Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the properties of these languages are often not well represented by those available during training. Hence, we argue that the i.i.d. assumption ingrained in MAML makes it ill-suited for cross-lingual NLP. In fact, under a decision-theoretic framework, MAML can be interpreted as minimising the expected risk across training languages (with a uniform prior), which is known as Bayes criterion. To increase its robustness to outlier languages, we create two variants of MAML based on alternative criteria: Minimax MAML reduces the maximum risk across languages, while Neyman-Pearson MAML constrains the risk in each language to a maximum threshold. Both criteria constitute fully differentiable two-player games. In light of this, we propose a new adaptive optimiser solving for a local approximation to their Nash equilibrium. We evaluate both model variants on two popular NLP tasks, part-of-speech tagging and question answering. We report gains for their average and minimum performance across low-resource languages in zero- and few-shot settings, compared to joint multi-source transfer and vanilla MAML.
Code (1)
Tasks
Meta-LearningPart-Of-Speech TaggingQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages
Transfer Neyman-Pearson Algorithm for Outlier Detection
We consider the problem of transfer learning in outlier detection where target abnormal data is rare. While transfer learning has been considered extensively in traditional balanced classification, the problem of transfe…
Classificationimbalanced classificationOutlier DetectionTransfer LearningDistribution-Free Rates in Neyman-Pearson Classification
We consider the problem of Neyman-Pearson classification which models unbalanced classification settings where error w.r.t. a distribution $\mu_1$ is to be minimized subject to low error w.r.t. a different distribution $…
ClassificationDensity Ratio Estimation and Neyman Pearson Classification with Missing Data
Density Ratio Estimation (DRE) is an important machine learning technique with many downstream applications. We consider the challenge of DRE with missing not at random (MNAR) data. In this setting, we show that using st…
Density Ratio EstimationBounding Neyman-Pearson Region with $f$-Divergences
The Neyman-Pearson region of a simple binary hypothesis testing is the set of points whose coordinates represent the false positive rate and false negative rate of some test. The lower boundary of this region is given by…
LEMMA