Internet Archive Scholar
Filters
























3 Hits in 2.4 sec

SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks [article]

Won Joon Yun, Yunseok Kwak, Hankyul Baek, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim
<span title="2022-03-26">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.5 MB)
https://web.archive.org/web/20220618064743/https://arxiv.org/pdf/2203.14094v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2203.14094v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To cope with these issues, this paper proposes a novel learning framework by integrating FL and width-adjustable slimmable neural networks (SNN).  ...  Motivated by this, we propose a communication and energy-efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST  ...  As opposed to a de facto standard neural network architecture with a universal batch normalization layer, US-MobileNet is equipped with multiple separate BN layers to cope with all slimmable model configurations  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14094v1">arXiv:2203.14094v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kt4hptbb7rezffa3exs3btkzxm">fatcat:kt4hptbb7rezffa3exs3btkzxm</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220618064743/https://arxiv.org/pdf/2203.14094v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/65/f5/65f5e2aeeabe42b44c9b8dd05b2a62e3a7fa9ccd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.14094v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Won Joon Yun, Yunseok Kwak, Hankyul Baek, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim. "SlimFL: Federated Learning with Superposition Coding over Slimmable Neural Networks." arXiv (2022)

Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding [article]

Hankyul Baek, Won Joon Yun, Soyi Jung, Jihong Park, Mingyue Ji, Joongheon Kim, Mehdi Bennis
<span title="2021-12-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.6 MB)
https://web.archive.org/web/20211209025128/https://arxiv.org/pdf/2112.03267v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2112.03267v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

To resolve the heterogeneous energy capacity problem, each device in SlimFL runs a width-adjustable slimmable neural network (SNN).  ...  Federated learning (FL) has a great potential in exploiting these private data by exchanging locally trained models instead of their raw data.  ...  Slimmable federated learning (SlimFL) in the (a) uplink and (b) downlink, with the superposition coding (SC) and successive decoding (SD) of the slimmable neural networks (SNNs).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03267v1">arXiv:2112.03267v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3ii6pjxznjhwteqcroktter4je">fatcat:3ii6pjxznjhwteqcroktter4je</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211209025128/https://arxiv.org/pdf/2112.03267v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/07/04/0704fef53451936da1564e52b534df4101d65448.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03267v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Hankyul Baek, Won Joon Yun, Soyi Jung, Jihong Park, Mingyue Ji, Joongheon Kim, Mehdi Bennis. "Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding." arXiv (2021)

Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks [article]

Hankyul Baek, Won Joon Yun, Yunseok Kwak, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim
<span title="2021-12-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (4.5 MB)
https://web.archive.org/web/20211208164755/https://arxiv.org/pdf/2112.02543v1.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2112.02543v1.pdf">the original URL</a>. The file type is <code>application/pdf</code>.

This paper aims to integrate two synergetic technologies, federated learning (FL) and width-adjustable slimmable neural network (SNN) architectures.  ...  Motivated by this, we propose a communication and energy-efficient SNN-based FL (named SlimFL) that jointly utilizes superposition coding (SC) for global model aggregation and superposition training (ST  ...  Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02543v1">arXiv:2112.02543v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3vob653qeza5ngqjdovhkqmuum">fatcat:3vob653qeza5ngqjdovhkqmuum</a> </span>
<span class="ui label basic orange small" title="Open Access">Open Access</span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208164755/https://arxiv.org/pdf/2112.02543v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ca/7d/ca7de00675ed516fbc9eb04995dff69615994c4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.02543v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
Citation

Hankyul Baek, Won Joon Yun, Yunseok Kwak, Soyi Jung, Mingyue Ji, Mehdi Bennis, Jihong Park, Joongheon Kim. "Joint Superposition Coding and Training for Federated Learning over Multi-Width Neural Networks." arXiv (2021)