Singh

Companies provide annual reports to their shareholders at the end of the financial year that de-scribes their operations and financial conditions.

Sentence

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts

1 code implementation19 Mar 2024 Sai Ashish Somayajula, Youwei Liang, Abhishek Singh, Li Zhang, Pengtao Xie

Pretrained Language Models (PLMs) have advanced Natural Language Processing (NLP) tasks significantly, but finetuning PLMs on low-resource datasets poses significant challenges such as instability and overfitting.

DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Images

no code implementations19 Mar 2024 Zaid Tasneem, Akshat Dave, Abhishek Singh, Kushagra Tiwary, Praneeth Vepakomma, Ashok Veeraraghavan, Ramesh Raskar

It learns photorealistic scene representations by decomposing users' 3D views into personal and global NeRFs and a novel optimally weighted aggregation of only the latter.

CoDream: Exchanging dreams instead of models for federated aggregation with heterogeneous models

no code implementations25 Feb 2024 Abhishek Singh, Gauri Gupta, Ritvik Kapila, Yichuan Shi, Alex Dang, Sheshank Shankar, Mohammed Ehab, Ramesh Raskar

Federated Learning (FL) enables collaborative optimization of machine learning models across decentralized data by aggregating model parameters.

Federated Learning

EIGEN: Expert-Informed Joint Learning Aggregation for High-Fidelity Information Extraction from Document Images

1 code implementation23 Nov 2023 Abhishek Singh, Venkatapathy Subramanian, Ayush Maheshwari, Pradeep Narayan, Devi Prasad Shetty, Ganesh Ramakrishnan

We empirically show that our EIGEN framework can significantly improve the performance of state-of-the-art deep models with the availability of very few labeled data instances.

Scalable Collaborative Learning via Representation Sharing

no code implementations20 Nov 2022 Frédéric Berdoz, Abhishek Singh, Martin Jaggi, Ramesh Raskar

To do so, each client releases averaged last hidden layer activations of similar labels to a central server that only acts as a relay (i. e., is not involved in the training or aggregation of the models).

Federated Learning Knowledge Distillation +1

Learning to Censor by Noisy Sampling

no code implementations23 Mar 2022 Ayush Chopra, Abhinav Java, Abhishek Singh, Vivek Sharma, Ramesh Raskar

The goal of this work is to protect sensitive information when learning from point clouds; by censoring the sensitive information before the point cloud is released for downstream tasks.

Attribute

Decouple-and-Sample: Protecting sensitive information in task agnostic data release

no code implementations17 Mar 2022 Abhishek Singh, Ethan Garza, Ayush Chopra, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar

While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is not inhibited by privacy concerns.

Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads

no code implementations16 Feb 2022 Dharma Shukla, Muthian Sivathanu, Srinidhi Viswanatha, Bhargav Gulavani, Rimma Nehme, Amey Agrawal, Chen Chen, Nipun Kwatra, Ramachandran Ramjee, Pankaj Sharma, Atul Katiyar, Vipul Modi, Vaibhav Sharma, Abhishek Singh, Shreshth Singhal, Kaustubh Welankar, Lu Xun, Ravi Anupindi, Karthik Elangovan, Hasibur Rahman, Zhou Lin, Rahul Seetharaman, Cheng Xu, Eddie Ailijiang, Suresh Krishnappa, Mark Russinovich

At the heart of Singularity is a novel, workload-aware scheduler that can transparently preempt and elastically scale deep learning workloads to drive high utilization without impacting their correctness or performance, across a global fleet of AI accelerators (e. g., GPUs, FPGAs).

Scheduling

AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning

no code implementations2 Dec 2021 Ayush Chopra, Surya Kant Sahu, Abhishek Singh, Abhinav Java, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar

In this work, we introduce AdaSplit which enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients.

Federated Learning

Sanitizer: Sanitizing data for anonymizing sensitive information

no code implementations29 Sep 2021 Abhishek Singh, Ethan Garza, Ayush Chopra, Praneeth Vepakomma, Vivek Sharma, Ramesh Raskar

This is done in a two-step process: first, we develop a method that encodes unstructured image-like modality into a structured representation bifurcated by sensitive and non-sensitive representation.

