arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06735cs.LGstat.ML
收藏

在不可知破坏监督下学习深度神经网络

Learning Deep Neural Networks under Agnostic Corrupted Supervision

Michigan State University(密歇根州立大学)

Boyang Liu, Mengying Sun, Ding Wang, Pang-Ning Tan, Jiayu Zhou

摘要:

在存在损坏的监督的情况下训练深度神经模型是具有挑战性的,因为损坏的数据点可能会显著影响泛化性能。为了缓解这个问题,我们提出了一种高效的鲁棒算法,该算法在不对腐败类型进行任何假设的情况下实现了强有力的保证,并为分类和回归问题提供了统一的框架。与量化数据点的质量的许多现有方法(例如,基于它们各自的损失值),并相应地对它们进行过滤,所提出的算法集中于控制数据点对平均梯度的集体影响。与基于损失值的最新过滤方法相比,即使我们的算法未能排除损坏的数据点,该数据点对整体损失的影响也非常有限。在多个基准数据集上进行的大量实验证明了该算法在不同类型的腐败下的鲁棒性。

英文摘要:

Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance. To alleviate this problem, we present an efficient robust algorithm that achieves strong guarantees without any assumption on the type of corruption and provides a unified framework for both classification and regression problems. Unlike many existing approaches that quantify the quality of the data points (e.g., based on their individual loss values), and filter them accordingly, the proposed algorithm focuses on controlling the collective impact of data points on the average gradient. Even when a corrupted data point failed to be excluded by our algorithm, the data point will have a very limited impact on the overall loss, as compared with state-of-the-art filtering methods based on loss values. Extensive experiments on multiple benchmark datasets have demonstrated the robustness of our algorithm under different types of corruption.

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。

↑