ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning

Kuo, Kevin; Ostuni, Anthony; Horishny, Elizabeth; Curry, Michael J.; Dooley, Samuel; Chiang, Ping-yeh; Goldstein, Tom; Dickerson, John P.

doi:10.48550/arxiv.2010.06398

Cited by 7 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, multiple extensions of RegretNet have been proposed, including the extensions to the optimal auction design with budget constraints [14], fairness constraints [31], and human preferences over desirable allocations [48], as well as the problem of faculty allocation [15] and the matching problem [51]. Shen et al [54] and Dütting et al [12] propose revenue-maximizing alternatives to RegretNet that are exactly DSIC but that are only applicable to the auctions with one bidder.…”

Section: Other Related Workmentioning

confidence: 99%

Optimal-er Auctions through Attention

Ivanov¹,

Safiulin²,

Balabaeva³

et al. 2022

Preprint

View full text Add to dashboard Cite

RegretNet is a recent breakthrough in the automated design of revenue-maximizing auctions. It combines the expressivity of deep learning with the regret-based approach to relax and quantify the Incentive Compatibility constraint (that participants benefit from bidding truthfully). As a follow-up to its success, we propose two independent modifications of RegretNet, namely a new neural architecture based on the attention mechanism, denoted as TransRegret, and an alternative loss function that is interpretable and significantly less sensitive to hyperparameters. We investigate both proposed modifications in an extensive experimental study in settings with fixed and varied input sizes and additionally test out-of-setting generalization of our network. In all experiments, we find that TransRegret consistently outperforms existing architectures in revenue. Regarding our loss modification, we confirm its effectiveness at controlling the revenue-regret trade-off by varying a single interpretable hyperparameter.

show abstract

Section: Other Related Workmentioning

confidence: 99%

Optimal-er Auctions through Attention

Ivanov¹,

Safiulin²,

Balabaeva³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Further work has built directly on both RochetNet and RegretNet [30,10,43,44]. Others have taken a similar approach but applied to different mechanism design problems, including finding welfare-maximizing auctions [49] and facility location [21].…”

Section: Related Workmentioning

confidence: 99%

“…This learning approach to auction design can replicate some known-optimal auctions, and can learn good auctions in settings where the optimal auction is not known. It has been extended in a variety of ways [10,49,21,30,18,43,44,41].…”

Section: Introductionmentioning

confidence: 99%

Learning Revenue-Maximizing Auctions With Differentiable Matching

Curry,

Lyi,

Goldstein

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a new architecture to approximately learn incentive compatible, revenue-maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm to perform a differentiable bipartite matching which allows the network to learn strategyproof revenue-maximizing mechanisms in settings not learnable by the previous RegretNet architecture. In particular, our architecture is able to learn mechanisms in settings without free disposal where each bidder must be allocated exactly some number of items. In experiments, we show our approach successfully recovers multiple known optimal mechanisms and highrevenue, low-regret mechanisms in larger settings where the optimal mechanism is unknown.Preprint. Under review.

show abstract

“…[41] shares significant, but limited results which solve the case in which items may have at most 2 values. Due to the apparent difficulty of analytically designing strategyproof, revenue maximizing auctions, recent methods instead approximate optimal auctions using machine learning approaches [13,10,19,25,15,32,33]. [37] proposes an method which guarantees exact strategyproofness in the single-agent setting.…”

Section: Introductionmentioning

confidence: 99%

“…In other cases, such as auctions involving job or credit advertisements, it might be necessary to additionally constrain the auction mechanism to ensure fairness with respect to protected characteristics [23,6]. Recent work has considered the problem of determining revenue-maximizing, strategyproof, fair auctions, either from a specific class [5] or with a general neural network approach [25].…”

Section: Introductionmentioning

confidence: 99%

PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

Peri,

Curry,

Dooley

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The design of optimal auctions is a problem of interest in economics, game theory and computer science. Despite decades of effort, strategyproof, revenuemaximizing auction designs are still not known outside of restricted settings. However, recent methods using deep learning have shown some success in approximating optimal auctions, recovering several known solutions and outperforming strong baselines when optimal auctions are not known. In addition to maximizing revenue, auction mechanisms may also seek to encourage socially desirable constraints such as allocation fairness or diversity. However, these philosophical notions neither have standardization nor do they have widely accepted formal definitions. In this paper, we propose PreferenceNet, an extension of existing neural-network-based auction mechanisms to encode constraints using (potentially human-provided) exemplars of desirable allocations. In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs. We validate our approach through human subject research and show that we are able to effectively capture real human preferences. Our code is available on GitHub * The first two authors contributed equally to this work. Preprint. Under review.

show abstract

ProportionNet: Balancing Fairness and Revenue for Auction Design with Deep Learning

Cited by 7 publications

References 24 publications

Optimal-er Auctions through Attention

Optimal-er Auctions through Attention

Learning Revenue-Maximizing Auctions With Differentiable Matching

PreferenceNet: Encoding Human Preferences in Auction Design with Deep Learning

Contact Info

Product

Resources

About