A Survey of Data-driven and Knowledge-aware eXplainable AI. Li, X., Cao, C. C., Shi, Y., Bai, W., Gao, H., Qiu, L., Wang, C., Gao, Y., Zhang, S., Xue, X., & Chen, L. IEEE Transactions on Knowledge and Data Engineering, 2020. Conference Name: IEEE Transactions on Knowledge and Data Engineeringdoi abstract bibtex We are witnessing a fast development of Artificial Intelligence (AI), but it becomes dramatically challenging to explain AI models in the past decade. “Explanation” has a flexible philosophical concept of “satisfying the subjective curiosity for causal information”, driving a wide spectrum of methods being invented and/or adapted from many aspects and communities, including machine learning, visual analytics, human-computer interaction and so on. Nevertheless, from the view-point of data and knowledge engineering (DKE), a best explaining practice that is cost-effective in terms of extra intelligence acquisition should exploit the causal information and scenarios which is hidden richly in the data itself. In the past several years, there are plenty of works contributing in this line but there is a lack of a clear taxonomy and systematic review of the current effort. To this end, we propose this survey, reviewing and taxonomizing existing efforts from the view-point of DKE, summarizing their contribution, technical essence and comparative characteristics. Specifically, we categorize methods into data-driven methods where explanation comes from the task-related data, and knowledge-aware methods where extraneous knowledge is incorporated. Furthermore, in the light of practice, we provide survey of state-of-art evaluation metrics and deployed explanation applications in industrial practice.
@article{li_survey_2020,
title = {A {Survey} of {Data}-driven and {Knowledge}-aware {eXplainable} {AI}},
issn = {1558-2191},
doi = {10.1109/TKDE.2020.2983930},
abstract = {We are witnessing a fast development of Artificial Intelligence (AI), but it becomes dramatically challenging to explain AI models in the past decade. “Explanation” has a flexible philosophical concept of “satisfying the subjective curiosity for causal information”, driving a wide spectrum of methods being invented and/or adapted from many aspects and communities, including machine learning, visual analytics, human-computer interaction and so on. Nevertheless, from the view-point of data and knowledge engineering (DKE), a best explaining practice that is cost-effective in terms of extra intelligence acquisition should exploit the causal information and scenarios which is hidden richly in the data itself. In the past several years, there are plenty of works contributing in this line but there is a lack of a clear taxonomy and systematic review of the current effort. To this end, we propose this survey, reviewing and taxonomizing existing efforts from the view-point of DKE, summarizing their contribution, technical essence and comparative characteristics. Specifically, we categorize methods into data-driven methods where explanation comes from the task-related data, and knowledge-aware methods where extraneous knowledge is incorporated. Furthermore, in the light of practice, we provide survey of state-of-art evaluation metrics and deployed explanation applications in industrial practice.},
journal = {IEEE Transactions on Knowledge and Data Engineering},
author = {Li, Xiao-Hui and Cao, Caleb Chen and Shi, Yuhan and Bai, Wei and Gao, Han and Qiu, Luyu and Wang, Cong and Gao, Yuanyuan and Zhang, Shenjia and Xue, Xun and Chen, Lei},
year = {2020},
note = {Conference Name: IEEE Transactions on Knowledge and Data Engineering},
keywords = {Algorithms, Data models, Data visualization, Deep Learning, Explainable AI (XAI), Feature extraction, Knowledge-base, Metrics, Predictive models, Task analysis, Taxonomy},
pages = {1--1},
}
Downloads: 0
{"_id":"DQEusZftmNyqzSFuo","bibbaseid":"li-cao-shi-bai-gao-qiu-wang-gao-etal-asurveyofdatadrivenandknowledgeawareexplainableai-2020","author_short":["Li, X.","Cao, C. C.","Shi, Y.","Bai, W.","Gao, H.","Qiu, L.","Wang, C.","Gao, Y.","Zhang, S.","Xue, X.","Chen, L."],"bibdata":{"bibtype":"article","type":"article","title":"A Survey of Data-driven and Knowledge-aware eXplainable AI","issn":"1558-2191","doi":"10.1109/TKDE.2020.2983930","abstract":"We are witnessing a fast development of Artificial Intelligence (AI), but it becomes dramatically challenging to explain AI models in the past decade. “Explanation” has a flexible philosophical concept of “satisfying the subjective curiosity for causal information”, driving a wide spectrum of methods being invented and/or adapted from many aspects and communities, including machine learning, visual analytics, human-computer interaction and so on. Nevertheless, from the view-point of data and knowledge engineering (DKE), a best explaining practice that is cost-effective in terms of extra intelligence acquisition should exploit the causal information and scenarios which is hidden richly in the data itself. In