{"type":"ScholarlyArticle","title":"Deep Learning for Abstract Argumentation Semantics","authors":[{"name":"Dennis Craandijk","slug":"dennis-craandijk","given":"Dennis","family":"Craandijk","affiliation":"National Police Lab AI , Netherlands Police; Information and Computing Sciences , Utrecht University"},{"name":"Floris Bex","slug":"floris-bex","given":"Floris","family":"Bex","affiliation":"Information and Computing Sciences , Utrecht University; Institute for Law, Technology and Society , Tilburg University"}],"abstract":"In this paper, we present a learning-based approach to determining acceptance of arguments under several abstract argumentation semantics. More specifically, we propose an argumentation graph neural network (AGNN) that learns a message-passing algorithm to predict the likelihood of an argument being accepted. The experimental results demonstrate that the AGNN can almost perfectly predict the acceptability under different semantics and scales well for larger argumentation frameworks. Furthermore, analysing the behaviour of the message-passing algorithm shows that the AGNN learns to adhere to basic principles of argument semantics as identified in the literature, and can thus be trained to predict extensions under the different semantics – we show how the latter can be done for multi-extension semantics by using AGNNs to guide a basic search. We publish our code at https://github.com/DennisCraandijk/DL-Abstract-Argumentation.","doi":"10.24963/ijcai.2020/231","url":"https://ijcai.org/proceedings/2020/231","pdf":"https://ijcai.org/proceedings/2020/0231.pdf","markdown":"https://ijcai.org/proceedings/2020/231.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/231","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":"Knowledge Representation and Reasoning","track":"Main track","number":231,"pages":{"first":1667,"last":1673},"keywords":["Machine Learning: Neuro-Symbolic Methods","Knowledge Representation and Reasoning: Computational Models of Argument"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24840/file_24840.m3u8","length_sec":254,"provider":"hls"}],"references":[{"position":1,"raw":"[Atkinson et al., 2017] K. Atkinson, P. Baroni, M. Gia- comin, A. Hunter, H. Prakken, C. Reed, G. R. Simari, M. Thimm, and S. Villata. Towards artificial argumen- tation. AI Magazine, 38(3):25-36, 2017.","title":"Towards artificial argumentation","authors":"K Atkinson, P Baroni, M Giacomin, A Hunter, H Prakken, C Reed, G R Simari, M Thimm, S Villata","year":"2017","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baroni et al., 2011] P. Baroni, M. Caminada, and M. Gi- acomin. An introduction to argumentation semantics. Knowledge Engineering Review, 26(4):365-410, 2011.","title":"An introduction to argumentation semantics","authors":"P Baroni, M Caminada, M Giacomin","year":"2011","venue":"Knowledge Engineering Review","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Battaglia et al., 2018] P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Mali- nowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, et al. Relational inductive biases, deep learning, and graph networks. arXiv e-prints, arXiv:1806.01261, 2018.","title":"Relational inductive biases, deep learning, and graph networks","authors":"P W Battaglia, J B Hamrick, V Bapst, A Sanchez-Gonzalez, V Zambaldi, M Malinowski, A Tacchetti, D Raposo, A Santoro, R Faulkner","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Besnard and Doutre, 2004] P. Besnard and S. Doutre. Checking the acceptability of a set of arguments. In Proceedings of the 10th International Workshop on Non- Monotonic Reasoning (NMR'04), pages 59-64, 2004.","title":"Checking the acceptability of a set of arguments","authors":"P Besnard, S Doutre","year":"2004","venue":"Proceedings of the 10th International Workshop on Non-Monotonic Reasoning (NMR'04)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bonzon et al., 2016] E. Bonzon, J. Delobelle, S. Konieczny, and N. Maudet. A comparative study of ranking-based semantics for abstract argumentation. