Semi-Supervised Learning with Meta-Gradient [article]

Xin-Yu Zhang, Taihong Xiao, Haolin Jia, Ming-Ming Cheng, Ming-Hsuan Yang
<span title="2021-03-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning. We notice that most existing consistency-based approaches suffer from overfitting and limited model generalization ability, especially when training with only a small number of labeled data. To alleviate this issue, we propose a learn-to-generalize regularization term by utilizing the label information and optimize the problem in a meta-learning fashion. Specifically, we seek the pseudo labels
more &raquo; ... the unlabeled data so that the model can generalize well on the labeled data, which is formulated as a nested optimization problem. We address this problem using the meta-gradient that bridges between the pseudo label and the regularization term. In addition, we introduce a simple first-order approximation to avoid computing higher-order derivatives and provide theoretic convergence analysis. Extensive evaluations on the SVHN, CIFAR, and ImageNet datasets demonstrate that the proposed algorithm performs favorably against state-of-the-art methods.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03966v2">arXiv:2007.03966v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wls2mkzn4nb7dhgyzk5dtjq4km">fatcat:wls2mkzn4nb7dhgyzk5dtjq4km</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831214855/https://arxiv.org/pdf/2007.03966v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c4/70/c470c98b140dd2810657e78decb403a3cea504f7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03966v2" 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>