Abstract
We explore an approach to designing false-name-proof auction mechanisms using deep learning. While multi-agent systems researchers have recently proposed data-driven approaches to automatically designing auction mechanisms through deep learning, false-name-proofness, which generalizes strategy-proofness by assuming that a bidder can submit multiple bids under fictitious identifiers, has not been taken into account as a property that a mechanism has to satisfy. We extend the RegretNet neural network architecture to incorporate false-name-proof constraints and then conduct experiments demonstrating that the generated mechanisms satisfy false-name-proofness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Conitzer, V., Sandholm, T.: Complexity of mechanism design. In: UAI, pp. 103–110 (2002)
Conitzer, V., Sandholm, T.: Self-interested automated mechanism design and implications for optimal combinatorial auctions. In: ACM EC, pp. 132–141 (2004)
Düetting, P., Feng, Z., Narasimhan, H., Parkes, D., Ravindranath, S.S.: Optimal auctions through deep learning. In: ICML, pp. 1706–1715 (2019)
Feng, Z., Narasimhan, H., Parkes, D.C.: Deep learning for revenue-optimal auctions with budgets. In: AAMAS, pp. 354–362 (2018)
Guo, M., Conitzer, V.: Computationally feasible automated mechanism design: General approach and case studies. In: AAAI, pp. 1676–1679 (2010)
Iwasaki, A., et al.: Worst-case efficiency ratio in false-name-proof combinatorial auction mechanisms. In: AAMAS, pp. 633–640 (2010)
Manisha, P., Jawahar, C.V., Gujar, S.: Learning optimal redistribution mechanisms through neural networks. In: AAMAS, pp. 345–353 (2018)
Yokoo, M.: Characterization of strategy/false-name proof combinatorial auction protocols: price-oriented, rationing-free protocol. In: IJCAI, pp. 733–739 (2003)
Yokoo, M., Sakurai, Y., Matsubara, S.: Robust combinatorial auction protocol against false-name bids. Artif. Intell. J. 130(2), 167–181 (2001)
Acknowledgments
This work was partially supported by JSPS KAKENHI Grant Numbers JP17H0 0761, JP17KK0008 and JP18H03337, by the Kayamori Foundation of Informational Science Advancement, and by the Telecommunications Advancement Foundation. We thank Paul Dütting and his coauthors for sharing the source code for the RegretNet framework.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sakurai, Y., Oyama, S., Guo, M., Yokoo, M. (2019). Deep False-Name-Proof Auction Mechanisms. In: Baldoni, M., Dastani, M., Liao, B., Sakurai, Y., Zalila Wenkstern, R. (eds) PRIMA 2019: Principles and Practice of Multi-Agent Systems. PRIMA 2019. Lecture Notes in Computer Science(), vol 11873. Springer, Cham. https://doi.org/10.1007/978-3-030-33792-6_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-33792-6_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33791-9
Online ISBN: 978-3-030-33792-6
eBook Packages: Computer ScienceComputer Science (R0)