the past several years, there are plenty of works contributing in this line but there is a lack of a clear taxonomy and systematic review of the current effort. To this end, we propose this survey, reviewing and taxonomizing existing efforts from the view-point of DKE, summarizing their contribution, technical essence and comparative characteristics. Specifically, we categorize methods into data-driven methods where explanation comes from the task-related data, and knowledge-aware methods where extraneous knowledge is incorporated. Furthermore, in the light of practice, we provide survey of state-of-art evaluation metrics and deployed explanation applications in industrial practice.","journal":"IEEE Transactions on Knowledge and Data Engineering","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Xiao-Hui"],"suffixes":[]},{"propositions":[],"lastnames":["Cao"],"firstnames":["Caleb","Chen"],"suffixes":[]},{"propositions":[],"lastnames":["Shi"],"firstnames":["Yuhan"],"suffixes":[]},{"propositions":[],"lastnames":["Bai"],"firstnames":["Wei"],"suffixes":[]},{"propositions":[],"lastnames":["Gao"],"firstnames":["Han"],"suffixes":[]},{"propositions":[],"lastnames":["Qiu"],"firstnames":["Luyu"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Cong"],"suffixes":[]},{"propositions":[],"lastnames":["Gao"],"firstnames":["Yuanyuan"],"suffixes":[]},{"propositions":[],"lastnames":["Zhang"],"firstnames":["Shenjia"],"suffixes":[]},{"propositions":[],"lastnames":["Xue"],"firstnames":["Xun"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Lei"],"suffixes":[]}],"year":"2020","note":"Conference Name: IEEE Transactions on Knowledge and Data Engineering","keywords":"Algorithms, Data models, Data visualization, Deep Learning, Explainable AI (XAI), Feature extraction, Knowledge-base, Metrics, Predictive models, Task analysis, Taxonomy","pages":"1–1","bibtex":"@article{li_survey_2020,\n\ttitle = {A {Survey} of {Data}-driven and {Knowledge}-aware {eXplainable} {AI}},\n\tissn = {1558-2191},\n\tdoi = {10.1109/TKDE.2020.2983930},\n\tabstract = {We are witnessing a fast development of Artificial Intelligence (AI), but it becomes dramatically challenging to explain AI models in the past decade. “Explanation” has a flexible philosophical concept of “satisfying the subjective curiosity for causal information”, driving a wide spectrum of methods being invented and/or adapted from many aspects and communities, including machine learning, visual analytics, human-computer interaction and so on. Nevertheless, from the view-point of data and knowledge engineering (DKE), a best explaining practice that is cost-effective in terms of extra intelligence acquisition should exploit the causal information and scenarios which is hidden richly in the data itself. In the past several years, there are plenty of works contributing in this line but there is a lack of a clear taxonomy and systematic review of the current effort. To this end, we propose this survey, reviewing and taxonomizing existing efforts from the view-point of DKE, summarizing their contribution, technical essence and comparative characteristics. Specifically, we categorize methods into data-driven methods where explanation comes from the task-related data, and knowledge-aware methods where extraneous knowledge is incorporated. Furthermore, in the light of practice, we provide survey of state-of-art evaluation metrics and deployed explanation applications in industrial practice.},\n\tjournal = {IEEE Transactions on Knowledge and Data Engineering},\n\tauthor = {Li, Xiao-Hui and Cao, Caleb Chen and Shi, Yuhan and Bai, Wei and Gao, Han and Qiu, Luyu and Wang, Cong and Gao, Yuanyuan and Zhang, Shenjia and Xue, Xun and Chen, Lei},\n\tyear = {2020},\n\tnote = {Conference Name: IEEE Transactions on Knowledge and Data Engineering},\n\tkeywords = {Algorithms, Data models, Data visualization, Deep Learning, Explainable AI (XAI), Feature extraction, Knowledge-base, Metrics, Predictive models, Task analysis, Taxonomy},\n\tpages = {1--1},\n}\n\n\n\n","author_short":["Li, X.","Cao, C. C.","Shi, Y.","Bai, W.","Gao, H.","Qiu, L.","Wang, C.","Gao, Y.","Zhang, S.","Xue, X.","Chen, L."],"key":"li_survey_2020","id":"li_survey_2020","bibbaseid":"li-cao-shi-bai-gao-qiu-wang-gao-etal-asurveyofdatadrivenandknowledgeawareexplainableai-2020","role":"author","urls":{},"keyword":["Algorithms","Data models","Data visualization","Deep Learning","Explainable AI (XAI)","Feature extraction","Knowledge-base","Metrics","Predictive models","Task analysis","Taxonomy"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"],"keywords":["algorithms","data models","data visualization","deep learning","explainable ai (xai)","feature extraction","knowledge-base","metrics","predictive models","task analysis","taxonomy"],"search_terms":["survey","data","driven","knowledge","aware","explainable","li","cao","shi","bai","gao","qiu","wang","gao","zhang","xue","chen"],"title":"A Survey of Data-driven and Knowledge-aware eXplainable AI","year":2020}