Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift

By Marvin Zhang, Henrik Marklund, Abhishek Gupta, Sergey Levine, Chelsea Finn. 2020

88 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On Generalizing Beyond Domains in Cross-Domain Continual Learning (2022, methodology): “Additionally, to handle distribution shifts at test time, ARM [38] uses a contextual network that utilizes extra domain information via a meta-learning strategy.”
SWAD: Domain Generalization by Seeking Flat Minima (2021, neutral): “…68.7 [31] 48.6 [32] 43.6 [15, 33] 65.3 SWAD (proposed) 88.1 79.1 70.6 50.0 46.5 66.9 Previous SOTA [31] + SWAD 88.3 78.9 71.3 51.0 46.8 67.3 12], obtained well-transferable model parameters by the meta-learning framework [13–16], data augmentation [17–19], or capturing causal relation [20, 21].”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “For example, adaptive risk minimization (ARM) is a meta-learning approach that adapts models to each batch of test examples under the assumption that all data points in a batch come from the same domain (Zhang et al., 2020).”
Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (2021, methodology): “These results include the following algorithms: Empirical Risk Minimization (ERM), Group Distributionally Robust Optimization (GroupDRO) [41], Inter-domain Mixup (Mixup) [56, 58, 53], Meta-Learning for Domain Generalization (MLDG) [28], DomainAdversarial Neural Networks (DANN) [15], Class-conditiona”
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization (2021, background): “This testbed currently provides seven multi-domain datasets (i.e. ColoredMNIST [1], RotatedMNIST [16], VLCS [13], PACS [26], Ofﬁce-Home [42], and TerraIncognita [2], DomainNet [34]) and provides benchmarks results of 14 baseline approaches (i.e. ERM [41], IRM [1], GroupDRO [36], Mixup [45], MLDG [27”