Open challenges and opportunities in federated foundation models towards biomedical healthcare
Abstract This survey explores the transformative impact of foundation models (FMs) in artificial intelligence, focusing on their integration with federated learning (FL) in biomedical research. Foundation models such as ChatGPT, LLaMa, and CLIP, which are trained on vast datasets through methods inc...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BioData Mining |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13040-024-00414-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559824624517120 |
|---|---|
| author | Xingyu Li Lu Peng Yu-Ping Wang Weihua Zhang |
| author_facet | Xingyu Li Lu Peng Yu-Ping Wang Weihua Zhang |
| author_sort | Xingyu Li |
| collection | DOAJ |
| description | Abstract This survey explores the transformative impact of foundation models (FMs) in artificial intelligence, focusing on their integration with federated learning (FL) in biomedical research. Foundation models such as ChatGPT, LLaMa, and CLIP, which are trained on vast datasets through methods including unsupervised pretraining, self-supervised learning, instructed fine-tuning, and reinforcement learning from human feedback, represent significant advancements in machine learning. These models, with their ability to generate coherent text and realistic images, are crucial for biomedical applications that require processing diverse data forms such as clinical reports, diagnostic images, and multimodal patient interactions. The incorporation of FL with these sophisticated models presents a promising strategy to harness their analytical power while safeguarding the privacy of sensitive medical data. This approach not only enhances the capabilities of FMs in medical diagnostics and personalized treatment but also addresses critical concerns about data privacy and security in healthcare. This survey reviews the current applications of FMs in federated settings, underscores the challenges, and identifies future research directions including scaling FMs, managing data diversity, and enhancing communication efficiency within FL frameworks. The objective is to encourage further research into the combined potential of FMs and FL, laying the groundwork for healthcare innovations. |
| format | Article |
| id | doaj-art-8e60c358e00c4b7e88c74232b45ac6f5 |
| institution | Kabale University |
| issn | 1756-0381 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BioData Mining |
| spelling | doaj-art-8e60c358e00c4b7e88c74232b45ac6f52025-01-05T12:10:25ZengBMCBioData Mining1756-03812025-01-0118115410.1186/s13040-024-00414-9Open challenges and opportunities in federated foundation models towards biomedical healthcareXingyu Li0Lu Peng1Yu-Ping Wang2Weihua Zhang3Department of Computer Science, Tulane UniversityDepartment of Computer Science, Tulane UniversityDepartment of Biomedical Engineering, Tulane UniversitySchool of Computer Science, Fudan UniversityAbstract This survey explores the transformative impact of foundation models (FMs) in artificial intelligence, focusing on their integration with federated learning (FL) in biomedical research. Foundation models such as ChatGPT, LLaMa, and CLIP, which are trained on vast datasets through methods including unsupervised pretraining, self-supervised learning, instructed fine-tuning, and reinforcement learning from human feedback, represent significant advancements in machine learning. These models, with their ability to generate coherent text and realistic images, are crucial for biomedical applications that require processing diverse data forms such as clinical reports, diagnostic images, and multimodal patient interactions. The incorporation of FL with these sophisticated models presents a promising strategy to harness their analytical power while safeguarding the privacy of sensitive medical data. This approach not only enhances the capabilities of FMs in medical diagnostics and personalized treatment but also addresses critical concerns about data privacy and security in healthcare. This survey reviews the current applications of FMs in federated settings, underscores the challenges, and identifies future research directions including scaling FMs, managing data diversity, and enhancing communication efficiency within FL frameworks. The objective is to encourage further research into the combined potential of FMs and FL, laying the groundwork for healthcare innovations.https://doi.org/10.1186/s13040-024-00414-9Foundation modelFederated learningHealthcareBiomedicalLarge language modelVision language model |
| spellingShingle | Xingyu Li Lu Peng Yu-Ping Wang Weihua Zhang Open challenges and opportunities in federated foundation models towards biomedical healthcare BioData Mining Foundation model Federated learning Healthcare Biomedical Large language model Vision language model |
| title | Open challenges and opportunities in federated foundation models towards biomedical healthcare |
| title_full | Open challenges and opportunities in federated foundation models towards biomedical healthcare |
| title_fullStr | Open challenges and opportunities in federated foundation models towards biomedical healthcare |
| title_full_unstemmed | Open challenges and opportunities in federated foundation models towards biomedical healthcare |
| title_short | Open challenges and opportunities in federated foundation models towards biomedical healthcare |
| title_sort | open challenges and opportunities in federated foundation models towards biomedical healthcare |
| topic | Foundation model Federated learning Healthcare Biomedical Large language model Vision language model |
| url | https://doi.org/10.1186/s13040-024-00414-9 |
| work_keys_str_mv | AT xingyuli openchallengesandopportunitiesinfederatedfoundationmodelstowardsbiomedicalhealthcare AT lupeng openchallengesandopportunitiesinfederatedfoundationmodelstowardsbiomedicalhealthcare AT yupingwang openchallengesandopportunitiesinfederatedfoundationmodelstowardsbiomedicalhealthcare AT weihuazhang openchallengesandopportunitiesinfederatedfoundationmodelstowardsbiomedicalhealthcare |