{"type":"ScholarlyArticle","title":"Bridging Causality and Learning: How Do They Benefit from Each Other?","authors":[{"name":"Mingming Gong","slug":"mingming-gong","given":"Mingming","family":"Gong","affiliation":"School of Mathematics and Statistics , University of Melbourne , Australia"}],"abstract":"Modern machine learning techniques can discover complicated statistical dependencies between ran- dom variables, usually in the form a statistical model, and make use of these dependencies to per- form predictions on future observations. How- ever, many real problems involve causal inference, which aims to infer how the data generating sys- tem should behave under changing conditions. To perform causal inference, we need not only statisti- cal dependencies but also causal structures to deter- mine the system’s behavior under external interven- tions. In this paper, I will be focusing on two essen- tial problems that bridge causality and learning and investigate how they can benefit from each other. On the one hand, since conducting randomized controlled experiments for causal structure discov- ery is often expensive or infeasible, it would be valuable to investigate how we can explore modern machine learning algorithms to search for causal structures from observational data. On the other hand, since causal structure provides information about the distribution changing properties, it can be used as a fundamental tool to tackle a major chal- lenge for machine learning: the capability of gener- alization to new distributions and prediction in non- stationary environment.","doi":"10.24963/ijcai.2020/725","url":"https://ijcai.org/proceedings/2020/725","pdf":"https://ijcai.org/proceedings/2020/0725.pdf","markdown":"https://ijcai.org/proceedings/2020/725.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/725","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Early Career","track":"Early Career","number":725,"pages":{"first":5150,"last":5153},"keywords":["Knowledge Representation and Reasoning: Action, Change and Causality","Uncertainty in AI: Graphical Models"],"videos":[],"references":[{"position":1,"raw":"[Chenwei et al., 2019] DING Chenwei, Mingming Gong, Kun Zhang, and Dacheng Tao. Likelihood-free overcom- plete ica and applications in causal discovery. In Advances in Neural Information Processing Systems, pages 6880- 6890, 2019.","title":"Likelihood-free overcomplete ica and applications in causal discovery","authors":"Chenwei","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chickering, 2002] David Maxwell Chickering. Optimal structure identification with greedy search. Journal of ma- chine learning research, 3(Nov):507-554, 2002.","title":"Optimal structure identification with greedy search","authors":"David Chickering, Chickering Maxwell","year":"2002","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Geiger et al., 2015] Philipp Geiger, Kun Zhang, Bernhard Schoelkopf, Mingming Gong, and Dominik Janzing. Causal inference by identification of vector autoregressive processes with hidden components. In International Con- ference on Machine Learning, pages 1917-1925, 2015.","title":"Causal inference by identification of vector autoregressive processes with hidden components","authors":"Philipp Geiger, Kun Zhang, Bernhard Schoelkopf, Mingming Gong, Dominik Janzing","year":"2015","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gong* et al., 2015] M. Gong*, K. Zhang*, D. Tao, P. Geiger, and B. Schölkopf. Discovering temporal causal relations from subsampled data. In Proc. 32th Interna- tional Conference on Machine Learning (ICML 2015), 2015.","title":"Discovering temporal causal relations from subsampled data","authors":"M Gong, *, K Zhang, *, D Tao, P Geiger, B Schölkopf","year":"2015","venue":"Proc. 32th International Conference on Machine Learning (ICML 2015)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gong et al., 2016] M. Gong, K. Zhang, T. Liu, D. Tao, C. Glymour, and B. Schölkopf. Domain adaptation with conditional transferable components. In Proceedings of the 33nd International Conference on Machine Learning (ICML 2016), volume 48, pages 2839-2848, 2016.","title":"Domain adaptation with conditional transferable components","authors":"M Gong, K Zhang, T Liu, D Tao, C Glymour, B Schölkopf","year":"2016","venue":"Proceedings of the 33nd International Conference on Machine Learning (ICML 2016)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gong et al., 2017] Mingming Gong, Kun Zhang, Bernhard Schölkopf, Clark Glymour, and Dacheng Tao. Causal dis- covery from temporally aggregated time series. In Un- certainty in artificial intelligence: proceedings of the... conference. Conference on Uncertainty in Artificial Intel- ligence, volume 2017. NIH Public Access, 2017.","title":"Causal discovery from temporally aggregated time series","authors":"Mingming Gong, Kun Zhang, Bernhard Schölkopf, Clark Glymour, Dacheng Tao","year":"2017","venue":"conference. Conference on Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gong et al., 2018] Mingming Gong, Kun Zhang, Biwei Huang, Clark Glymour, Dacheng Tao, and Kayhan Bat- manghelich. Causal generative domain adaptation net- works. arXiv preprint arXiv:1804.04333, 2018.","title":"Causal generative domain adaptation networks","authors":"Mingming Gong, Kun Zhang, Biwei Huang, Clark Glymour, Dacheng Tao, Kayhan Batmanghelich","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Granger, 1969] Clive WJ Granger. Investigating causal rela- tions by econometric models and cross-spectral methods. Econometrica: Journal of the Econometric Society, pages 424-438, 1969.","title":"Investigating causal relations by econometric models and cross-spectral methods","authors":"Clive Wj Granger","year":"1969","venue":"Econometrica: Journal of the Econometric Society","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hannun et al., 2014] Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, et al. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567, 2014.","title":"Deep speech: Scaling up end-to-end speech recognition","authors":"Awni Hannun, Carl Case, Jared Casper, Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[He et al., 2015] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. arXiv preprint arXiv:1512.03385, 2015.