paper-with-me

홈 › Papers

Elastic weight consolidation for better bias inoculation

2020-04-29 · EACL 2021 2 · James Thorne, Andreas Vlachos

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.

📄 PDF Abstract BibTeX arXiv:2004.14366

Code (1)

j6mes/eacl2021-debias-finetuning 공식 구현 pytorch

Tasks

Fact VerificationGeneral ClassificationNatural Language InferenceSentenceSentence-Pair Classification

Methods 이 논문이 사용한 방법론

EWC The methon to overcome catastrophic forgetting in neural network while continual learning

Similar Papers 제목 키워드 기반

EVCL: Elastic Variational Continual Learning with Weight Consolidation

2024-06-23 · Hunar Batra, Ronald Clark

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 Learning

Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation

2021-09-13 · Michalis Korakakis, Andreas Vlachos

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 TranslationTranslation

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

2018-02-08 · Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer 외

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 learning

Elastic Weight Consolidation Improves the Robustness of Self-Supervised Learning Methods under Transfer

2022-10-28 · Andrius Ovsianas, Jason Ramapuram, Dan Busbridge, Eeshan Gunesh Dhekane 외

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 Learning

Elastic Weight Consolidation (EWC): Nuts and Bolts

2021-05-10 · Abhishek Aich

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