Search

Your search keyword '"Agrawal, Neha"' showing total 406 results
Start Over Author "Agrawal, Neha" Search Limiters Full Text
406 results on '"Agrawal, Neha"'

1. List of contributors

Author

Acharya, Amitabha, primary, Agrawal, Neha, additional, Ahlawat, Navin, additional, Bajpai, Sangeeta, additional, Banaspati, Atrayee, additional, Bathla, Manik, additional, Batish, Daizy Rani, additional, Bhavsar, Kalpesh V., additional, Chandimala, U.R., additional, Dhushane, S., additional, Gaur, Pooja, additional, Gautam, Ayushi, additional, Guleria, Praveen, additional, Gupta, Ipsa, additional, Hasan, Ziaul, additional, Husain, Arbab, additional, Jagtap, Uday P., additional, Jandrotia, Rupali, additional, Kalita, Debajit, additional, Kamboj, Monika, additional, Khanam, Afreen, additional, Khare, Puja, additional, Kumar, Vineet, additional, Lateef, Muneera, additional, Mahajan, Priyanka, additional, Mandal, Mamun, additional, Mishra, Disha, additional, Pal, Probir Kumar, additional, Pandey, Garima, additional, Pandey, Versha, additional, Poonia, Amrita, additional, Prasai, Jiwan Raj, additional, Rajkhowa, Sanchayita, additional, Rao, Vasundhara, additional, Saini, Trilok Chand, additional, Sarkar, Abhijit, additional, Sarma, Jyotirmoy, additional, Sarmah, Nirupamjit, additional, Shanker, Karuna, additional, Sharma, Mansi, additional, Sharma, Priya, additional, Singh, Harminder Pal, additional, Singh, Pardeep, additional, Srivastav, Ajeet K., additional, Srivastava, Madhumita, additional, Srivastava, Nupur, additional, Swapana, Ningombam, additional, Tiwari, Neerja, additional, and Yadav, Anisha, additional

Published
2024
Full Text
View/download PDF

16. Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices

Author

Xu, Mingbin, Song, Congzheng, Tian, Ye, Agrawal, Neha, Granqvist, Filip, van Dalen, Rogier, Zhang, Xiao, Argueta, Arturo, Han, Shiyi, Deng, Yaqiao, Liu, Leo, Walia, Anmol, and Jin, Alex

Subjects
Computer Science - Machine Learning, Computer Science - Computation and Language, Computer Science - Cryptography and Security
Abstract

Federated Learning (FL) is a technique to train models using data distributed across devices. Differential Privacy (DP) provides a formal privacy guarantee for sensitive data. Our goal is to train a large neural network language model (NNLM) on compute-constrained devices while preserving privacy using FL and DP. However, the DP-noise introduced to the model increases as the model size grows, which often prevents convergence. We propose Partial Embedding Updates (PEU), a novel technique to decrease noise by decreasing payload size. Furthermore, we adopt Low Rank Adaptation (LoRA) and Noise Contrastive Estimation (NCE) to reduce the memory demands of large models on compute-constrained devices. This combination of techniques makes it possible to train large-vocabulary language models while preserving accuracy and privacy.

Published
2022

18. 2650. Characteristics of In-Hospital Care and Immediate Post-Discharge Care Status among Older Adults Hospitalized with Respiratory Syncytial Virus Infection, Seasonal Influenza, Acute Myocardial Infarction, and Stroke in the US

Author

Sato, Reiko, primary, Judy, Jennifer, additional, Yacisin, Kari, additional, Begier, Elizabeth, additional, Sardana, Poorva, additional, Agrawal, Neha, additional, Goswami, Anchita, additional, and Sharma, Manvi, additional

Published
2023
Full Text
View/download PDF

27. Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices

Author

Xu, Mingbin, primary, Song, Congzheng, additional, Tian, Ye, additional, Agrawal, Neha, additional, Granqvist, Filip, additional, van Dalen, Rogier, additional, Zhang, Xiao, additional, Argueta, Arturo, additional, Han, Shiyi, additional, Deng, Yaqiao, additional, Liu, Leo, additional, Walia, Anmol, additional, and Jin, Alex, additional

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results