{"type":"ScholarlyArticle","title":"Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment","authors":[{"name":"Jakob Weissteiner","slug":"jakob-weissteiner","given":"Jakob","family":"Weissteiner","affiliation":"University of Zurich; ETH AI Center"},{"name":"Jakob Heiss","slug":"jakob-heiss","given":"Jakob","family":"Heiss","affiliation":"ETH Zurich"},{"name":"Julien Siems","slug":"julien-siems","given":"Julien","family":"Siems","affiliation":"University of Zurich"},{"name":"Sven Seuken","slug":"sven-seuken","given":"Sven","family":"Seuken","affiliation":"University of Zurich; ETH AI Center"}],"abstract":"Many important resource allocation problems involve the combinatorial assignment of items, e.g., auctions or course allocation. Because the bundle space grows exponentially in the number of items, preference elicitation is a key challenge in these domains. Recently, researchers have proposed ML-based mechanisms that outperform traditional mechanisms while reducing preference elicitation costs for agents. However, one major shortcoming of the ML algorithms that were used is their disregard of important prior knowledge about agents' preferences. To address this, we introduce monotone-value neural networks (MVNNs), which are designed to capture combinatorial valuations, while enforcing monotonicity and normality. On a technical level, we prove that our MVNNs are universal in the class of monotone and normalized value functions, and we provide a mixed-integer linear program (MILP) formulation to make solving MVNN-based winner determination problems (WDPs) practically feasible. We evaluate our MVNNs experimentally in spectrum auction domains. Our results show that MVNNs improve the prediction performance, they yield state-of-the-art allocative efficiency in the auction, and they also reduce the run-time of the WDPs. Our code is available on GitHub: https://github.com/marketdesignresearch/MVNN.","doi":"10.24963/ijcai.2022/77","url":"https://ijcai.org/proceedings/2022/77","pdf":"https://ijcai.org/proceedings/2022/0077.pdf","markdown":"https://ijcai.org/proceedings/2022/77.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/77","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":"Agent-based and Multi-agent Systems","track":"Main Track","number":77,"pages":{"first":541,"last":548},"keywords":["Agent-based and Multi-agent Systems: Economic Paradigms, Auctions and Market-Based Systems","Machine Learning: Theory of Deep Learning","Machine Learning: Regression","Constraint Satisfaction and Optimization: Constraints and Machine Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986532","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984675","length_sec":352,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Ausubel and Baranov, 2017] Lawrence M Ausubel and Oleg Baranov. A practical guide to the combinatorial clock auction. Economic Journal, 127(605):F334-F350, 2017. 1, 3, 6","title":"A practical guide to the combinatorial clock auction","authors":"M Lawrence, Oleg Ausubel, Baranov","year":"2017","venue":"Economic Journal","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ausubel and Cramton, 2011] Lawrence Ausubel and Peter Cramton. Auction design for wind rights. Report to Bu- reau of Ocean Energy Management, Regulation and En- forcement, 2011.","title":"Auction design for wind rights","authors":"Cramton Ausubel, Lawrence Ausubel, Peter Cramton","year":"2011","venue":"Report to Bureau of Ocean Energy Management, Regulation and Enforcement","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ausubel et al., 2006] Lawrence M Ausubel, Peter Cramton, and Paul Milgrom. The clock-proxy auction: A practi- cal combinatorial auction design. In Peter Cramton, Yoav Shoham, and Richard Steinberg, editors, Combinatorial Auctions, pages 115-138. MIT Press, 2006.","title":"The clock-proxy auction: A practical combinatorial auction design","authors":"Peter Lawrence M Ausubel, Paul Cramton, Milgrom","year":"2006","venue":"Combinatorial Auctions","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bichler et al., 2019] Martin Bichler, Vladimir Fux, and Ja- cob K Goeree. Designing combinatorial exchanges for the reallocation of resource rights. Proceedings of the Na- tional Academy of Sciences, 116(3):786-791, 2019.","title":"Designing combinatorial exchanges for the reallocation of resource rights","authors":"Martin Bichler, Vladimir Fux, Jacob K Goeree","year":"2019","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Brero et al., 2018] Gianluca Brero, Benjamin Lubin, and Sven Seuken. Combinatorial auctions via machine learning-based preference elicitation. In Proceedings of the 27th International Joint