一句话：提出 Apricot，从原模型生成约简模型，基于失败测试用例调整权重，迭代修复深度学习模型，平均提升测试准确率 1.08%。
深度学习模型本质上不精确，现有修复方法依赖更大训练集、故障注入模型或失败测试用例的洞察。本文提出 Apricot，一种迭代的权重自适应方法。其关键观察是：将原模型架构在原始训练集的多个不同子集上训练，所得约简模型（rDLM）的权重可揭示原模型权重的调整方向与幅度。Apricot 对每个误分类测试用例，将原模型（iDLM）的每个权重朝正确分类该用例的 rDLM 的平均权重调整，并远离误分类该用例的 rDLM 的平均权重，再在原始训练集上训练调整后的模型以进入下一轮。在五个先进模型上，Apricot 将测试准确率提升 0.87%–1.55%，平均 1.08%，并揭示了 rDLM 的互补性。
A deep learning (DL) model is inherently imprecise. To address this problem, existing techniques retrain a DL model over a larger training dataset or with the help of fault injected models or using the insight of failing test cases in a DL model. In this paper, we present Apricot, a novel weight-adaptation approach to fixing DL models iteratively. Our key observation is that if the deep learning architecture of a DL model is trained over many different subsets of the original training dataset, the weights in the resultant reduced DL model (rDLM) can provide insights on the adjustment direction and magnitude of the weights in the original DL model to handle the test cases that the original DL model misclassifies. Apricot generates a set of such reduced DL models from the original DL model. In each iteration, for each failing test case experienced by the input DL model (iDLM), Apricot adjusts each weight of this iDLM toward the average weight of these rDLMs correctly classifying the test case and/or away from that of these rDLMs misclassifying the same test case, followed by training the weight-adjusted iDLM over the original training dataset to generate a new iDLM for the next iteration. The experiment using five state-of-the-art DL models shows that Apricot can increase the test accuracy of these models by 0.87%-1.55% with an average of 1.08%. The experiment also reveals the complementary nature of these rDLMs in Apricot.
DOI 原文 ·
@inproceedings{paperbot5310,
title = {Apricot: A Weight-Adaptation Approach to Fixing Deep Learning Models},
author = {Hao Zhang and W.K. Chan},
booktitle = {ASE},
year = {2019},
doi = {10.1109/ase.2019.00043}
}