[1]向许,于洪,张晓霞,等.IsomapVSG-LIME：一种新的模型无关解释方法[J].智能系统学报,2023,18(4):841-848.[doi:10.11992/tis.202209010]
XIANG Xu,YU Hong,ZHANG Xiaoxia,et al.IsomapVSG-LIME: a novel local interpretable model-agnostic explanations[J].CAAI Transactions on Intelligent Systems,2023,18(4):841-848.[doi:10.11992/tis.202209010]
点击复制
XIANG Xu,YU Hong,ZHANG Xiaoxia,et al.IsomapVSG-LIME: a novel local interpretable model-agnostic explanations[J].CAAI Transactions on Intelligent Systems,2023,18(4):841-848.[doi:10.11992/tis.202209010]
IsomapVSG-LIME：一种新的模型无关解释方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
18
期数:
2023年第4期
页码:
841-848
栏目:
人工智能院长论坛
出版日期:
2023-07-15
- Title:
- IsomapVSG-LIME: a novel local interpretable model-agnostic explanations
- 关键词:
- 局部可解释模型无关的解释; 机器学习; 等距映射虚拟样本生成; 凝聚层次聚类; 稳定性; 局部忠实性; 随机扰动采样; 特征序列稳定性指数
- Keywords:
- local interpretable model-agnostic explanations(LIME); machine learning; IsomapVSG; hierarchical agglomerative clustering; stability; local fidelity; random perturbation sampling; features sequence stability index(FSSI)
- 分类号:
- TP181
- 摘要:
- 为了解决局部可解释模型无关的解释(local interpretable model-agnostic explanations, LIME)随机扰动采样方法导致产生的解释缺乏局部忠实性和稳定性的问题，本文提出了一种新的模型无关解释方法IsomapVSG-LIME。该方法使用基于流形学习的等距映射虚拟样本生成 (isometric mapping virtual sample generation, IsomapVSG) 方法代替LIME的随机扰动采样方法来生成样本，并使用凝聚层次聚类方法从虚拟样本中选择具有代表性的样本用以训练解释模型；本文还提出了一种新的解释稳定性评价指标—特征序列稳定性指数 (features sequence stability index, FSSI)，解决了以往评价指标忽略特征的序关系和解释翻转的问题。实验结果表明，本文提出的方法在稳定性和局部忠实性上均优于现有的最新模型。
- Abstract:
- In order to solve the problem of lacking local fidelity and stability caused by local interpretable model-agnostic explanations (LIME) random perturbation sampling method, a new local interpretable model-agnostic explanation, IsomapVSG-LIME is proposed in this paper. In this method, isometric mapping virtual sample generation (IsomapVSG), a virtual sample generation method based on manifold learning, is used in substitution of random perturbation sampling method of LIME to generate samples, and aggregation hierarchical clustering method is used to select representative samples from virtual samples for training explanation model. In addition, this paper also proposes a new explanation stability evaluation index, the features sequence stability index (FSSI), which solves the problem that previous evaluation indexes ignore the sequential relationship of features and the flipping of explanations. Experimental results show that the proposed method outperforms the latest models in terms of stability and local fidelity.
- 参考文献/References:
-
[1] 纪守领, 李进锋, 杜天宇, 等. 机器学习模型可解释性方法、应用与安全研究综述[J]. 计算机研究与发展, 2019, 56(10): 2071–2096
JI Shouling, LI Jinfeng, DU Tianyu, et al. A review of interpretability methods, applications and security of machine learning models[J]. Journal of computer research and development, 2019, 56(10): 2071–2096
[2] 陈珂锐, 孟小峰. 机器学习的可解释性[J]. 计算机研究与发展, 2020, 57(9): 1971–1986
CHEN Kerui, MENG Xiaofeng. Interpretability of Machine Learning[J]. Journal of computer research and development, 2020, 57(9): 1971–1986
[3] MOLNAR C. Interpretable machine learning[M]. Raleigh: Lulu Press, 2019.
[4] 程国建,刘连宏. 机器学习的可解释性综述[J]. 智能计算机与应用, 2020, 10(5): 6–9
CHENG Guojian , LIU Lianhong. An overview of the inte rpre tability of machine learning[J]. Intelligent computer and applications, 2020, 10(5): 6–9
[5] RIBEIRO M T, SINGH S, GUESTRIN C. “why should I trust You?”: explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 1135–1144.
