Data Exchange Markets via Utility Balancing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909081070993408 |
|---|---|
| author | Bhaskara, Aditya Gollapudi, Sreenivas Im, Sungjin Kollias, Kostas Munagala, Kamesh Sankar, Govind S. |
| author_facet | Bhaskara, Aditya Gollapudi, Sreenivas Im, Sungjin Kollias, Kostas Munagala, Kamesh Sankar, Govind S. |
| contents | This paper explores the design of a balanced data-sharing marketplace for entities with heterogeneous datasets and machine learning models that they seek to refine using data from other agents. The goal of the marketplace is to encourage participation for data sharing in the presence of such heterogeneity. Our market design approach for data sharing focuses on interim utility balance, where participants contribute and receive equitable utility from refinement of their models. We present such a market model for which we study computational complexity, solution existence, and approximation algorithms for welfare maximization and core stability. We finally support our theoretical insights with simulations on a mean estimation task inspired by road traffic delay estimation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13053 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Data Exchange Markets via Utility Balancing Bhaskara, Aditya Gollapudi, Sreenivas Im, Sungjin Kollias, Kostas Munagala, Kamesh Sankar, Govind S. Computer Science and Game Theory Data Structures and Algorithms This paper explores the design of a balanced data-sharing marketplace for entities with heterogeneous datasets and machine learning models that they seek to refine using data from other agents. The goal of the marketplace is to encourage participation for data sharing in the presence of such heterogeneity. Our market design approach for data sharing focuses on interim utility balance, where participants contribute and receive equitable utility from refinement of their models. We present such a market model for which we study computational complexity, solution existence, and approximation algorithms for welfare maximization and core stability. We finally support our theoretical insights with simulations on a mean estimation task inspired by road traffic delay estimation. |
| title | Data Exchange Markets via Utility Balancing |
| topic | Computer Science and Game Theory Data Structures and Algorithms |
| url | https://arxiv.org/abs/2401.13053 |