Elastic weight consolidation for better bias inoculation
The biases present in training datasets have been shown to affect models for sentence pair classification tasks such as natural language inference (NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate them, a common issue is that of catastrophic forgetting of the original training dataset. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases while being less susceptible to catastrophic forgetting. In our evaluation on fact verification and NLI stress tests, we show that fine-tuning with EWC dominates standard fine-tuning, yielding models with lower levels of forgetting on the original (biased) dataset for equivalent gains in accuracy on the fine-tuning (unbiased) dataset.
Code (1)
Tasks
Fact VerificationGeneral ClassificationNatural Language InferenceSentenceSentence-Pair ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EVCL: Elastic Variational Continual Learning with Weight Consolidation
Continual learning aims to allow models to learn new tasks without forgetting what has been learned before. This work introduces Elastic Variational Continual Learning with Weight Consolidation (EVCL), a novel hybrid mod…
Continual LearningIncremental LearningImproving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation
Despite strong performance in many sequence-to-sequence tasks, autoregressive models trained with maximum likelihood estimation suffer from exposure bias, i.e. the discrepancy between the ground-truth prefixes used durin…
Machine TranslationTranslationRotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Informatio…
Lifelong learningElastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer
Self-supervised representation learning (SSL) methods provide an effective label-free initial condition for fine-tuning downstream tasks. However, in numerous realistic scenarios, the downstream task might be biased with…
Continual LearningRepresentation LearningSelf-Supervised LearningElastic Weight Consolidation (EWC): Nuts and Bolts
In this report, we present a theoretical support of the continual learning method \textbf{Elastic Weight Consolidation}, introduced in paper titled `Overcoming catastrophic forgetting in neural networks'. Being one of th…
Continual Learning