Explaining the behavior of AI systems is an important problem that, in practice, is generally avoided. While the XAI community has been developing an abundance of techniques, most incur a set of costs that the wider deep learning community has been unwilling to pay in most situations. We take a pragmatic view of the issue, and define a set of desiderata that capture both the ambitions of XAI and the practical constraints of deep learning. We describe an effective way to satisfy all the desiderata: train the AI system to build a causal model of itself. We develop an instance of this solution for Deep RL agents: Causal Self-Talk. CST operates by training the agent to communicate with itself across time. We implement this method in a simulated 3D environment, and show how it enables agents to generate faithful and semantically-meaningful explanations of their own behavior. Beyond explanations, we also demonstrate that these learned models provide new ways of building semantic control interfaces to AI systems.
REX: Causal discovery based on machine learning and explainability techniques
BBVA Madrid, Spain(西班牙BBVA马德里);Instituto de Ciencia de Datos e Inteligencia Artificil (DATAI)(数据与人工智能研究所);University of Navarra(纳瓦拉大学);Tecnun, University of Navarra(纳瓦拉大学技术学院)
Causal Explainability of Machine Learning in Heart Failure Prediction from Electronic Health Records
Department of Computer Science(计算机科学系);Tennessee State University(田纳西州立大学);Department of Electrical and Computer Engineering(电气与计算机工程系);Department of Mathematics and Statistics(数学与统计学系);Old Dominion University(老奥尔巴尼大学)
Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAI
Insight SFI Centre for Data Analytics, School of Computer Science, University College Dublin(都柏林大学学院计算机科学学院Insight SFI数据分析中心);VistaMilk SFI Research Centre, School of Computer Science, University College Dublin(都柏林大学学院计算机科学学院VistaMilk SFI研究中心);School of Psychology and Institute of Neuroscience, Trinity College Dublin, University of Dublin(都柏林圣三一学院心理学院和神经科学研究所)
CausalStock: Deep End-to-end Causal Discovery for News-driven Stock Movement Prediction
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Peking University(北京大学);King Abdullah University of Science and Technology(阿卜杜拉国王科技大学);University of Electronic Science and Technology of China(电子科技大学)
Scientific Explanations in Health Sciences: Causality, Trust, and Epistemic Adequacy
College of Mathematical Medicine, Zhejiang Normal University(浙江师范大学数学医学院);DAIS, Ca’ Foscari University of Venice(威尼斯大学DAIS);European Centre for Living Technology(欧洲生命技术中心)
CUTS: Neural Causal Discovery from Irregular Time-Series Data
Tsinghua University(清华大学);Institute for Brain and Cognitive Science, Tsinghua University (THUIBCS)(清华大学脑与认知科学研究所);Chinese PLA General Hospital(中国人民解放军总医院)
Towards a Transportable Causal Network Model Based on Observational Healthcare Data
University of Milano - Bicocca(米兰比可卡大学);Fondazione IRCCS Istituto Nazionale dei Tumori(意大利国家肿瘤研究所(IRCCS基金会));F. Hoffmann - La Roche Ltd(罗氏公司);University of Twente(特文特大学);Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA)(达勒·莫勒人工智能研究所(IDSIA))
Causal Interventional Prediction System for Robust and Explainable Effect Forecasting
Zhejiang University(浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新区(滨江)区块链与数据安全研究院);Ant Group(蚂蚁集团);Nanyang Technological University(南洋理工大学)
A Causal Argumentation Method for Explainability of Machine Learning Models
Department of Computer Science, The University of Texas at El Paso, El Paso, TX, USA(计算机科学系,德克萨斯理工大学埃尔帕索分校);Department of Engineering Education and Leadership, The University of Texas at El Paso, El Paso, TX, USA(工程教育与领导力系,德克萨斯理工大学埃尔帕索分校)
Causal Parrots: Large Language Models May Talk Causality But Are Not Causal
TU Darmstadt(达姆施塔特工业大学);Hessian Center for AI (hessian.AI)(黑森人工智能中心);Centre for Cognitive Science, TU Darmstadt(达姆施塔特工业大学认知科学中心);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心)
TabSCM: A practical Framework for Generating Realistic Tabular Data
Federal Institute for Occupational Safety and Health (BAuA)(联邦职业安全与健康研究所);School of Computation, Information and Technology, Technical University of Munich(计算、信息与技术学院,慕尼黑技术大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心)
Modeling Endogenous Logic: Causal Neuro-Symbolic Reasoning Model for Explainable Multi-Behavior Recommendation
School of Computer Science and Engineering(计算机科学与工程学院);Nanjing University of Science and Technology(南京理工大学);School of Management(管理学院);Hefei University of Technology(合肥工业大学);School of Computer Science and Artificial Intelligence(计算机科学与人工智能学院);Nanjing University of Finance and Economics(南京财经大学);Department of Finance and Accounting(金融与会计系);Saint Petersburg State University(圣彼得堡国立大学);School of Computing(计算机学院);Macquarie University(麦考瑞大学)
Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning
Sani Analytics;Department of Biostatistics, Columbia University(生物统计学系,哥伦比亚大学);Department of Computer Science, Johns Hopkins University(计算机科学系,约翰霍普金斯大学)