Conference on Artificial Intel- ligence, 2018.","title":"Combinatorial auctions via machine learning-based preference elicitation","authors":"Gianluca Brero, Benjamin Lubin, Sven Seuken","year":"2018","venue":"Proceedings of the 27th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/18"},{"position":6,"raw":"[Brero et al., 2019] Gianluca Brero, Sébastien Lahaie, and Sven Seuken. Fast iterative combinatorial auctions via bayesian learning. In Proceedings of the 33rd AAAI Con- ference of Artificial Intelligence, 2019.","title":"Fast iterative combinatorial auctions via bayesian learning","authors":"Gianluca Brero, Sébastien Lahaie, Sven Seuken","year":"2019","venue":"Proceedings of the 33rd AAAI Conference of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Brero et al., 2021] Gianluca Brero, Benjamin Lubin, and Sven Seuken. Machine learning-powered iterative com- binatorial auctions. arXiv preprint arXiv:1911.08042, Jan 2021. 2, 3, 5, 6","title":"Machine learning-powered iterative combinatorial auctions","authors":"Gianluca Brero, Benjamin Lubin, Sven Seuken","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Bronstein et al., 2017] Michael M Bronstein, Joan Bruna, Yann LeCun, Arthur Szlam, and Pierre Vandergheynst. Geometric deep learning: going beyond euclidean data. IEEE Signal Processing Magazine, 34(4):18-42, 2017.","title":"Geometric deep learning: going beyond euclidean data","authors":"Joan Michael M Bronstein, Yann Bruna, Arthur Lecun, Pierre Szlam, Vandergheynst","year":"2017","venue":"IEEE Signal Processing Magazine","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Budish, 2011] Eric Budish. The combinatorial assign- ment problem: Approximate competitive equilibrium from equal incomes. Journal of Political Economy, 119(6):1061-1103, 2011.","title":"The combinatorial assignment problem: Approximate competitive equilibrium from equal incomes","authors":"Eric Budish","year":"2011","venue":"Journal of Political Economy","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cramton, 2013] Peter Cramton. Spectrum auction design. Review of Industrial Organization, 42(2):161-190, 2013. 1, 6","title":"Spectrum auction design","authors":"Peter Cramton","year":"2013","venue":"Review of Industrial Organization","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Dütting et al., 2019] Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C Parkes, and Sai Srivatsa Ravin- dranath. Optimal auctions through deep learning. In Pro- ceedings of the 36th International Conference on Machine Learning, 2019. 2","title":"Optimal auctions through deep learning","authors":"Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C Parkes, Sai Srivatsa Ravindranath","year":"2019","venue":"Proceedings of the 36th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Goeree and Holt, 2010] Jacob K Goeree and Charles A Holt. Hierarchical package bidding: A paper & pencil combinatorial auction. Games and Economic Behavior, 70(1):146-169, 2010.","title":"Hierarchical package bidding: A paper & pencil combinatorial auction","authors":"K Jacob, Charles A Goeree, Holt","year":"2010","venue":"Games and Economic Behavior","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Heiss et al., 2021] Jakob Heiss, Jakob Weissteiner, Hanna Wutte, Sven Seuken, and Josef Teichmann. Nomu: Neu- ral optimization-based model uncertainty. arXiv preprint arXiv:2102.13640, 2021. 6, 7","title":"Nomu: Neural optimization-based model uncertainty","authors":"Heiss","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hutter et al., 2011] Frank Hutter, Holger H Hoos, and Kevin Leyton-Brown. Sequential model-based optimiza- tion for general algorithm configuration. In International Conference on learning and intelligent optimization, pages 507-523. Springer, 2011.","title":"Sequential model-based optimization for general algorithm configuration","authors":"Frank Hutter, Kevin Holger H Hoos, Leyton-Brown","year":"2011","venue":"International Conference on learning and intelligent optimization","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liew et al., 2016] Shan Sung Liew, Mohamed Khalil-Hani, and Rabia Bakhteri. Bounded activation functions for en- hanced training stability of deep neural networks on visual pattern recognition problems. Neurocomputing, 216:718- 734, 2016.","title":"Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems","authors":"Sung Shan, Mohamed Liew, Rabia Khalil-Hani, Bakhteri","year":"2016","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Liu et al., 2020] Xingchao Liu, Xing Han, Na Zhang, and Qiang Liu. Certified monotonic neural networks. Advances in Neural Information Processing Systems, 33:15427-15438, 