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huang et al., 2018] Biwei Huang, Kun Zhang, Yizhu Lin, Bernhard Schölkopf, and Clark Glymour. Generalized score functions for causal discovery. In Proceedings of the 24th ACM SIGKDD International Conference on Knowl- edge Discovery & Data Mining, pages 1551-1560, 2018.","title":"Generalized score functions for causal discovery","authors":"Huang","year":"2018","venue":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Huang et al., 2019] Biwei Huang, Kun Zhang, Mingming Gong, and Clark Glymour. Causal discovery and forecast- ing in nonstationary environments with state-space mod- els. Proceedings of machine learning research, 97:2901, 2019.","title":"Causal discovery and forecasting in nonstationary environments with state-space models","authors":"Huang","year":"2019","venue":"Proceedings of machine learning research","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jaber et al., 2019] Amin Jaber, Jiji Zhang, and Elias Barein- boim. Identification of conditional causal effects under markov equivalence. In Advances in Neural Information Processing Systems, pages 11512-11520, 2019.","title":"Identification of conditional causal effects under markov equivalence","authors":"Amin Jaber, Jiji Zhang, Elias Bareinboim","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Koller and Friedman, 2009] D. Koller and N. Friedman. Probabilistic Graphical Models: Principles and Tech- niques. MIT Press, Cambridge, MA, 2009.","title":"Probabilistic Graphical Models: Principles and Techniques","authors":"D Koller, N Friedman","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pearl and others, 2009] Judea Pearl et al. Causal inference in statistics: An overview. Statistics Surveys, 3:96-146, 2009.","title":"Judea Pearl et al. Causal inference in statistics: An overview","authors":"Others Pearl","year":"2009","venue":"Statistics Surveys","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pearl, 1994] Judea Pearl. A probabilistic calculus of ac- tions. In Proceedings of the Tenth international conference on Uncertainty in artificial intelligence, pages 454-462.","title":"Judea Pearl. A probabilistic calculus of actions","authors":"Pearl","year":"1994","venue":"Proceedings of the Tenth international conference on Uncertainty in artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pearl, 2000] J. Pearl. Causality: Models, Reasoning, and Inference. Cambridge University Press, Cambridge, 2000.","title":"Causality: Models, Reasoning, and Inference","authors":"J Pearl","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rubin, 2005] Donald B Rubin. Causal inference using po- tential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469):322-331, 2005.","title":"Causal inference using potential outcomes: Design, modeling, decisions","authors":"Donald B Rubin","year":"2005","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schölkopf, 2019] Bernhard Schölkopf. Causality for ma- chine learning. arXiv preprint arXiv:1911.10500, 2019.","title":"Causality for machine learning","authors":"Bernhard Schölkopf","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shpitser and Pearl, 2006] Ilya Shpitser and Judea Pearl. Identification of joint interventional distributions in recur- sive semi-markovian causal models. In 21st National Con- ference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI- 06/IAAI-06, pages 1219-1226, 2006.","title":"Ilya Shpitser and Judea Pearl. Identification of joint interventional distributions in recursive semi-markovian causal models","authors":"Pearl Shpitser","year":"2006","venue":"21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Silver et al., 2016] David Silver, Aja Huang, Chris J Maddi- son, Arthur Guez, Laurent Sifre, George Van Den Driess- che, Julian Schrittwieser, Ioannis Antonoglou, Veda Pan- neershelvam, Marc Lanctot, et al. Mastering the game of go with deep neural networks and tree search. Nature, 529(7587):484-489, 2016.","title":"Mastering the game of go with deep neural networks and tree search","authors":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den, Marc Driessche, Lanctot","year":"2016","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sims, 1980] C. A. Sims. Macroeconomics and reality. Econometrica, 48:1-48, 1980.","title":"Macroeconomics and reality","authors":"C A Sims","year":"1980","venue":"Econometrica","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Spirtes et al., 2001] P. Spirtes, C. Glymour, and R. Scheines. Causation, Prediction, and Search. MIT Press, Cambridge, MA, 2nd edition, 2001.","title":"Causation, Prediction, and Search","authors":"P Spirtes, C Glymour, R Scheines","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Szegedy et al., 2015] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabi- novich. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1-9, 2015.","title":"Going deeper with convolutions","authors":"Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich","year":"2015","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tian and Pearl, 2002] Jin Tian and Judea Pearl. A general identification condition for causal effects. In Aaai/iaai, pages 567-573, 2002.","title":"A general identification condition for causal effects","authors":"Pearl ; Tian, Jin Tian, Judea Pearl","year":"2002","venue":"Aaai/iaai","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhang et al., 2015] K. Zhang, M. Gong, and B. Schölkopf. Multi-source domain adaptation: A causal view. In Pro- ceedings of the Twenty-Ninth AAAI Conference on Artifi- cial Intelligence, pages 3150-3157. AAAI Press, 2015.","title":"Multi-source domain adaptation: A causal view","authors":"K Zhang, M Gong, B Schölkopf","year":"2015","venue":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhang et al., 2020] Kun Zhang, Mingming Gong, Petar Sto- janov, Biwei Huang, and Clark Glymour. Domain adapta- tion as a problem of inference on graphical models. arXiv preprint arXiv:2002.03278, 2020.","title":"Domain adaptation as a problem of inference on graphical models","authors":"Kun Zhang, Mingming Gong, Petar Stojanov, Biwei Huang, Clark Glymour","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhu and Chen, 2019] Shengyu Zhu and Zhitang Chen. Causal discovery with reinforcement learning. arXiv preprint arXiv:1906.04477, 2019.","title":"Causal discovery with reinforcement learning","authors":"Chen ; Zhu, Shengyu Zhu, Zhitang Chen","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}