[6] MODHUKUR V, SHARMA S, MONDAL M, et al. Machine learning approaches to classify primary and metastatic cancers using tissue of origin-based DNA methylation profiles[J]. Cancers, 2021, 13(15): 3768.
[7] PAN Pan, LI Yichao, XIAO Yongjiu, et al. Prognostic assessment of COVID-19 in the intensive care unit by machine learning methods: model development and validation[J]. Journal of medical internet research, 2020, 22(11): e23128.
[8] SCHULTEBRAUCKS K, CHOI K W, GALATZER-LEVY I R, et al. Discriminating heterogeneous trajectories of resilience and depression after major life stressors using polygenic scores[J]. JAMA psychiatry, 2021, 78(7): 744–752.
[9] FAN Yanghua, LI Dongfang, LIU Yifan, et al. Toward better prediction of recurrence for Cushing’s disease: a factorization-machine based neural approach[J]. International journal of machine learning and cybernetics, 2021, 12(3): 625–633.
[10] NóBREGA C, MARINHO L. Towards explaining recommendations through local surrogate models[C]//Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing. New York: ACM, 2019: 1671?1678.
[11] ZHU Fan, JIANG Min, QIU Yiming, et al. RSLIME: an efficient feature importance analysis approach for industrial recommendation systems[C]//2019 International Joint Conference on Neural Networks. Piscataway: IEEE, 2019: 1?6.
[12] DARIAN M, ONCHIS. Stable and explainable deep learning damage prediction for prismatic cantilever steel beam[J]. Computers in industry, 2021, 125: 103359.
[13] PANDEY P, RAI A, MITRA M. Explainable 1-D convolutional neural network for damage detection using Lamb wave[J]. Mechanical systems and signal processing, 2022, 164: 108220.
[14] GARREAU D, LUXBURG U. Explaining the explainer: A first theoretical analysis of LIME[C]//International Conference on Artificial Intelligence and Statistics. Palermo: PMLR, 2020: 1287?1296.
[15] SLACK D, HILGARD S, JIA E, et al. Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods[C]//Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. New York: ACM, 2020: 180?186.
[16] RAHNAMA A H A, BOSTR?M H. A study of data and label shift in the LIME framework[EB/OL].(2019-10-31)[2022-09-06].https://arxiv.org/abs/1910.14421.
[17] ZAFAR M R, KHAN N. Deterministic local interpretable model-agnostic explanations for stable explainability[J]. Machine learning and knowledge extraction, 2021, 3(3): 525–541.
[18] ZHAO Xingyu, HUANG Wei, HUANG Xiaowei, et al. Baylime: Bayesian local interpretable model-agnostic explanations[C]//Uncertainty in Artificial Intelligence.Toronto: PMLR, 2021: 887?896.
[19] SHANKARANARAYANA S M, RUNJE D. ALIME: autoencoder based approach for local interpretability[M]. Cham: Springer International Publishing, 2019: 454?463.
[20] ZHOU Zhengze, HOOKER G, WANG Fei. S-LIME: stabilized-LIME for model explanation[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. New York: ACM, 2021: 2429?2438.
[21] VISANI G, BAGLI E, CHESANI F, et al. Statistical stability indices for LIME: obtaining reliable explanations for machine learning models[J]. Journal of the operational research society, 2022, 73(1): 91–101.
[22] ZHANG Xiaohan, XU Yuan, HE Yanlin, et al. Novel manifold learning based virtual sample generation for optimizing soft sensor with small data[J]. ISA transactions, 2021, 109: 229–241.
[23] TENENBAUM J B, DE SILVA V, LANGFORD J C. A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290(5500): 2319–2323.
[24] HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]//2004 IEEE International Joint Conference on Neural Networks. Piscataway: IEEE, 2005: 985?990.
[25] RASOULI P, YU I C. EXPLAN: explaining black-box classifiers using adaptive neighborhood generation[C]//2020 International Joint Conference on Neural Networks . Piscataway: IEEE, 2020: 1-9.
[26] BREIMAN L. Random forests[J]. Machine learning, 2001, 45(1): 5–32.
- 相似文献/References:
-
[1]叶志飞,文益民,吕宝粮.不平衡分类问题研究综述[J].智能系统学报,2009,4(2):148.
