OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning
arXiv:2105.00602 · doi:10.1109/TPDS.2022.3157258
Abstract
The diversity and quantity of data warehouses, gathering data from distributed devices such as mobile devices, can enhance the success and robustness of machine learning algorithms. Federated learning enables distributed participants to collaboratively learn a commonly-shared model while holding data locally. However, it is also faced with expensive communication and limitations due to the heterogeneity of distributed data sources and lack of access to global data. In this paper, we investigate a practical distributed learning scenario where multiple downstream tasks (e.g., classifiers) could be efficiently learned from dynamically-updated and non-iid distributed data sources while providing local data privatization. We introduce a new distributed/collaborative learning scheme to address communication overhead via latent compression, leveraging global data while providing privatization of local data without additional cost due to encryption or perturbation. This scheme divides learning into (1) informative feature encoding, and transmitting the latent representation of local data to address communication overhead; (2) downstream tasks centralized at the server using the encoded codes gathered from each node to address computing overhead. Besides, a disentanglement strategy is applied to address the privatization of sensitive components of local data. Extensive experiments are conducted on image and speech datasets. The results demonstrate that downstream tasks on the compact latent representations with the privatization of local data can achieve comparable accuracy to centralized learning.
References in corpus (22)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Challenges, Methods, and Future Directions
- WaveNet: A Generative Model for Raw Audio
- Federated Learning: Strategies for Improving Communication Efficiency
- Neural Discrete Representation Learning
- Federated Learning with Non-IID Data
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- Towards Federated Learning at Scale: System Design
- How To Backdoor Federated Learning
- Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
- Federated Machine Learning: Concept and Applications
- Differentially Private Federated Learning: A Client Level Perspective
- Unsupervised speech representation learning using WaveNet autoencoders
- Local SGD Converges Fast and Communicates Little
- Practical Secure Aggregation for Federated Learning on User-Held Data
- Fast Decoding in Sequence Models using Discrete Latent Variables
- Federated Learning: Opportunities and Challenges
- PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
- Data Poisoning Attacks on Federated Machine Learning
- Efficient Privacy Preserving Edge Computing Framework for Image Classification