2023 Fiscal Year Annual Research Report
Trustworthy decentralized AI for large-scale IoT representation learning
| Project/Area Number |
22KJ0878
|
|---|
| Allocation Type | Multi-year Fund |
|---|
| Research Institution | The University of Tokyo |
|---|
Principal Investigator |
SUN YUWEI 東京大学, 情報理工学系研究科, 特別研究員(DC2)
|
|---|
| Project Period (FY) |
2023-03-08 – 2024-03-31
|
| Keywords | transfer learning / multi-modal / Transformer / modularity / attention |
|---|
| Outline of Annual Research Achievements |
This project delved into localized learning in multi-modal distributed machine learning to address the out-of-distribution problem. The study initially explored knowledge transfer among a group of expert models observing partial environments in a federated learning setup. It demonstrated that generalization could be attained through the coordination of localized models by extracting domain-invariant knowledge with a global model. An additional approach is the Markov chain-based Homogeneous Learning, where a meta-observer learns an efficient communication policy of individual models.
Overall, this project proposed novel approaches to reusable neural modules for distributed machine learning in real-world learning settings. The project contributed to invited talks and multiple publications in both journals and top conferences in the field.
|
Research Products
(15 results)
