Strategies for Re-Training a Pruned Neural Network in an Edge Computing Paradigm
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Construction of robust and accurate deep neural networks (DNNs) is a computationally demanding and time-consuming process. Such networks also end up being memory intensive. Today, there is ever-increasing need to provide proactive and personalized support for users of smart devices. We could provide better personalization if we have the ability to update/train the DNN on edge devices. Also, by moving some computation to the edge of the cloud infrastructure, we could reduce the load on computing clusters, thus providing them more resources to handle core and complex tasks. To this end, weight pruning for DNNs has been proposed to reduce their storage footprint by an order of magnitude. However, it is yet unclear as to how to update/re-train DNNs once they are deployed on mobile devices. In this paper, we introduce the concept of re-training of pruned networks that should aid personalization of smart devices as well as increase their fault tolerance. We assume that the data used to re-train the pruned network comes from a distribution similar to what used in the original, unpruned network. We propose various strategies for pruning and re-training the networks and show that we may obtain a significant improvement on the new data while minimizing the reduction in performance on the original data.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., & Bengio, Y. (2016) · arXiv · doi:10.48550/arxiv.1602.02830 · Cited by 2,106
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Denton, R., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1404.0736 · Cited by 1,414
EIE: Efficient Inference Engine on Compressed Deep Neural Network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.30 · Cited by 1,077
Predicting Parameters in Deep Learning
Denil, M., Shakibi, B., Dinh, L., Ranzato, M., & de Freitas, N. (2013) · arXiv · doi:10.48550/arxiv.1306.0543 · Cited by 853
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA
Han, S., Kang, J., Mao, H., Hu, Y., Li, X., Li, Y., Xie, D., Luo, H., Yao, S., Wang, Y., et al. (2017) · Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/3020078.3021745 · Cited by 591 · cited 2×
“Other line of research includes developing specialized hardware accelerators [8], [9] and guiding shallow CNNs using the activations of deeper ones [12].”
BackgroundSelf-citationPredicting Parameters in Deep Learning
Shakibi, B. (2014) · University of British Columbia · doi:10.14288/1.0165555 · Cited by 462
Diving deeper into mentee networks
Venkatesan, R., & Li, B. (2016) · arXiv · doi:10.48550/arxiv.1604.08220 · Cited by 14 · cited 1×
“Other line of research includes developing specialized hardware accelerators [8], [9] and guiding shallow CNNs using the activations of deeper ones [12].”
BackgroundSelf-citation
Cited by
Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence
Deng, S., Zhao, H., Fang, W., Yin, J., Dustdar, S., & Zomaya, A. Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2984887 · Cited by 1,147
Edge Machine Learning for AI-Enabled IoT Devices: A Review
Merenda, M., Porcaro, C., & Iero, D. (2020) · Sensors · doi:10.3390/s20092533 · Cited by 523
Communication-Efficient Federated Learning for Wireless Edge Intelligence in IoT
Mills, J., Hu, J., & Min, G. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2956615 · Cited by 436
“Chandakkar et al. [24] developed a system for re-training and pruning networks at the edge as nodes receive data over time.”
Liang, S., Wu, H., Zhen, L., Hua, Q., Garg, S., Kaddoum, G., Hassan, M. M., & Yu, K. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3158253 · Cited by 367
Blockchain and Machine Learning for Communications and Networking Systems
Liu, Y., Yu, F. R., Li, X., Ji, H., & Leung, V. C. M. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2975911 · Cited by 313
Metadata
- Authors
- Chandakkar, P. S., Li, Y., Ding, P. L. K., & Li, B.
- Venue
- 2017 IEEE International Conference on Edge Computing (EDGE)
- Publisher
- IEEE
- Published
- 2017-06
- Pages
- 244-247
- OpenAlex
- W2755837314
- Cited by
- 39
- References
- 9
- FWCI
- 1.46
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.