A clustering-based process for creating federated learning benchmarks with controllable semantic heterogeneity, demonstrated on panoptic scene graph generation and CelebA.
Sharpness- awareminimizationforefficientlyimprovinggeneralization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Benchmarking Federated Learning for Semantic Datasets: Federated Scene Graph Generation
A clustering-based process for creating federated learning benchmarks with controllable semantic heterogeneity, demonstrated on panoptic scene graph generation and CelebA.