CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913469462216704 |
|---|---|
| author | Zipperling, Domenique Allmendinger, Simeon Struppek, Lukas Kühl, Niklas |
| author_facet | Zipperling, Domenique Allmendinger, Simeon Struppek, Lukas Kühl, Niklas |
| contents | In the landscape of generative artificial intelligence, diffusion-based models present challenges for socio-technical systems in data requirements and privacy. Traditional approaches like federated learning distribute the learning process but strain individual clients, especially with constrained resources (e.g., edge devices). In response to these challenges, we introduce CollaFuse, a novel framework inspired by split learning. Tailored for efficient and collaborative use of denoising diffusion probabilistic models, CollaFuse enables shared server training and inference, alleviating client computational burdens. This is achieved by retaining data and computationally inexpensive GPU processes locally at each client while outsourcing the computationally expensive processes to the shared server. Demonstrated in a healthcare context, CollaFuse enhances privacy by highly reducing the need for sensitive information sharing. These capabilities hold the potential to impact various application areas, such as the design of edge computing solutions, healthcare research, or autonomous driving. In essence, our work advances distributed machine learning, shaping the future of collaborative GenAI networks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_19105 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI Zipperling, Domenique Allmendinger, Simeon Struppek, Lukas Kühl, Niklas Machine Learning Artificial Intelligence In the landscape of generative artificial intelligence, diffusion-based models present challenges for socio-technical systems in data requirements and privacy. Traditional approaches like federated learning distribute the learning process but strain individual clients, especially with constrained resources (e.g., edge devices). In response to these challenges, we introduce CollaFuse, a novel framework inspired by split learning. Tailored for efficient and collaborative use of denoising diffusion probabilistic models, CollaFuse enables shared server training and inference, alleviating client computational burdens. This is achieved by retaining data and computationally inexpensive GPU processes locally at each client while outsourcing the computationally expensive processes to the shared server. Demonstrated in a healthcare context, CollaFuse enhances privacy by highly reducing the need for sensitive information sharing. These capabilities hold the potential to impact various application areas, such as the design of edge computing solutions, healthcare research, or autonomous driving. In essence, our work advances distributed machine learning, shaping the future of collaborative GenAI networks. |
| title | CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2402.19105 |