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 914--920, 2016.","title":"A comparative study of ranking-based semantics for abstract argumentation","authors":"E Bonzon, J Delobelle, S Konieczny, N Maudet","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Charwat et al., 2015] G. Charwat, W. Dvorák, S. A. Gaggl, J. P. Wallner, and S. Woltran. Methods for solving reason- ing problems in abstract argumentation -A survey. Artifi- cial Intelligence, 220:28-63, 2015.","title":"Methods for solving reasoning problems in abstract argumentation -A survey","authors":"G Charwat, W Dvorák, S A Gaggl, J P Wallner, S Woltran","year":"2015","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cocarascu and Toni, 2017] O. Cocarascu and F. Toni. Iden- tifying attack and support argumentative relations using deep learning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1374-1379, 2017.","title":"Identifying attack and support argumentative relations using deep learning","authors":"O Cocarascu, F Toni","year":"2017","venue":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"['Avila Garcez et al., 2015] A. S. d'Avila Garcez, T. R. Besold, L. D. Raedt, P. Földiák, P. Hitzler, T. Icard, K. Kühnberger, L. C. Lamb, R. Miikkulainen, and D. L. Silver. Neural-symbolic learning and reasoning: Contri- butions and challenges. In Proceedings of the 2015 AAAI Spring Symposia, Palo Alto, 2015. Stanford University.","title":"Neural-symbolic learning and reasoning: Contributions and challenges","authors":"Avila Garcez","year":"2015","venue":"Proceedings of the 2015 AAAI Spring Symposia","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Doutre and Mailly, 2018] S. Doutre and J. Mailly. Con- straints and changes: A survey of abstract argumentation dynamics. Argument & Computation, 9(3):223-248, 2018.","title":"Constraints and changes: A survey of abstract argumentation dynamics","authors":"S Doutre, J Mailly","year":"2018","venue":"Argument & Computation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Dung, 1995] P. M. Dung. On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artificial Intelligence, 77(2):321-358, 1995.","title":"On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games","authors":"P M Dung","year":"1995","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dunne and Wooldridge, 2009] P. E. Dunne and M. J. Wooldridge. Complexity of abstract argumentation. In G. R. Simari and I. Rahwan, editors, Argumentation in Ar- tificial Intelligence, pages 85-104. Springer, 2009.","title":"Complexity of abstract argumentation","authors":"P E Dunne, M J Wooldridge","year":"2009","venue":"Argumentation in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gaggl et al., 2020] S. A. Gaggl, T. Linsbichler, M. Maratea, and S. Woltran. Design and results of the second interna- tional competition on computational models of argumen- tation. Artificial Intelligence, 279:103193, 2020.","title":"Design and results of the second international competition on computational models of argumentation","authors":"S A Gaggl, T Linsbichler, M Maratea, S Woltran","year":"2020","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gilmer et al., 2017] J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl. Neural message passing for quantum chemistry. In Proceedings of the 34th Interna- tional Conference on Machine Learning, volume 70, pages 1263-1272, 2017.","title":"Neural message passing for quantum chemistry","authors":"J Gilmer, S S Schoenholz, P F Riley, O Vinyals, G E Dahl","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hochreiter and Schmidhuber, 1997] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computation, 9(8):1735-1780, 1997.","title":"Long short-term memory","authors":"S Hochreiter, J Schmidhuber","year":"1997","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kipf and Welling, 2017] T. N. Kipf and M. Welling. Semi- supervised classification with graph convolutional net- works. In 5th International Conference on Learning Rep- resentations), 2017.","title":"Semisupervised classification with graph convolutional networks","authors":"T N Kipf, M Welling","year":"2017","venue":"5th International Conference on Learning Representations)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kuhlmann and Thimm, 2019] I. Kuhlmann and M. Thimm. Using graph convolutional networks for approximate rea- soning with abstract argumentation frameworks: A fea- sibility study. In Proceedings of the 13th international conference on Scalable Uncertainty Management (SUM), pages 24-37, 2019.","title":"Using graph convolutional networks for approximate reasoning with abstract argumentation