Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer
Multi-task transfer learning based on pre-trained language encoders achieves state-of-the-art performance across a range of tasks. Standard approaches implicitly assume the tasks, for which we have training data, are equally representative of the tasks we are interested in, an assumption which is often hard to justify. This paper presents a more agnostic approach to multi-task transfer learning, which uses automated curriculum learning to minimize a new family of worst-case-aware losses across tasks. Not only do these losses lead to better performance on outlier tasks; they also lead to better performance in zero-shot and few-shot transfer settings.
Code (1)
Tasks
Transfer LearningSimilar Papers 제목 키워드 기반
Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze 2019), but only between relat…
Cross-Lingual TransferDependency ParsingMulti-Task LearningZero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models Wu and Dredze (2019), but only between relat…
Cross-Lingual TransferDependency ParsingMulti-Task LearningTight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
We develop a rigorous mathematical analysis of zero-shot learning with attributes. In this setting, the goal is to label novel classes with no training data, only detectors for attributes and a description of how those a…
AttributeZero-Shot LearningNon-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithm…
Model-based Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version
This work tackles the problem of robust zero-shot planning in non-stationary stochastic environments. We study Markov Decision Processes (MDPs) evolving over time and consider Model-Based Reinforcement Learning algorithm…
Model-based Reinforcement LearningReinforcement Learning