arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00120cs.LGcs.CRstat.ML
收藏

通过结合逻辑推理的统计学习提升可认证鲁棒性

Improving Certified Robustness via Statistical Learning with Logical Reasoning

UIUC(伊利诺伊大学厄巴纳-香槟分校);ETH Zürich(苏黎世联邦理工学院);Kwai Inc.(快手公司);University of Edinburgh(爱丁堡大学)

Zhuolin Yang, Zhikuan Zhao, Boxin Wang, Jiawei Zhang, Linyi Li, Hengzhi Pei, Bojan Karlas, Ji Liu, Heng Guo, Ce Zhang, Bo Li

AI总结:

本文针对纯数据驱动方法在可认证鲁棒性上的瓶颈,提出将统计学习与马尔可夫逻辑网络中的逻辑知识推理相结合,并首次给出 MLN 鲁棒性认证的 #P-hard 复杂度证明及可认证鲁棒性界,实验表明该方法显著优于现有最优方法。

摘要:

近年来,为了推动复杂机器学习模型可认证鲁棒性的快速提升,人们开展了大量算法层面的工作。然而,当前的鲁棒性认证方法只能在有限的扰动半径内进行认证。鉴于现有纯数据驱动的统计方法已经达到瓶颈,本文提出将统计机器学习模型与以逻辑规则表示的知识相结合,利用马尔可夫逻辑网络(MLN)作为推理组件,从而进一步提升整体可认证鲁棒性。这为认证此类范式的鲁棒性开辟了新的研究问题,尤其是针对推理组件(例如 MLN)的鲁棒性认证。作为理解这些问题的第一步,我们首先证明了认证 MLN 鲁棒性的计算复杂度是 #P-hard。基于这一困难性结果,我们通过仔细分析不同模型机制,推导出首个针对 MLN 的可认证鲁棒性界。最后,我们在五个数据集上进行了大量实验,包括高维图像和自然语言文本,结果表明,结合基于知识的逻辑推理所获得的可认证鲁棒性显著优于当前最先进方法。

英文摘要:

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation radius. Given that existing pure data-driven statistical approaches have reached a bottleneck, in this paper, we propose to integrate statistical ML models with knowledge (expressed as logical rules) as a reasoning component using Markov logic networks (MLN, so as to further improve the overall certified robustness. This opens new research questions about certifying the robustness of such a paradigm, especially the reasoning component (e.g., MLN). As the first step towards understanding these questions, we first prove that the computational complexity of certifying the robustness of MLN is #P-hard. Guided by this hardness result, we then derive the first certified robustness bound for MLN by carefully analyzing different model regimes. Finally, we conduct extensive experiments on five datasets including both high-dimensional images and natural language texts, and we show that the certified robustness with knowledge-based logical reasoning indeed significantly outperforms that of the state-of-the-arts.

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。

↑