frameworks: A feasibility study","authors":"Thimm Kuhlmann, I Kuhlmann, M Thimm","year":"2019","venue":"Proceedings of the 13th international conference on Scalable Uncertainty Management (SUM)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2018] Z. Li, Q. Chen, and V. Koltun. Combina- torial optimization with graph convolutional networks and guided tree search. In Proceedings of the 32nd Interna- tional Conference on Neural Information Processing Sys- tems, pages 537-546, 2018.","title":"Combinatorial optimization with graph convolutional networks and guided tree search","authors":"Z Li, Q Chen, V Koltun","year":"2018","venue":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Loshchilov and Hutter, 2019] I. Loshchilov and F. Hutter. Decoupled weight decay regularization. In 7th Interna- tional Conference on Learning Representations), 2019.","title":"Decoupled weight decay regularization","authors":"Hutter Loshchilov, I Loshchilov, F Hutter","year":"2019","venue":"7th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[McKay and Piperno, 2014] B. D. McKay and A. Piperno. Practical graph isomorphism, II. Journal of Symbolic Computation, 60:94-112, 2014.","title":"Practical graph isomorphism, II","authors":"B D Mckay, A Piperno","year":"2014","venue":"Journal of Symbolic Computation","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Modgil and Caminada, 2009] S. Modgil and M. Caminada. Proof theories and algorithms for abstract argumentation frameworks. In I. Rahwan and G. R. Simari, editors, Argumentation in Artificial Intelligence, pages 105-129. Springer, 2009.","title":"Proof theories and algorithms for abstract argumentation frameworks","authors":"S Modgil, M Caminada","year":"2009","venue":"Argumentation in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Niskanen and Järvisalo, 2019] A. Niskanen and M. Järvisalo. µ-toksia: Sat-based solver for static and dynamic argumentation frameworks. https://bitbucket.org/andreasniskanen/mu-toksia, 2019.","title":"µ-toksia: Sat-based solver for static and dynamic argumentation frameworks","authors":"A Niskanen, M Järvisalo","year":null,"venue":null,"doi":null,"url":"https://bitbucket.org/andreasniskanen/mu-toksia,2019","internal_url":null},{"position":22,"raw":"[Palm et al., 2018] R. B. Palm, U. Paquet, and O. Winther. Recurrent relational networks. In Proceedings of the 32nd International Conference on Neural Information Process- ing Systems, pages 3372-3382, 2018.","title":"Recurrent relational networks","authors":"R B Palm, U Paquet, O Winther","year":"2018","venue":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pascanu et al., 2013] R. Pascanu, T. Mikolov, and Y. Ben- gio. On the difficulty of training recurrent neural networks. In Proceedings of the 30th International Conference on Machine Learning (ICML), pages 1310-1318, 2013.","title":"On the difficulty of training recurrent neural networks","authors":"R Pascanu, T Mikolov, Y Bengio","year":"2013","venue":"Proceedings of the 30th International Conference on Machine Learning (ICML)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Powers, 2011] D. Powers. Evaluation: From precision, re- call and f-measure to roc, informedness, markedness & correlation. Journal of Machice Learning Technology, 2:2229-3981, 01 2011.","title":"Evaluation: From precision, recall and f-measure to roc, informedness, markedness & correlation","authors":"D Powers","year":"2011","venue":"Journal of Machice Learning Technology","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Selsam et al., 2019] D. Selsam, M. Lamm, B. Bünz, P. Liang, L. de Moura, and D. L. Dill. Learning a SAT solver from single-bit supervision. In 7th International Conference on Learning Representations (ICLR), 2019.","title":"Learning a SAT solver from single-bit supervision","authors":"D Selsam, M Lamm, B Bünz, P Liang, L De Moura, D L Dill","year":"2019","venue":"7th International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Smith, 2017] L. N. Smith. Cyclical learning rates for train- ing neural networks. IEEE Winter Conference on Applica- tions of Computer Vision (WACV), 2017.","title":"Cyclical learning rates for training neural networks","authors":"L N Smith","year":"2017","venue":"IEEE Winter Conference on Applications of Computer Vision (WACV)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}