Knowledge Commons of Institute of Automation,CAS
FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction | |
Dianbo Sui1,2; Yubo Chen1,2; Jun Zhao1,2; Yantao Jia3; Yunantao Xie3; Weijian Sun3 | |
2020-11 | |
会议名称 | Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) |
会议日期 | 2020-11 |
会议地点 | Online |
摘要 | Unlike other domains, medical texts are inevitably accompanied by private information, so sharing or copying these texts is strictly restricted. However, training a medical relation extraction model requires collecting these privacy-sensitive texts and storing them on one machine, which comes in conflict with privacy protection. In this paper, we propose a privacy-preserving medical relation extraction model based on federated learning, which enables training a central model with no single piece of private local data being shared or exchanged. Though federated learning has distinct advantages in privacy protection, it suffers from the communication bottleneck, which is mainly caused by the need to upload cumbersome local parameters. To overcome this bottleneck, we leverage a strategy based on knowledge distillation. Such a strategy uses the uploaded predictions of ensemble local models to train the central model without requiring uploading local parameters. Experiments on three publicly available medical relation extraction datasets demonstrate the effectiveness of our method. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48927 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Yubo Chen |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Huawei Technologies Co., Ltd |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Dianbo Sui,Yubo Chen,Jun Zhao,et al. FedED: Federated Learning via Ensemble Distillation for Medical Relation Extraction[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2020.emnlp-main.165.(382KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论