dc.citation.conferencePlace |
CN |
- |
dc.citation.conferencePlace |
Online |
- |
dc.citation.endPage |
190 |
- |
dc.citation.startPage |
175 |
- |
dc.citation.title |
ACM International Conference on Mobile Systems, Applications, and Services |
- |
dc.contributor.author |
Lee, Seulki |
- |
dc.contributor.author |
Nirjon, Shahriar |
- |
dc.date.accessioned |
2024-01-31T23:06:40Z |
- |
dc.date.available |
2024-01-31T23:06:40Z |
- |
dc.date.created |
2021-08-23 |
- |
dc.date.issued |
2020-06-17 |
- |
dc.description.abstract |
This paper introduces the concept of Neural Weight Virtualization - which enables fast and scalable in-memory multitask deep learning on memory-constrained embedded systems. The goal of neural weight virtualization is two-fold: (1) packing multiple DNNs into a fixed-sized main memory whose combined memory requirement is larger than the main memory, and (2) enabling fast in-memory execution of the DNNs. To this end, we propose a two-phase approach: (1) virtualization of weight parameters for fine-grained parameter sharing at the level of weights that scales up to multiple heterogeneous DNNs of arbitrary network architectures, and (2) in-memory data structure and run-time execution framework for in-memory execution and context-switching of DNN tasks. We implement two multitask learning systems: (1) an embedded GPU-based mobile robot, and (2) a microcontroller-based IoT device. We thoroughly evaluate the proposed algorithms as well as the two systems that involve ten state-of-the-art DNNs. Our evaluation shows that weight virtualization improves memory efficiency, execution time, and energy efficiency of the multitask learning systems by 4.1x, 36.9x, and 4.2x, respectively. |
- |
dc.identifier.bibliographicCitation |
ACM International Conference on Mobile Systems, Applications, and Services, pp.175 - 190 |
- |
dc.identifier.doi |
10.1145/3386901.3388947 |
- |
dc.identifier.scopusid |
2-s2.0-85088104997 |
- |
dc.identifier.uri |
https://scholarworks.unist.ac.kr/handle/201301/78484 |
- |
dc.identifier.url |
https://www.youtube.com/watch?v=9-3qh1fKfCU |
- |
dc.language |
영어 |
- |
dc.publisher |
Association for Computing Machinery |
- |
dc.title |
Fast and scalable in-memory deep multitask learning via neural weight virtualization |
- |
dc.type |
Conference Paper |
- |
dc.date.conferenceDate |
2020-06-15 |
- |