{"type":"ScholarlyArticle","title":"Non-Cheating Teaching Revisited: A New Probabilistic Machine Teaching Model","authors":[{"name":"Cèsar Ferri","slug":"cesar-ferri","given":"Cèsar","family":"Ferri","affiliation":"VRAIN , Universitat Politècnica de València , Spain."},{"name":"José Hernández-Orallo","slug":"jose-hernandez-orallo","given":"José","family":"Hernández-Orallo","affiliation":"VRAIN , Universitat Politècnica de València , Spain."},{"name":"Jan Arne Telle","slug":"jan-arne-telle","given":"Jan Arne","family":"Telle","affiliation":"Department of Informatics , University of Bergen , Norway."}],"abstract":"Over the past decades in the field of machine teaching, several restrictions have been  introduced to avoid ‘cheating’, such as collusion-free or non-clashing teaching. However, these restrictions forbid several teaching situations  that  we  intuitively consider natural and fair, especially those ‘changes of mind’ of the learner as more evidence is given, affecting the likelihood of concepts and ultimately their  posteriors. Under a new generalised probabilistic teaching, not only do these non-cheating constraints look too narrow but we also show that the most relevant machine teaching models are particular cases of this framework: the consistency graph between concepts and elements simply becomes a joint probability distribution. We show a simple procedure that builds the witness joint distribution from the ground joint distribution. We prove a chain of relations, also with a theoretical lower bound, on the teaching dimension of the old and new models. Overall, this new setting is more general than the traditional machine teaching models, yet at the same time more intuitively capturing a less abrupt notion of non-cheating teaching.","doi":"10.24963/ijcai.2022/412","url":"https://ijcai.org/proceedings/2022/412","pdf":"https://ijcai.org/proceedings/2022/0412.pdf","markdown":"https://ijcai.org/proceedings/2022/412.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/412","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":412,"pages":{"first":2973,"last":2979},"keywords":["Machine Learning: Learning Theory","Machine Learning: Probabilistic Machine Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986834","length_sec":32,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984977","length_sec":364,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Balbach, 2008] Frank J Balbach. Measuring teachability us- ing variants of the teaching dimension. Theoretical Com- puter Science, 397(1-3):94-113, 2008.","title":"Measuring teachability using variants of the teaching dimension","authors":"J Frank, Balbach","year":"2008","venue":"Theoretical Computer Science","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Doliwa et al., 2010] Thorsten Doliwa, Hans Ulrich Simon, and Sandra Zilles. Recursive teaching dimension, learning complexity, and maximum classes. In International Con- ference on Algorithmic Learning Theory, pages 209-223. Springer, 2010.","title":"Recursive teaching dimension, learning complexity, and maximum classes","authors":"Thorsten Doliwa, Hans Ulrich Simon, Sandra Zilles","year":"2010","venue":"International Conference on Algorithmic Learning Theory","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Doliwa et al., 2014] Thorsten Doliwa, Gaojian Fan, Hans Ulrich Simon, and Sandra Zilles. Recursive teaching dimension, VC-dimension and sample compression. The Journal of Machine Learning Research, 15(1):3107-3131, 2014.","title":"Recursive teaching dimension, VC-dimension and sample compression","authors":"Thorsten Doliwa, Gaojian Fan, Hans Ulrich Simon, Sandra Zilles","year":"2014","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Eaves-Jr. and Shafto, 2016] Baxter S Eaves-Jr. and Patrick Shafto. Toward a general, scaleable framework for bayesian teaching with applications to topic models. CoRR, 2016.","title":"Toward a general, scaleable framework for bayesian teaching with applications to topic models","authors":"Patrick Baxter S Eaves-Jr, Shafto","year":"2016","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gao et al., 2017a] Ziyuan Gao, David Kirkpatrick, Christoph Ries, Hans Simon, and Sandra Zilles. Preference-based teaching of unions of geometric objects. In Proceedings of the 28th International Conference on Algorithmic Learning Theory, volume 76 of Proceedings of Machine Learning Research, pages 185-207. PMLR, 15-17 Oct 2017.","title":"Preference-based teaching of unions of geometric objects","authors":"Gao","year":"2017","venue":"Proceedings of the 28th International Conference on Algorithmic Learning Theory","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gao et al., 2017b] Ziyuan Gao, Christoph Ries, Hans Ul- rich Simon, and Sandra Zilles. Preference-based teaching. Journal of Machine Learning Research, 18:31:1-31:32, 2017.","title":"Preference-based teaching","authors":"Gao","year":"2017","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goldman and Kearns, 1995] Sally A Goldman and Michael J Kearns. On the complexity of teaching. Journal of Computer and System Sciences, 50(1):20-31, 1995.","title":"On the complexity of teaching","authors":"A Sally, Michael J Goldman, Kearns","year":"1995","venue":"Journal of Computer and System Sciences","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Goldman and Mathias, 1996] Sally A Goldman and H David Mathias. Teaching a smarter learner. Journal of Computer and System Sciences, 52(2):255-267, 1996.","title":"Teaching a smarter learner","authors":"A Sally, H Goldman, Mathias David","year":"1996","venue":"Journal of Computer and System