A Context-Integrated Transformer-Based Neural Network for Auction Design
This addresses auction design for auctioneers by enabling more flexible and asymmetric solutions, though it is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of designing incentive-compatible auctions to maximize revenue by incorporating public contextual information into a deep learning framework, overcoming limitations of fixed or symmetric settings. The result was CITransNet, which recovered optimal solutions in single-item cases, outperformed baselines in multi-item auctions, and showed good generalization.
One of the central problems in auction design is developing an incentive-compatible mechanism that maximizes the auctioneer's expected revenue. While theoretical approaches have encountered bottlenecks in multi-item auctions, recently, there has been much progress on finding the optimal mechanism through deep learning. However, these works either focus on a fixed set of bidders and items, or restrict the auction to be symmetric. In this work, we overcome such limitations by factoring \emph{public} contextual information of bidders and items into the auction learning framework. We propose $\mathtt{CITransNet}$, a context-integrated transformer-based neural network for optimal auction design, which maintains permutation-equivariance over bids and contexts while being able to find asymmetric solutions. We show by extensive experiments that $\mathtt{CITransNet}$ can recover the known optimal solutions in single-item settings, outperform strong baselines in multi-item auctions, and generalize well to cases other than those in training.