Two continual learning methods applied to sequential early-exit training reduce interference between exits, yielding higher accuracy and faster inference at low compute budgets on standard benchmarks.
Learning multiple layers of features from tiny images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A unified compression pipeline for federated learning delivers over 11x model size reduction and 60% faster training with a 2% accuracy drop on CIFAR-10 ResNet-12 under 2 Mbps bandwidth.
citing papers explorer
-
Balancing Stability and Plasticity in Sequentially Trained Early-Exiting Neural Networks
Two continual learning methods applied to sequential early-exit training reduce interference between exits, yielding higher accuracy and faster inference at low compute budgets on standard benchmarks.
-
A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments
A unified compression pipeline for federated learning delivers over 11x model size reduction and 60% faster training with a 2% accuracy drop on CIFAR-10 ResNet-12 under 2 Mbps bandwidth.