Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/23446
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cheng, H | - |
dc.contributor.author | Wang, Z | - |
dc.contributor.author | Ma, L | - |
dc.contributor.author | Liu, X | - |
dc.contributor.author | Wei, Z | - |
dc.date.accessioned | 2021-11-03T19:25:08Z | - |
dc.date.available | 2021-11-03T19:25:08Z | - |
dc.date.issued | 2021-06-25 | - |
dc.identifier.citation | Cheng, H., Wang, Z., Ma, L., Liu, X. and Wei, Z. (2021) 'Multi-task Pruning via Filter Index Sharing: A Many-Objective Optimization Approach', Cognitive Computation, 13 (4), pp. 1070 - 1084. doi: 10.1007/s12559-021-09894-x. | en_US |
dc.identifier.issn | 1866-9956 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/23446 | - |
dc.description.abstract | © The Author(s) 2021. State-of-the-art deep neural network plays an increasingly important role in artificial intelligence, while the huge number of parameters in networks brings high memory cost and computational complexity. To solve this problem, filter pruning is widely used for neural network compression and acceleration. However, existing algorithms focus mainly on pruning single model, and few results are available to multi-task pruning that is capable of pruning multi-model and promoting the learning performance. By utilizing the filter sharing technique, this paper aimed to establish a multi-task pruning framework for simultaneously pruning and merging filters in multi-task networks. An optimization problem of selecting the important filters is solved by developing a many-objective optimization algorithm where three criteria are adopted as objectives for the many-objective optimization problem. With the purpose of keeping the network structure, an index matrix is introduced to regulate the information sharing during multi-task training. The proposed multi-task pruning algorithm is quite flexible that can be performed with either adaptive or pre-specified pruning rates. Extensive experiments are performed to verify the applicability and superiority of the proposed method on both single-task and multi-task pruning. | en_US |
dc.description.sponsorship | National Natural Science Foundation of China under Grants 61701238, 11431015, 61773209, 61873148 and 61933007; Natural Science Foundation of Jiangsu Province of China under Grant BK20190021; Six Talent Peaks Project in Jiangsu Province of China under Grant XYDXX-033; Royal Society of the U.K.; Alexander von Humboldt Foundation of Germany. | en_US |
dc.format.extent | 1070 - 1084 | - |
dc.format.medium | Print-Electronic | - |
dc.publisher | Springer Nature Switzerland AG | en_US |
dc.rights | © The Author(s) 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit https://creativecommons.org/licenses/by/4.0/. | - |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | - |
dc.subject | multi-task learning | en_US |
dc.subject | evolutionary algorithm | en_US |
dc.subject | network pruning | en_US |
dc.subject | multiple input delays | en_US |
dc.subject | many-objective optimization | en_US |
dc.title | Multi-task Pruning via Filter Index Sharing: A Many-Objective Optimization Approach | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1007/s12559-021-09894-x | - |
dc.relation.isPartOf | Cognitive Computation | - |
pubs.issue | 4 | - |
pubs.publication-status | Published | - |
pubs.volume | 13 | - |
dc.identifier.eissn | 1866-9964 | - |
Appears in Collections: | Dept of Computer Science Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | 2.8 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License