Background
In traditional centralized machine learning, all data will be transmitted from devices (e.g., mobile phone, laptop, vehicles) to the central server. Then, the server will build a training model based on the received data.
Different from the traditional centralized machine algorithms, federated learning is a new distributed machine learning. The raw data will be kept locally in a device. Each device will build a training machine learning model purely based on its own data. Then, the device will send the parameters of the model to the server. Finally, the server will collect all parameters from all devices and then apply an aggregation method to build the system machine learning model.
Federated learning has many advantages, compared with the centralized machine learning methods. First, the raw data are kept locally in a device and the data privacy is naturally preserved. Second, raw data are not transmitted while only model parameters are
transmitted. In some applications (e.g., video surveillance), the transmitted data is largely reduced.
Still, we can see a significant challenge related to federated learning. For example, when there are many vehicles in a transport system, all vehicles need to transmit the parameters of their machine learning models to the server. This will incur substantial communications overhead between devices and the server. It becomes very important to propose new methods to reduce the communications overhead between devices and the server.
Goal
To have a good understanding of federated learning and then develop
new methods to reduce communications overhead in federated learning
What will the student do?
- Understand federated learning: concepts, architectures, advantages, challenges and applications
- Design new methods to reduced communications overhead in federated learning
- Program and simulate the reduced communications overhead in a scenario
Want to know more information?
Please feel free drop us an email and we can have a Zoom meeting