Neural Information Processing Systems · 2018 · 404 citations · 27 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningDomain ModelingMeta-learningRepresentation LearningCross-domain GeneralizationDomain AdaptationDomain GeneralizationExperimental ValidationMeta-regularizationMeta-trainingRegularization
Training models that generalize to new domains at test time is a problem of fundamental importance in machine learning. The authors aim to encode domain generalization by introducing a novel regularization function. They formulate the search for this regularizer within a meta‑learning framework, learning a regularizer that improves performance on unseen domains. Experimental validation on computer vision and natural language datasets demonstrates that the learned regularizers achieve strong cross‑domain generalization.
Training models that generalize to new domains at test time is a problem of fundamental importance in machine learning. In this work, we encode this notion of domain generalization using a novel regularization function. We pose the problem of finding such a regularization function in a Learning to Learn (or) meta-learning framework. The objective of domain generalization is explicitly modeled by learning a regularizer that makes the model trained on one domain to perform well on another domain. Experimental validations on computer vision and natural language datasets indicate that our method can learn regularizers that achieve good cross-domain generalization.
27
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations