Corpus ID: 54439509

Split learning for health: Distributed deep learning without sharing raw patient data

@article{Vepakomma2018SplitLF,
  title={Split learning for health: Distributed deep learning without sharing raw patient data},
  author={Praneeth Vepakomma and Otkrist Gupta and Tristan Swedish and Ramesh Raskar},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.00564}
}
Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not share raw data or model details with collaborating institutions. The proposed configurations of splitNN cater to practical settings of i) entities holding different modalities of patient data, ii) centralized and local health entities collaborating on… Expand
Split Learning for collaborative deep learning in healthcare
TLDR
This work proves the significant benefit of distributed learning in healthcare, and paves the way for future real-world implementations of split learning based approach in the medical field. Expand
Gradient Assisted Learning
TLDR
This work proposes Gradient Assisted Learning (GAL), a new method for various entities to assist each other in supervised learning tasks without sharing data, models, and objective functions. Expand
Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
TLDR
An extendable and elastic learning framework to preserve privacy and security while enabling collaborative learning with efficient communication is proposed. Expand
An Experimental Study of Data Heterogeneity in Federated Learning Methods for Medical Imaging
TLDR
The proposed optimizations to federated learning methods improve their capability of handling heterogeneity across institutions, which provides valuable guidance for the deployment of Federated learning in real clinical applications. Expand
R EDUCING LEAKAGE IN DISTRIBUTED DEEP LEARNING FOR SENSITIVE HEALTH DATA
For distributed machine learning with health data we demonstrate how minimizing distance correlation between raw data and intermediary representations (smashed data) reduces leakage of sensitive rawExpand
Privacy-Sensitive Parallel Split Learning
TLDR
A parallel split learning method is proposed that prevents overfitting due to differences in a training order and data size by the node and synchronizes the layers that nodes have during the training process so that all nodes can use the equivalent deep learning model when the training is complete. Expand
Handling Data Heterogeneity with Generative Replay in Collaborative Learning for Medical Imaging
TLDR
A novel generative replay strategy that can be incorporated into existing collaborative learning methods to improve their capability of handling data heterogeneity across institutions, or used as a novel and individual collaborative learning framework (termed FedReplay) to reduce communication cost. Expand
Federated and Differentially Private Learning for Electronic Health Records
TLDR
It is found that while it is straightforward to apply differentially private stochastic gradient descent to achieve strong privacy bounds when training in a centralized setting, it is considerably more difficult to do so in the federated setting. Expand
Comparison of Privacy-Preserving Distributed Deep Learning Methods in Healthcare
TLDR
This paper uses federated learning, split learning, and SplitFed to develop binary classification models for detecting tuberculosis from chest X-rays and compares them in terms of classification performance, communication and computational costs, and training time. Expand
QoE Modeling on Split Features with Distributed Deep Learning
TLDR
The DEL approach is ML model-agnostic and achieves up to 12% accuracy improvement of ensembling various generic and specific models and the vFL approach is based on neural networks and achieves on-par accuracy with a conventional Fully Centralized machine learning model, while exhibiting statistically significant performance that is superior to that of the Isolated local models. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 43 REFERENCES
Distributed learning of deep neural network over multiple agents
TLDR
This work proposes a new technique to train deep neural networks over several data sources in a distributed fashion, which paves the way for distributed training ofDeep neural networks in data sensitive applications when raw data may not be shared directly. Expand
Efficient Deep Learning on Multi-Source Private Data
TLDR
This work introduces Myelin, a deep learning framework which combines privacy-preservation primitives, and uses it to establish a baseline level of performance for fully private machine learning. Expand
Deep learning for healthcare: review, opportunities and challenges
TLDR
It is suggested that deep learning approaches could be the vehicle for translating big biomedical data into improved human health and develop holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability. Expand
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
TLDR
Private Aggregation of Teacher Ensembles (PATE) is demonstrated, in a black-box fashion, multiple models trained with disjoint datasets, such as records from different subsets of users, which achieves state-of-the-art privacy/utility trade-offs on MNIST and SVHN. Expand
Communication-Efficient Learning of Deep Networks from Decentralized Data
TLDR
This work presents a practical method for the federated learning of deep networks based on iterative model averaging, and conducts an extensive empirical evaluation, considering five different model architectures and four datasets. Expand
Revisiting Distributed Synchronous SGD
TLDR
It is demonstrated that a third approach, synchronous optimization with backup workers, can avoid asynchronous noise while mitigating for the worst stragglers and is empirically validated and shown to converge faster and to better test accuracies. Expand
Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis
TLDR
This review surveys the current research on applying deep learning to clinical tasks based on EHR data, where a variety of deep learning techniques and frameworks are being applied to several types of clinical applications including information extraction, representation learning, outcome prediction, phenotyping, and deidentification. Expand
Federated Learning: Strategies for Improving Communication Efficiency
TLDR
Two ways to reduce the uplink communication costs are proposed: structured updates, where the user directly learns an update from a restricted space parametrized using a smaller number of variables, e.g. either low-rank or a random mask; and sketched updates, which learn a full model update and then compress it using a combination of quantization, random rotations, and subsampling. Expand
Federated Multi-Task Learning
TLDR
This work shows that multi-task learning is naturally suited to handle the statistical challenges of this setting, and proposes a novel systems-aware optimization method, MOCHA, that is robust to practical systems issues. Expand
Deep Learning for Health Informatics
TLDR
A comprehensive up-to-date review of research employing deep learning in health informatics is presented, providing a critical analysis of the relative merit, and potential pitfalls of the technique as well as its future outlook. Expand
...
1
2
3
4
5
...