Avoiding catastrophic forgetting in mitigating model biases in sentence-pair classification with elastic weight consolidation

04/29/2020
by   James Thorne, et al.
0

The biases present in training datasets have been shown to be affecting models for a number of tasks such as natural language inference(NLI) and fact verification. While fine-tuning models on additional data has been used to mitigate such biases, a common issue is that of catastrophic forgetting of the original task. In this paper, we show that elastic weight consolidation (EWC) allows fine-tuning of models to mitigate biases for NLI and fact verification while being less susceptible to catastrophic forgetting. In our evaluation on fact verification systems, we show that fine-tuning with EWC Pareto dominates standard fine-tuning, yielding models lower levels of forgetting on the original task for equivalent gains in accuracy on the fine-tuned task. Additionally, we show that systems trained on NLI can be fine-tuned to improve their accuracy on stress test challenge tasks with minimal loss in accuracy on the MultiNLI dataset despite greater domain shift.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/28/2017

Gradual Tuning: a better way of Fine Tuning the parameters of a Deep Neural Network

In this paper we present an alternative strategy for fine-tuning the par...
research
09/19/2023

Investigating the Catastrophic Forgetting in Multimodal Large Language Models

Following the success of GPT4, there has been a surge in interest in mul...
research
08/17/2023

An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning

Catastrophic forgetting (CF) is a phenomenon that occurs in machine lear...
research
04/13/2022

Sapinet: A sparse event-based spatiotemporal oscillator for learning in the wild

We introduce Sapinet – a spike timing (event)-based multilayer neural ne...
research
11/30/2022

MSV Challenge 2022: NPU-HC Speaker Verification System for Low-resource Indian Languages

This report describes the NPU-HC speaker verification system submitted t...
research
05/28/2018

Adding New Tasks to a Single Network with Weight Trasformations using Binary Masks

Visual recognition algorithms are required today to exhibit adaptive abi...
research
09/13/2021

Mitigating Catastrophic Forgetting in Scheduled Sampling with Elastic Weight Consolidation in Neural Machine Translation

Despite strong performance in many sequence-to-sequence tasks, autoregre...

Please sign up or login with your details

Forgot password? Click here to reset