Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability Ming Xiang
–Neural Information Processing Systems
Most prior work either overlooks the potential non-stationarity in the dynamics of client unavailability or requires substantial memory/computation overhead.
Neural Information Processing Systems
Feb-17-2026, 20:20:15 GMT
- Country:
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- California > San Francisco County
- San Francisco (0.14)
- Massachusetts > Suffolk County
- Boston (0.04)
- Pennsylvania > Allegheny County
- Pittsburgh (0.04)
- Virginia (0.04)
- California > San Francisco County
- Europe > United Kingdom
- Genre:
- Research Report > New Finding (0.45)
- Industry:
- Government (0.67)
- Technology: