Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910938709360640 |
|---|---|
| author | Xu, Renzhe Wang, Kang Li, Bo |
| author_facet | Xu, Renzhe Wang, Kang Li, Bo |
| contents | Data heterogeneity across multiple sources is common in real-world machine learning (ML) settings. Although many methods focus on enabling a single model to handle diverse data, real-world markets often comprise multiple competing ML providers. In this paper, we propose a game-theoretic framework -- the Heterogeneous Data Game -- to analyze how such providers compete across heterogeneous data sources. We investigate the resulting pure Nash equilibria (PNE), showing that they can be non-existent, homogeneous (all providers converge on the same model), or heterogeneous (providers specialize in distinct data sources). Our analysis spans monopolistic, duopolistic, and more general markets, illustrating how factors such as the "temperature" of data-source choice models and the dominance of certain data sources shape equilibrium outcomes. We offer theoretical insights into both homogeneous and heterogeneous PNEs, guiding regulatory policies and practical strategies for competitive ML marketplaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_07688 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources Xu, Renzhe Wang, Kang Li, Bo Computer Science and Game Theory Machine Learning Data heterogeneity across multiple sources is common in real-world machine learning (ML) settings. Although many methods focus on enabling a single model to handle diverse data, real-world markets often comprise multiple competing ML providers. In this paper, we propose a game-theoretic framework -- the Heterogeneous Data Game -- to analyze how such providers compete across heterogeneous data sources. We investigate the resulting pure Nash equilibria (PNE), showing that they can be non-existent, homogeneous (all providers converge on the same model), or heterogeneous (providers specialize in distinct data sources). Our analysis spans monopolistic, duopolistic, and more general markets, illustrating how factors such as the "temperature" of data-source choice models and the dominance of certain data sources shape equilibrium outcomes. We offer theoretical insights into both homogeneous and heterogeneous PNEs, guiding regulatory policies and practical strategies for competitive ML marketplaces. |
| title | Heterogeneous Data Game: Characterizing the Model Competition Across Multiple Data Sources |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2505.07688 |