Distributed learning of deep neural network over multiple agents
In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to t...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Elsevier BV
2019
|
| Online Access: | https://hdl.handle.net/1721.1/121966 |
| _version_ | 1811095151695626240 |
|---|---|
| author | Gupta, Otkrist Gupta, Otkrist Raskar, Ramesh |
| author2 | Program in Media Arts and Sciences (Massachusetts Institute of Technology) |
| author_facet | Program in Media Arts and Sciences (Massachusetts Institute of Technology) Gupta, Otkrist Gupta, Otkrist Raskar, Ramesh |
| author_sort | Gupta, Otkrist |
| collection | MIT |
| description | In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural networks over several data sources. Our method allows for deep neural networks to be trained using data from multiple entities in a distributed fashion. We evaluate our algorithm on existing datasets and show that it obtains performance which is similar to a regular neural network trained on a single machine. We further extend it to incorporate semi-supervised learning when training with few labeled samples, and analyze any security concerns that may arise. Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly. |
| first_indexed | 2024-09-23T16:11:28Z |
| format | Article |
| id | mit-1721.1/121966 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T16:11:28Z |
| publishDate | 2019 |
| publisher | Elsevier BV |
| record_format | dspace |
| spelling | mit-1721.1/1219662022-10-02T06:58:20Z Distributed learning of deep neural network over multiple agents Gupta, Otkrist Gupta, Otkrist Raskar, Ramesh Program in Media Arts and Sciences (Massachusetts Institute of Technology) Massachusetts Institute of Technology. Media Laboratory In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural networks over several data sources. Our method allows for deep neural networks to be trained using data from multiple entities in a distributed fashion. We evaluate our algorithm on existing datasets and show that it obtains performance which is similar to a regular neural network trained on a single machine. We further extend it to incorporate semi-supervised learning when training with few labeled samples, and analyze any security concerns that may arise. Our algorithm paves the way for distributed training of deep neural networks in data sensitive applications when raw data may not be shared directly. 2019-08-02T19:28:37Z 2019-08-02T19:28:37Z 2018-08 2018-04 2019-08-02T14:08:40Z Article http://purl.org/eprint/type/JournalArticle 1084-8045 https://hdl.handle.net/1721.1/121966 Gupta, Otkrist and Ramesh Raskar. "Distributed learning of deep neural network over multiple agents." Journal of Network and Computer Applications 116 (August 2018): 1-8 © 2018 Elsevier Ltd en http://dx.doi.org/10.1016/j.jnca.2018.05.003 Journal of Network and Computer Applications Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier BV arXiv |
| spellingShingle | Gupta, Otkrist Gupta, Otkrist Raskar, Ramesh Distributed learning of deep neural network over multiple agents |
| title | Distributed learning of deep neural network over multiple agents |
| title_full | Distributed learning of deep neural network over multiple agents |
| title_fullStr | Distributed learning of deep neural network over multiple agents |
| title_full_unstemmed | Distributed learning of deep neural network over multiple agents |
| title_short | Distributed learning of deep neural network over multiple agents |
| title_sort | distributed learning of deep neural network over multiple agents |
| url | https://hdl.handle.net/1721.1/121966 |
| work_keys_str_mv | AT guptaotkrist distributedlearningofdeepneuralnetworkovermultipleagents AT guptaotkrist distributedlearningofdeepneuralnetworkovermultipleagents AT raskarramesh distributedlearningofdeepneuralnetworkovermultipleagents |