arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.08367stat.MLcs.LG
收藏

生成对抗网络的影响估计

Influence Estimation for Generative Adversarial Networks

Hitachi, Ltd.(日立制作所)

Naoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru

摘要:

识别在训练数据集中不存在的有害实例可以提高模型性能,这对于构建更好的机器学习模型非常重要。尽管以前的研究已经成功地在监督设置下估计了有害实例,但它们不能简单地扩展到生成对抗网络(GANs)。这是因为以前的方法要求(1)缺少训练实例直接影响损失值,以及(2)损失的变化直接衡量实例对模型性能的危害。然而,在GAN训练中,这两个要求都不满足。这是因为,(1)发电机的损失不直接受训练实例的影响,因为它们不是发电机训练步骤的一部分,以及(2)GAN的损失值通常不捕获模型的生成性能。为此,(1)我们提出了一种影响估计方法,该方法使用发电机损耗相对于发电机参数的梯度的雅可比矩阵(反之亦然)跟踪实例的缺失如何影响生成器的参数,以及(2)我们提出了一种新的评估方案,其中我们根据GAN评估指标(例如,初始得分)预期会由于实例的移除而改变。我们通过实验验证了我们的影响估计方法正确地推断了GAN评估指标的变化。此外,我们证明了删除已识别的有害实例有效地提高了模型在各种GAN评估指标方面的生成性能。

英文摘要:

Identifying harmful instances, whose absence in a training dataset improves model performance, is important for building better machine learning models. Although previous studies have succeeded in estimating harmful instances under supervised settings, they cannot be trivially extended to generative adversarial networks (GANs). This is because previous approaches require that (1) the absence of a training instance directly affects the loss value and that (2) the change in the loss directly measures the harmfulness of the instance for the performance of a model. In GAN training, however, neither of the requirements is satisfied. This is because, (1) the generator's loss is not directly affected by the training instances as they are not part of the generator's training steps, and (2) the values of GAN's losses normally do not capture the generative performance of a model. To this end, (1) we propose an influence estimation method that uses the Jacobian of the gradient of the generator's loss with respect to the discriminator's parameters (and vice versa) to trace how the absence of an instance in the discriminator's training affects the generator's parameters, and (2) we propose a novel evaluation scheme, in which we assess harmfulness of each training instance on the basis of how GAN evaluation metric (e.g., inception score) is expect to change due to the removal of the instance. We experimentally verified that our influence estimation method correctly inferred the changes in GAN evaluation metrics. Further, we demonstrated that the removal of the identified harmful instances effectively improved the model's generative performance with respect to various GAN evaluation metrics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