Differentially-private Federated Neural Architecture Search [article]

Ishika Singh, Haoyi Zhou, Kunlin Yang, Meng Ding, Bill Lin, Pengtao Xie
<span title="2020-06-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, several parties would like to collaboratively search for a shared neural architecture by leveraging data from all parties. However, due to privacy concerns, no party wants its data to be seen by other parties. To address this problem, we propose
more &raquo; ... neural architecture search (FNAS), where different parties collectively search for a differentiable architecture by exchanging gradients of architecture variables without exposing their data to other parties. To further preserve privacy, we study differentially-private FNAS (DP-FNAS), which adds random noise to the gradients of architecture variables. We provide theoretical guarantees of DP-FNAS in achieving differential privacy. Experiments show that DP-FNAS can search highly-performant neural architectures while protecting the privacy of individual parties. The code is available at https://github.com/UCSD-AI4H/DP-FNAS
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.10559v2">arXiv:2006.10559v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7xpjs4bc6rf5nj6ljle4mnzdpm">fatcat:7xpjs4bc6rf5nj6ljle4mnzdpm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200625013314/https://arxiv.org/pdf/2006.10559v2.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/f5/e7/f5e77fce83506871f5a162410783d8b734c9214c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.10559v2" 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>