FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
复制标题
DOI：
10.1109/iccv48922.2021.01202
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Xiangxiang Chu;Bo Zhang;Ruijun Xu;Jixiang Li
中科院分区：
文献类型：
--
作者：
Xiangxiang Chu;Bo Zhang;Ruijun Xu;Jixiang Li
加权神经结构搜索中最关键的问题之一是在预先定义的搜索空间内对候选模型进行评估。在实践中，一次成功的超级网络被训练成评估者。一个忠实的排名肯定会带来更准确的搜索结果。然而，目前的方法容易产生误判。在本文中，我们证明了他们的偏见评价是由于超网训练中固有的不公平所致。有鉴于此，我们提出了两个层面的约束：期望公平和严格公平。特别是，严格的公平性确保了在整个训练过程中所有选择块的优化机会均等，这既不高估也不低估它们的能力。我们证明这对于提高模型排序的置信度是至关重要的。将提出的公平性约束下训练的一次超网与多目标进化搜索算法相结合，得到了各种最先进的模型，例如FairNAS-A在ImageNet上的TOP-1验证正确率达到了77.5%。
One of the most critical problems in weight-sharing neural architecture search is the evaluation of candidate models within a predefined search space. In practice, a one-shot supernet is trained to serve as an evaluator. A faithful ranking certainly leads to more accurate searching results. However, current methods are prone to making misjudgments. In this paper, we prove that their biased evaluation is due to inherent unfairness in the supernet training. In view of this, we propose two levels of constraints: expectation fairness and strict fairness. Particularly, strict fairness ensures equal optimization opportunities for all choice blocks throughout the training, which neither overestimates nor underestimates their capacity. We demonstrate that this is crucial for improving the confidence of models’ ranking. Incorporating the one-shot supernet trained under the proposed fairness constraints with a multi-objective evolutionary search algorithm, we obtain various state-of-the-art models, e.g., FairNAS-A attains 77.5% top-1 validation accuracy on ImageNet.