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

2018/12/03 by Praneeth Vepakomma, Otkrist Gupta, Vepakomma, Praneeth +5 · 36 citations
Computer Science · Medicine · #AI in cancer detection #Artificial Intelligence in Healthcare and Education #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Healthcare #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.1812.00564

openalex publication_date 2018/12/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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 multiple tasks and iii) learning without sharing labels. We compare performance and resource efficiency trade-offs of splitNN and other distributed deep learning methods like federated learning, large batch synchronous stochastic gradient descent and show highly encouraging results for splitNN.

Cited by

• REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature
• Hetero-SplitEE: Split Learning of Neural Networks with Early Exits for Heterogeneous IoT Devices
• Communication-Computation Pipeline Parallel Split Learning over Wireless Edge Networks
• Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning
• Accelerating Wireless Distributed Learning via Hybrid Split and Federated Learning Optimization
• CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning
• Sigil: Server-Enforced Watermarking in U-Shaped Split Federated Learning via Gradient Injection
• SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
• Data Heterogeneity and Forgotten Labels in Split Federated Learning
• Verifiable Split Learning via zk-SNARKs
• Split Learning-Enabled Framework for Secure and Light-weight Internet of Medical Things Systems
• Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
• CO-PFL: Contribution-Oriented Personalized Federated Learning for Heterogeneous Networks
• PrivaDE: Privacy-preserving Data Evaluation for Blockchain-based Data Marketplaces
• RockNet: Distributed Learning on Ultra-Low-Power Devices
• BlendFL: Blended Federated Learning for Handling Multimodal Data Heterogeneity
• Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
• Parameter-Efficient and Personalized Federated Training of Generative Models at the Edge
• Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
• Enhancing Split Learning with Sharded and Blockchain-Enabled SplitFed Approaches
• Communication-Efficient and Interoperable Distributed Learning
• Functional Encryption in Secure Neural Network Training: Data Leakage and Practical Mitigations
• Optimizing Split Federated Learning with Unstable Client Participation
• Service Function Chaining Architecture for Multi-hop Split Inference and Learning
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
• Flexible Personalized Split Federated Learning for On-Device Fine-Tuning of Foundation Models
• SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning
• X-VFL: A New Vertical Federated Learning Framework with Cross Completion and Decision Subspace Alignment
• VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
• Pigeon-SL: Robust Split Learning Framework for Edge Intelligence under Malicious Clients
• Federated Split Learning with Improved Communication and Storage Efficiency
• Characterizing Linear Alignment Across Language Models
• P3SL: Personalized Privacy-Preserving Split Learning on Heterogeneous Edge Devices
• VGS-ATD: Robust Distributed Learning for Multi-Label Medical Image Classification Under Heterogeneous and Imbalanced Conditions
• A Distributed Generative AI Approach for Heterogeneous Multi-Domain Environments under Data Sharing constraints
• VeFIA: An Efficient Inference Auditing Framework for Vertical Federated Collaborative Software

Related

• Split Learning for collaborative deep learning in healthcare
• Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics
• Comparison of Privacy-Preserving Distributed Deep Learning Methods in Healthcare
• Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation
• Federated Split Vision Transformer for COVID-19 CXR Diagnosis using Task-Agnostic Training