Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...最新文献

{"title":"Federated Learning: Fundamentals and Advances","authors":"Yaochu Jin, Hangyu Zhu, Jinjin Xu, Yang Chen","doi":"10.1007/978-981-19-7083-2","DOIUrl":"https://doi.org/10.1007/978-981-19-7083-2","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87962976","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation.","authors":"Chenyu You, Jinlin Xiang, Kun Su, Xiaoran Zhang, Siyuan Dong, John Onofrey, Lawrence Staib, James S Duncan","doi":"10.1007/978-3-031-18523-6_1","DOIUrl":"10.1007/978-3-031-18523-6_1","url":null,"abstract":"<p><p>Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2) generalizes well and transfers better to the unknown target site domain. Prior works have achieved this goal by jointly training one model on multi-site datasets, which achieve competitive performance on average but such methods rely on the assumption about the availability of all training data, thus limiting its effectiveness in practical deployment. In this paper, we propose a novel multi-site segmentation framework called <b>incremental-transfer learning (ITL)</b>, which learns a model from multi-site datasets in an end-to-end sequential fashion. Specifically, \"incremental\" refers to training sequentially constructed datasets, and \"transfer\" is achieved by leveraging useful information from the linear combination of embedding features on each dataset. In addition, we introduce our ITL framework, where we train the network including a site-agnostic encoder with pretrained weights and at most two segmentation decoder heads. We also design a novel site-level incremental loss in order to generalize well on the target domain. Second, we show for the first time that leveraging our ITL training scheme is able to alleviate challenging catastrophic forgetting problems in incremental learning. We conduct experiments using five challenging benchmark datasets to validate the effectiveness of our incremental-transfer learning approach. Our approach makes minimal assumptions on computation resources and domain-specific expertise, and hence constitutes a strong starting point in multi-site medical image segmentation.</p>","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"13573 ","pages":"3-16"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10323962/pdf/nihms-1913002.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9806819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensembling","authors":"Sourav Kumar, A. Lakshminarayanan, Ken Chang, Feri Guretno, Ivan Ho Mien, Jayashree Kalpathy-Cramer, Pavitra Krishnaswamy, Praveer Singh","doi":"10.48550/arXiv.2209.05424","DOIUrl":"https://doi.org/10.48550/arXiv.2209.05424","url":null,"abstract":"Federated Learning (FL) wherein multiple institutions collaboratively train a machine learning model without sharing data is becoming popular. Participating institutions might not contribute equally - some contribute more data, some better quality data or some more diverse data. To fairly rank the contribution of different institutions, Shapley value (SV) has emerged as the method of choice. Exact SV computation is impossibly expensive, especially when there are hundreds of contributors. Existing SV computation techniques use approximations. However, in healthcare where the number of contributing institutions are likely not of a colossal scale, computing exact SVs is still exorbitantly expensive, but not impossible. For such settings, we propose an efficient SV computation technique called SaFE (Shapley Value for Federated Learning using Ensembling). We empirically show that SaFE computes values that are close to exact SVs, and that it performs better than current SV approximations. This is particularly relevant in medical imaging setting where widespread heterogeneity across institutions is rampant and fast accurate data valuation is required to determine the contribution of each participant in multi-institutional collaborative learning.","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"16 1","pages":"119-129"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73408933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensembling.","authors":"Sourav Kumar,&nbsp;A Lakshminarayanan,&nbsp;Ken Chang,&nbsp;Feri Guretno,&nbsp;Ivan Ho Mien,&nbsp;Jayashree Kalpathy-Cramer,&nbsp;Pavitra Krishnaswamy,&nbsp;Praveer Singh","doi":"10.1007/978-3-031-18523-6_12","DOIUrl":"10.1007/978-3-031-18523-6_12","url":null,"abstract":"<p><p>Federated Learning (FL) wherein multiple institutions collaboratively train a machine learning model without sharing data is becoming popular. Participating institutions might not contribute equally - some contribute more data, some better quality data or some more diverse data. To fairly rank the contribution of different institutions, Shapley value (SV) has emerged as the method of choice. Exact SV computation is impossibly expensive, especially when there are hundreds of contributors. Existing SV computation techniques use approximations. However, in healthcare where the number of contributing institutions are likely not of a colossal scale, computing exact SVs is still exorbitantly expensive, but not impossible. For such settings, we propose an efficient SV computation technique called SaFE (Shapley Value for Federated Learning using Ensembling). We empirically show that SaFE computes values that are close to exact SVs, and that it performs better than current SV approximations. This is particularly relevant in medical imaging setting where widespread heterogeneity across institutions is rampant and fast accurate data valuation is required to determine the contribution of each participant in multi-institutional collaborative learning.