YE Zhi-fei,WEN Yi-min,LU Bao-liang.A survey of imbalanced pattern classification problems[J].CAAI Transactions on Intelligent Systems,2009,4():148.
[2]刘奕群,张 敏,马少平.基于非内容信息的网络关键资源有效定位[J].智能系统学报,2007,2(1):45.
LIU Yi-qun,ZHANG Min,MA Shao-ping.Web key resource page selection based on non-content inf o rmation[J].CAAI Transactions on Intelligent Systems,2007,2():45.
[3]马世龙,眭跃飞,许 可.优先归纳逻辑程序的极限行为[J].智能系统学报,2007,2(4):9.
MA Shi-long,SUI Yue-fei,XU Ke.Limit behavior of prioritized inductive logic programs[J].CAAI Transactions on Intelligent Systems,2007,2():9.
[4]姚伏天,钱沄涛.高斯过程及其在高光谱图像分类中的应用[J].智能系统学报,2011,6(5):396.
YAO Futian,QIAN Yuntao.Gaussian process and its applications in hyperspectral image classification[J].CAAI Transactions on Intelligent Systems,2011,6():396.
[5]文益民,强保华,范志刚.概念漂移数据流分类研究综述[J].智能系统学报,2013,8(2):95.[doi:10.3969/j.issn.1673-4785.201208012]
WEN Yimin,QIANG Baohua,FAN Zhigang.A survey of the classification of data streams with concept drift[J].CAAI Transactions on Intelligent Systems,2013,8():95.[doi:10.3969/j.issn.1673-4785.201208012]
[6]杨成东,邓廷权.综合属性选择和删除的属性约简方法[J].智能系统学报,2013,8(2):183.[doi:10.3969/j.issn.1673-4785.201209056]
YANG Chengdong,DENG Tingquan.An approach to attribute reduction combining attribute selection and deletion[J].CAAI Transactions on Intelligent Systems,2013,8():183.[doi:10.3969/j.issn.1673-4785.201209056]
[7]胡小生,钟勇.基于加权聚类质心的SVM不平衡分类方法[J].智能系统学报,2013,8(3):261.
HU Xiaosheng,ZHONG Yong.Support vector machine imbalanced data classification based on weighted clustering centroid[J].CAAI Transactions on Intelligent Systems,2013,8():261.
[8]丁科,谭营.GPU通用计算及其在计算智能领域的应用[J].智能系统学报,2015,10(1):1.[doi:10.3969/j.issn.1673-4785.201403072]
DING Ke,TAN Ying.A review on general purpose computing on GPUs and its applications in computational intelligence[J].CAAI Transactions on Intelligent Systems,2015,10():1.[doi:10.3969/j.issn.1673-4785.201403072]
[9]孔庆超,毛文吉,张育浩.社交网站中用户评论行为预测[J].智能系统学报,2015,10(3):349.[doi:10.3969/j.issn.1673-4785.201403019]
KONG Qingchao,MAO Wenji,ZHANG Yuhao.User comment behavior prediction in social networking sites[J].CAAI Transactions on Intelligent Systems,2015,10():349.[doi:10.3969/j.issn.1673-4785.201403019]
[10]姚霖,刘轶,李鑫鑫,等.词边界字向量的中文命名实体识别[J].智能系统学报,2016,11(1):37.[doi:10.11992/tis.201507065]
YAO Lin,LIU Yi,LI Xinxin,et al.Chinese named entity recognition via word boundarybased character embedding[J].CAAI Transactions on Intelligent Systems,2016,11():37.[doi:10.11992/tis.201507065]
备注/Memo
收稿日期:2022-09-06。
基金项目:国家自然科学基金项目(62136002，61876027)；重庆英才计划项目(cstc2022ycjh-bgzxm0004).
作者简介:向许，硕士研究生，主要研究方向为可解释机器学习;于洪，教授，博士生导师，主要研究方向为三支决策、粗糙集、粒计算、认知计算、聚类分析和可信人工智能。主持国家自然科学基金项目10余项。发表学术论文100余篇，出版专著5部;王国胤，教授，博士生导师，国家级人才，重庆邮电大学副校长，主要研究方向为粗糙集、粒计算、数据挖掘、认知计算、大数据、人工智能。授权发明专利20项。发表学术论文300余篇，出版专著23部。
通讯作者:于洪.E-mail:yuhong@cqupt.edu.cn
更新日期/Last Update:
1900-01-01