arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.02024cs.LGcs.LO
收藏

验证深度学习对分布外领域的泛化能力

Verifying the Generalization of Deep Learning to Out-of-Distribution Domains

The Hebrew University of Jerusalem(耶路撒冷希伯来大学);Stanford University(斯坦福大学)

Guy Amir, Osher Maayan, Tom Zelazny, Guy Katz, Michael Schapira

AI总结:

本文提出利用DNN验证技术,通过测量独立训练网络在输入领域内的一致性来识别对分布外领域具有鲁棒泛化能力的决策规则,并在监督、无监督及深度强化学习基准上验证了其现实适用性。

摘要:

深度神经网络(DNN)在机器学习领域发挥着至关重要的作用,在众多应用领域中展现出最先进的性能。然而,尽管取得了成功,基于DNN的模型有时仍会在泛化方面遇到挑战,即可能无法处理训练期间未曾遇到的输入。当将深度学习部署用于安全关键型任务以及以显著可变性为特征的现实世界场景时,这一局限性构成重大挑战。我们提出了一种新颖的方法,利用DNN验证技术来识别对先前未遇到的输入领域表现出鲁棒泛化能力的DNN驱动决策规则。我们的方法通过测量独立训练的深度神经网络在某一输入领域内对输入的一致程度来评估该领域内的泛化能力。我们还通过使用现成的DNN验证引擎高效地实现了该方法,并在监督和无监督DNN基准上进行了广泛评估,其中包括一个用于互联网拥塞控制的深度强化学习(DRL)系统——证明了我们的方法在现实世界场景中的适用性。此外,我们的研究为形式化验证引入了一个新的目标,为缓解在现实世界场景中部署DNN驱动系统所面临的挑战提供了前景。

英文摘要:

Deep neural networks (DNNs) play a crucial role in the field of machine learning, demonstrating state-of-the-art performance across various application domains. However, despite their success, DNN-based models may occasionally exhibit challenges with generalization, i.e., may fail to handle inputs that were not encountered during training. This limitation is a significant challenge when it comes to deploying deep learning for safety-critical tasks, as well as in real-world settings characterized by substantial variability. We introduce a novel approach for harnessing DNN verification technology to identify DNN-driven decision rules that exhibit robust generalization to previously unencountered input domains. Our method assesses generalization within an input domain by measuring the level of agreement between independently trained deep neural networks for inputs in this domain. We also efficiently realize our approach by using off-the-shelf DNN verification engines, and extensively evaluate it on both supervised and unsupervised DNN benchmarks, including a deep reinforcement learning (DRL) system for Internet congestion control -- demonstrating the applicability of our approach for real-world settings. Moreover, our research introduces a fresh objective for formal verification, offering the prospect of mitigating the challenges linked to deploying DNN-driven systems in real-world scenarios.

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。

↑