Collate jointly trains heterogeneous models under per-device latency constraints via dynamic zeroizing-recovering and proto-corrected aggregation, gaining ~2–3% accuracy over prior heterogeneous FL.
Morphnet: Fast & simple resource-constrained structure learn- ing of deep networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems
Collate jointly trains heterogeneous models under per-device latency constraints via dynamic zeroizing-recovering and proto-corrected aggregation, gaining ~2–3% accuracy over prior heterogeneous FL.