STARFISH: faST Accuracy Recovery in pruned networks From Internal State Healing

ArXi:2606.01126v1 Announce Type: cross Pruning is a process designed to reduce the number of weights in a large neural network. This can substantially speed up inference but might cause a considerable reduction in the model's accuracy, and thus it is usually followed by a healing process that regains some of the lost accuracy. In this paper, we propose a new healing method, STARFISH, that can recover (most of) the accuracy of any pruned network efficiently.