Sciences","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hernández-Orallo and Telle, 2020] Jose Hernández-Orallo and Jan Arne Telle. Finite and confident teaching in ex- pectation: Sampling from infinite concept classes. In ECAI 2020, pages 1182-1189. IOS Press, 2020.","title":"Jose Hernández-Orallo and Jan Arne Telle. Finite and confident teaching in ex-pectation: Sampling from infinite concept classes","authors":"Hernández-Orallo, Telle","year":"2020","venue":"ECAI 2020","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Khan et al., 2011] Faisal Khan, Xiaojin Zhu, and Bilge Mutlu. How do humans teach: on curriculum learning and teaching dimension. In Proceedings of the 24th In- ternational Conference on Neural Information Processing Systems, pages 1449-1457, 2011.","title":"How do humans teach: on curriculum learning and teaching dimension","authors":"Faisal Khan, Xiaojin Zhu, Bilge Mutlu","year":"2011","venue":"Proceedings of the 24th International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kirkpatrick et al., 2019] David Kirkpatrick, Hans U Simon, and Sandra Zilles. Optimal collusion-free teaching. In Al- gorithmic Learning Theory, pages 506-528. PMLR, 2019.","title":"Optimal collusion-free teaching","authors":"David Kirkpatrick, Hans U Simon, Sandra Zilles","year":"2019","venue":"Algorithmic Learning Theory","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2017] Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Chen Yu, Linda B. Smith, James M. Rehg, and Le Song. Iterative machine teaching. In Proceedings of the 34th International Conference on Machine Learn- ing, pages 2149-2158. PMLR, 2017.","title":"Iterative machine teaching","authors":"Weiyang Liu, Bo Dai, Ahmad Humayun, Charlene Tay, Chen Yu, Linda B Smith, James M Rehg, Le Song","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mansouri et al., 2019] Farnam Mansouri, Yuxin Chen, Ara Vartanian, Jerry Zhu, and Adish Singla. Preference-based batch and sequential teaching: Towards a unified view of models. Advances in Neural Information Processing Sys- tems, 32:9199-9209, 2019.","title":"Preference-based batch and sequential teaching: Towards a unified view of models","authors":"Farnam Mansouri, Yuxin Chen, Ara Vartanian, Jerry Zhu, Adish Singla","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Moran et al., 2015] Shay Moran, Amir Shpilka, Avi Wigderson, and Amir Yehudayoff. Compressing and teaching for low VC-dimension. In Symposium on Foundations of Computer Science, pages 40-51, 2015.","title":"Compressing and teaching for low VC-dimension","authors":"Shay Moran, Amir Shpilka, Avi Wigderson, Amir Yehudayoff","year":"2015","venue":"Symposium on Foundations of Computer Science","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Shafto et al., 2014] Patrick Shafto, Noah D. Goodman, and Thomas L. Griffiths. A rational account of pedagogi- cal reasoning: Teaching by, and learning from, examples. Cognitive Psychology, 71:55 -89, 2014.","title":"A rational account of pedagogical reasoning: Teaching by, and learning from, examples","authors":"Patrick Shafto, Noah D Goodman, Thomas L Griffiths","year":"2014","venue":"Cognitive Psychology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wallace and Dowe, 1999] C. S. Wallace and D. L. Dowe. Minimum message length and Kolmogorov complexity. Computer Journal, 42(4):270-283, 1999.","title":"Minimum message length and Kolmogorov complexity","authors":"C S Wallace, D L Dowe","year":"1999","venue":"Computer Journal","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Yang and Shafto, 2017] Scott Cheng-Hsin Yang and Patrick Shafto. Explainable artificial intelligence via bayesian teaching. In NIPS 2017 workshop on Teaching Machines, Robots, and Humans, pages 127-137, 2017.","title":"Explainable artificial intelligence via bayesian teaching","authors":"Scott Cheng-Hsin, Yang, Patrick Shafto","year":"2017","venue":"NIPS 2017 workshop on Teaching Machines, Robots, and Humans","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Yang et al., 2021] Scott Cheng-Hsin Yang, Wai Keen Vong, Ravi B Sojitra, Tomas Folke, and Patrick Shafto. Mit- igating belief projection in explainable artificial intelli- gence via bayesian teaching. Scientific reports, 11(1):1- 17, 2021.","title":"Mitigating belief projection in explainable artificial intelligence via bayesian teaching","authors":"Scott Cheng-Hsin, Wai Keen Yang, Ravi B Vong, Tomas Sojitra, Patrick Folke, Shafto","year":"2021","venue":"Scientific reports","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhu et al., 2018] Xiaojin Zhu, Adish Singla, Sandra Zilles, and Anna N Rafferty. An overview of machine teaching. arXiv preprint arXiv:1801.05927, 2018.","title":"An overview of machine teaching","authors":"Xiaojin Zhu, Adish Singla, Sandra Zilles, Anna N Rafferty","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhu, 2013] Xiaojin Zhu. Machine teaching for bayesian learners in the exponential family. In Neural Information Processing Systems 26, pages 1905-1913.","title":"Machine teaching for bayesian learners in the exponential family","authors":"Xiaojin Zhu","year":null,"venue":"Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Curran, 2013.","title":null,"authors":"Curran","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zilles et al., 2011] Sandra Zilles, Steffen Lange, Robert Holte, and Martin Zinkevich. Models of cooperative teach- ing and learning. Journal of Machine Learning Research, 12(Feb):349-384, 2011.","title":"Models of cooperative teaching and learning","authors":"Sandra Zilles, Steffen Lange, Robert Holte, Martin Zinkevich","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}