Task2Vec-based unsupervised metrics of client embedding cohesion, dispersion, and density correlate strongly with final federated learning performance across multiple datasets and heterogeneity levels.
Mohammed Aledhari, Rehma Razzak, Reza M Parizi, and Fahad Saeed
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Task2vec Readiness: Diagnostics for Federated Learning from Pre-Training Embeddings
Task2Vec-based unsupervised metrics of client embedding cohesion, dispersion, and density correlate strongly with final federated learning performance across multiple datasets and heterogeneity levels.