STARFISH recovers accuracy in pruned neural networks by optimizing internal state alignment to the original model with a minimal unlabeled calibration set, outperforming prior recovery methods especially at high pruning ratios.
Optimal brain connection: Towards efficient structural pruning.arXiv preprint arXiv:2508.05521, 2025
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
-
STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing
STARFISH recovers accuracy in pruned neural networks by optimizing internal state alignment to the original model with a minimal unlabeled calibration set, outperforming prior recovery methods especially at high pruning ratios.