Attribute

An In-Memory Analog Computing Co-Processor for Energy-Efficient CNN Inference on Mobile Devices

no code implementations24 May 2021 Mohammed Elbtity, Abhishek Singh, Brendan Reidy, Xiaochen Guo, Ramtin Zand

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays.

Automatic calibration of time of flight based non-line-of-sight reconstruction

no code implementations21 May 2021 Subhash Chandra Sadhu, Abhishek Singh, Tomohiro Maeda, Tristan Swedish, Ryan Kim, Lagnojita Sinha, Ramesh Raskar

Time of flight based Non-line-of-sight (NLOS) imaging approaches require precise calibration of illumination and detector positions on the visible scene to produce reasonable results.

Can Self Reported Symptoms Predict Daily COVID-19 Cases?

1 code implementation18 May 2021 Parth Patwa, Viswanatha Reddy, Rohan Sukumaran, Sethuraman TV, Eptehal Nashnoush, Sheshank Shankar, Rishemjit Kaur, Abhishek Singh, Ramesh Raskar

The models are developed at two levels of data granularity - local models, which are trained at the state level, and a single global model which is trained on the combined data aggregated across all states.

Blockchain Based Accounts Payable Platform for Goods Trade

no code implementations4 Mar 2021 Krishnasuri Narayanam, Seep Goel, Abhishek Singh, Yedendra Shrinivasan, Parameswaram Selvam

Goods trade is a supply chain transaction that involves shippers buying goods from suppliers and carriers providing goods transportation.

Distributed, Parallel, and Cluster Computing

COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms

no code implementations21 Dec 2020 Rohan Sukumaran, Parth Patwa, T V Sethuraman, Sheshank Shankar, Rishank Kanaparti, Joseph Bae, Yash Mathur, Abhishek Singh, Ayush Chopra, Myungsun Kang, Priya Ramaswamy, Ramesh Raskar

In this study, we understand trends in the spread of COVID-19 by utilizing the results of self-reported COVID-19 symptoms surveys as an alternative to COVID-19 testing reports.

Time Series Forecasting

PoinT-5: Pointer Network and T-5 based Financial NarrativeSummarisation

no code implementations8 Oct 2020 Abhishek Singh

In this paper, we propose our methodology PoinT-5 (the combination of Pointer Network and T-5 (Test-to-text transfer Transformer) algorithms) that we used in the Financial Narrative Summarisation (FNS) 2020 task.

Sentence

Proximity Inference with Wifi-Colocation during the COVID-19 Pandemic

no code implementations26 Sep 2020 Mikhail Dmitrienko, Abhishek Singh, Patrick Erichsen, Ramesh Raskar

In this work we propose a WiFi colocation methodology for digital contact tracing.

Computers and Society Signal Processing

NoPeek: Information leakage reduction to share activations in distributed deep learning

1 code implementation20 Aug 2020 Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, Ramesh Raskar

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while maintaining model accuracy.

SplitNN-driven Vertical Partitioning

no code implementations7 Aug 2020 Iker Ceballos, Vivek Sharma, Eduardo Mugica, Abhishek Singh, Alberto Roman, Praneeth Vepakomma, Ramesh Raskar

In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features.

Privacy in Deep Learning: A Survey

no code implementations25 Apr 2020 Fatemehsadat Mireshghallah, Mohammadkazem Taram, Praneeth Vepakomma, Abhishek Singh, Ramesh Raskar, Hadi Esmaeilzadeh

In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues.

Recommendation Systems

A single-cell RNA expression map of coronavirus receptors and associated factors in developing human embryos

no code implementations10 Apr 2020 Stacy Colaco, Karisma Chhabria, Domdatt Singh, Anshul Bhide, Neha Singh, Abhishek Singh, Atahar Husein, Anuradha Mishra, Richa Sharma, Nancy Ashary, Deepak Modi

To predict if developing human embryos are permissive to coronaviruses, we analyzed publicly available single cell RNA-seq datasets of zygotes, 4-cell, 8-cell, morula, inner cell mass, epiblast, primitive endoderm and trophectoderm for the coronavirus receptors (ACE2, BSG, DPP4 and ANPEP), the Spike protein cleavage enzymes (TMPRSS2, CTSL).

