MetaRepair: Learning to Repair Deep Neural Networks from Repairing Experiences

Repairing deep neural networks (DNNs) to maintain its performance during deployment presents significant challenges due to the potential occurrence of unknown but common environmental corruptions. Most existing DNN repair methods only focus on repairing DNN for each corruption separately, lacking the ability of generalizing to the myriad corruptions from the ever-changing deploying environment. In this work, we propose to repair DNN from a novel perspective, i.e. Learning to Repair (L2R), where the repairing of target DNN is realized as a general learning-to-learn, a.k.a. meta-learning, process. In specific, observing different corruptions are correlated on their data distributions, we propose to utilize previous DNN repair experiences as tasks for meta-learning how to repair the target corruption. With the meta-learning from different tasks, L2R learns a meta-knowledge that summarizes how the DNN is repaired under various environmental corruptions. The meta-knowledge essentially serves as a general repairing prior which enables the DNN quickly adapt to unknown corruptions, thus making our method generalizable to different type of corruptions. Practically, L2R benefits DNN repair with a general pipeline yet tailoring meta-learning for repairing DNN is not trivial. By re-designing the meta-learning components under DNN repair context, we further instantiate the proposed L2R strategy into a concrete model named MetaRepair with pragmatic assumption of experience availability. We conduct comprehensive experiments on the corrupted CIFAR-10 and tiny -ImageNet by applying MetaRepair to repair DenseNet, ConvNeXt and VAN. The experimental results confirmed the superior repairing and generalization capability of our proposed L2R strategy under various environmental corruptions.