</p>","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"13573 ","pages":"119-129"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9890952/pdf/nihms-1859434.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10673796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Incremental Learning Meets Transfer Learning: Application to Multi-site Prostate MRI Segmentation","authors":"Chenyu You, Jinlin Xiang, Kun Su, Xiaoran Zhang, Siyuan Dong, John A. Onofrey, L. Staib, J. Duncan","doi":"10.48550/arXiv.2206.01369","DOIUrl":"https://doi.org/10.48550/arXiv.2206.01369","url":null,"abstract":"Many medical datasets have recently been created for medical image segmentation tasks, and it is natural to question whether we can use them to sequentially train a single model that (1) performs better on all these datasets, and (2) generalizes well and transfers better to the unknown target site domain. Prior works have achieved this goal by jointly training one model on multi-site datasets, which achieve competitive performance on average but such methods rely on the assumption about the availability of all training data, thus limiting its effectiveness in practical deployment. In this paper, we propose a novel multi-site segmentation framework called incremental-transfer learning (ITL), which learns a model from multi-site datasets in an end-to-end sequential fashion. Specifically, \"incremental\" refers to training sequentially constructed datasets, and \"transfer\" is achieved by leveraging useful information from the linear combination of embedding features on each dataset. In addition, we introduce our ITL framework, where we train the network including a site-agnostic encoder with pretrained weights and at most two segmentation decoder heads. We also design a novel site-level incremental loss in order to generalize well on the target domain. Second, we show for the first time that leveraging our ITL training scheme is able to alleviate challenging catastrophic forgetting problems in incremental learning. We conduct experiments using five challenging benchmark datasets to validate the effectiveness of our incremental-transfer learning approach. Our approach makes minimal assumptions on computation resources and domain-specific expertise, and hence constitutes a strong starting point in multi-site medical image segmentation.","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"110 1","pages":"3-16"},"PeriodicalIF":0.0,"publicationDate":"2022-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87715630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Security and Robustness in Federated Learning","authors":"Ambrish Rawat, Giulio Zizzo, Muhammad Zaid Hameed, Luis Muñoz-González","doi":"10.1007/978-3-030-96896-0_16","DOIUrl":"https://doi.org/10.1007/978-3-030-96896-0_16","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"37 1","pages":"363-390"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74044856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tree-Based Models for Federated Learning Systems","authors":"Yuya Jeremy Ong, N. Baracaldo, Yi Zhou","doi":"10.1007/978-3-030-96896-0_2","DOIUrl":"https://doi.org/10.1007/978-3-030-96896-0_2","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"99 1","pages":"27-52"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79289573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated Reinforcement Learning for Portfolio Management","authors":"Pengqian Yu, L. Wynter, Shiau Hong Lim","doi":"10.1007/978-3-030-96896-0_21","DOIUrl":"https://doi.org/10.1007/978-3-030-96896-0_21","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"34 1","pages":"467-482"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72908911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Protecting Against Data Leakage in Federated Learning: What Approach Should You Choose?","authors":"N. Baracaldo, Runhua Xu","doi":"10.1007/978-3-030-96896-0_13","DOIUrl":"https://doi.org/10.1007/978-3-030-96896-0_13","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"693 1","pages":"281-312"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80186787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introduction to Federated Learning Systems","authors":"Syed Zawad, Feng Yan, A. Anwar","doi":"10.1007/978-3-030-96896-0_9","DOIUrl":"https://doi.org/10.1007/978-3-030-96896-0_9","url":null,"abstract":"","PeriodicalId":72833,"journal":{"name":"Distributed, collaborative, and federated learning, and affordable AI and healthcare for resource diverse global health : Third MICCAI Workshop, DeCaF 2022 and Second MICCAI Workshop, FAIR 2022, held in conjunction with MICCAI 2022, Sin...","volume":"4 1","pages":"195-212"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84907702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}