Management

Apps Gone Rogue: Maintaining Personal Privacy in an Epidemic

1 code implementation19 Mar 2020 Ramesh Raskar, Isabel Schunemann, Rachel Barbar, Kristen Vilcans, Jim Gray, Praneeth Vepakomma, Suraj Kapa, Andrea Nuzzo, Rajiv Gupta, Alex Berke, Dazza Greenwood, Christian Keegan, Shriank Kanaparti, Robson Beaudry, David Stansbury, Beatriz Botero Arcila, Rishank Kanaparti, Francesco M Benedetti, Alina Clough, Riddhiman Das, Kaushal Jain, Khahlil Louisy, Greg Nadeau, Vitor Pamplona, Steve Penrod, Yasaman Rajaee, Abhishek Singh, Greg Storm, John Werner

Containment, the key strategy in quickly halting an epidemic, requires rapid identification and quarantine of the infected individuals, determination of whom they have had close contact with in the previous days and weeks, and decontamination of locations the infected individual has visited.

Cryptography and Security Computers and Society Distributed, Parallel, and Cluster Computing

NASIB: Neural Architecture Search withIn Budget

no code implementations19 Oct 2019 Abhishek Singh, Anubhav Garg, Jinan Zhou, Shiv Ram Dubey, Debo Dutta

Neural Architecture Search (NAS) represents a class of methods to generate the optimal neural network architecture and typically iterate over candidate architectures till convergence over some particular metric like validation loss.

Image Classification Neural Architecture Search

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

no code implementations27 Sep 2019 Indu Ilanchezian, Praneeth Vepakomma, Abhishek Singh, Otkrist Gupta, G. N. Srinivasa Prasanna, Ramesh Raskar

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection.

Attribute Data Poisoning

Detailed comparison of communication efficiency of split learning and federated learning

no code implementations18 Sep 2019 Abhishek Singh, Praneeth Vepakomma, Otkrist Gupta, Ramesh Raskar

We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning.

Federated Learning

"When and Where?": Behavior Dominant Location Forecasting with Micro-blog Streams

no code implementations16 Dec 2018 Bhaskar Gautam, Annappa Basava, Abhishek Singh, Amit Agrawal

The proliferation of smartphones and wearable devices has increased the availability of large amounts of geospatial streams to provide significant automated discovery of knowledge in pervasive environments, but most prominent information related to altering interests have not yet adequately capitalized.

Fast Neural Architecture Construction using EnvelopeNets

no code implementations18 Mar 2018 Purushotham Kamath, Abhishek Singh, Debo Dutta

Fast Neural Architecture Construction (NAC) is a method to construct deep network architectures by pruning and expansion of a base network.

Evolutionary Algorithms Image Classification +1

AMLA: an AutoML frAmework for Neural Network Design

no code implementations ICML 2018 AutoML Workshop 2018 Purushotham Kamath, Abhishek Singh, Debo Dutta

Its key architectural features are the decoupling of the network generation from the network evaluation, support for network instrumentation, open model specification and a microservices based architecture for deployment at scale.

Hyperparameter Optimization Image Classification +1

Single Image Super-Resolution From Transformed Self-Exemplars

no code implementations CVPR 2015 Jia-Bin Huang, Abhishek Singh, Narendra Ahuja

However, the internal dictionary obtained from the given image may not always be sufficiently expressive to cover the textural appearance variations in the scene.

Image Super-Resolution

Super-Resolving Noisy Images

no code implementations CVPR 2014 Abhishek Singh, Fatih Porikli, Narendra Ahuja

We then show that by taking a convex combination of orientation and frequency selective bands of the noisy and the denoised HR images, we can obtain a desired HR image where (i) some of the textural signal lost in the denoising step is effectively recovered in the HR domain, and (ii) additional textures can be easily synthesized by appropriately constraining the parameters of the convex combination.

Denoising Super-Resolution

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