Knowledge-Injected Federated Learning
This addresses the challenge of leveraging human expertise in decentralized machine learning for industry applications, but appears incremental as it builds on existing federated learning methods.
The authors tackled the problem of incorporating domain knowledge from participants into federated learning, proposing a framework that refines the global model locally, and demonstrated its effectiveness in a real industry-level application.
Federated learning is an emerging technique for training models from decentralized data sets. In many applications, data owners participating in the federated learning system hold not only the data but also a set of domain knowledge. Such knowledge includes human know-how and craftsmanship that can be extremely helpful to the federated learning task. In this work, we propose a federated learning framework that allows the injection of participants' domain knowledge, where the key idea is to refine the global model with knowledge locally. The scenario we consider is motivated by a real industry-level application, and we demonstrate the effectiveness of our approach to this application.