2020.","title":"Certified monotonic neural networks","authors":"Liu","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Nisan and Segal, 2006] Noam Nisan and Ilya Segal. The communication requirements of efficient allocations and supporting prices. Journal of Economic Theory, 129(1):192-224, 2006.","title":"Noam Nisan and Ilya Segal. The communication requirements of efficient allocations and supporting prices","authors":"Segal Nisan","year":"2006","venue":"Journal of Economic Theory","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Osband et al., 2021] Ian Osband, Zheng Wen, Mohammad Asghari, Morteza Ibrahimi, Xiyuan Lu, and Benjamin Van Roy. Epistemic neural networks. arXiv preprint arXiv:2107.08924, 2021. Rahme et al., 2021]","title":"Epistemic neural networks","authors":"Ian Osband, Zheng Wen, Mohammad Asghari, Morteza Ibrahimi, Xiyuan Lu, Benjamin Van, Roy","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"Jad Rahme, Samy Jelassi, Joan Bruno, and S. Matthew Weinberg. A permutation-equivariant neu- ral network architecture for auction design. In Proceed- ings of the 35th AAAI Conference on Artificial Intelligence, 2021.","title":"A permutation-equivariant neural network architecture for auction design","authors":"Jad Rahme, Samy Jelassi, Joan Bruno, S Matthew Weinberg","year":"2021","venue":"Proceedings of the 35th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Scheffel et al., 2012] Tobias Scheffel, Georg Ziegler, and Martin Bichler. On the impact of package selection in combinatorial auctions: an experimental study in the con- text of spectrum auction design. Experimental Economics, 15(4):667-692, 2012.","title":"On the impact of package selection in combinatorial auctions: an experimental study in the context of spectrum auction design","authors":"Scheffel","year":"2012","venue":"Experimental Economics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sill, 1998] Joseph Sill. Monotonic networks. Advances in Neural Information Processing Systems, 10:661-667, 1998.","title":"Joseph Sill. Monotonic networks","authors":"Sill","year":"1998","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tjeng et al., 2019] Vincent Tjeng, Kai Y. Xiao, and Russ Tedrake. Evaluating robustness of neural networks with mixed integer programming. In International Conference on Learning Representations, 2019. 5","title":"Evaluating robustness of neural networks with mixed integer programming","authors":"Vincent Tjeng, Kai Y Xiao, Russ Tedrake","year":"2019","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wehenkel and Louppe, 2019] Antoine Wehenkel and Gilles Louppe. Unconstrained monotonic neural networks. Advances in Neural Information Processing Systems, 32:1545-1555, 2019.","title":"Antoine Wehenkel and Gilles Louppe. Unconstrained monotonic neural networks","authors":"Louppe Wehenkel","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Weiss et al., 2017] Michael Weiss, Benjamin Lubin, and Sven Seuken. Sats: A universal spectrum auction test suite. In Proceedings of the 16th Conference on Au- tonomous Agents and MultiAgent Systems, pages 51-59, 2017.","title":"Sats: A universal spectrum auction test suite","authors":"Michael Weiss, Benjamin Lubin, Sven Seuken","year":"2017","venue":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Weissteiner and Seuken, 2020] Jakob Weissteiner and Sven Seuken. Deep learning-powered iterative combinatorial auctions. In Proceedings of the 34th AAAI Conference of Artificial Intelligence, pages 2284-2293, 2020. 2, 3, 6, 7","title":"Deep learning-powered iterative combinatorial auctions","authors":"Seuken Weissteiner, Jakob Weissteiner, Sven Seuken","year":"2020","venue":"Proceedings of the 34th AAAI Conference of Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Weissteiner et al., 2022] Jakob Weissteiner, Chris Wendler, Sven Seuken, Ben Lubin, and Markus Püschel. Fourier analysis-based iterative combinatorial auctions. In Pro- ceedings of the 31st International Joint Conference on Ar- tificial Intelligence, 2022. 2, 3, 6","title":"Fourier analysis-based iterative combinatorial auctions","authors":"Jakob Weissteiner, Chris Wendler, Sven Seuken, Ben Lubin, Markus Püschel","year":"2022","venue":"Proceedings of the 31st International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2022/78"},{"position":27,"raw":"[You et al., 2017] Seungil You, David Ding, Kevin Canini, Jan Pfeifer, and Maya Gupta. Deep lattice networks and partial monotonic functions. Advances in neural informa- tion processing systems, 30, 2017.","title":"Deep lattice networks and partial monotonic functions","authors":"You","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}