Overcoming Conflicting Data for Model Updates

10/23/2020
by   David Gaddy, et al.
0

In this paper, we explore how to use a small amount of new data to update a model when the desired output for some examples has changed. When making updates in this way, one potential problem that arises is the presence of conflicting data, or out-of-date labels in the original training set. To evaluate the impact of this problem, we propose an experimental setup for simulating changes to a neural semantic parser. We show that the presence of conflicting data greatly hinders learning of an update, then explore several methods to mitigate its effect. Our methods lead to large improvements in model accuracy compared to a naive mixing strategy, and our best method closes 86 the accuracy gap between this baseline and an oracle upper bound.

READ FULL TEXT
research
04/09/2023

CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement

Due to the model aging problem, Deep Neural Networks (DNNs) need updates...
research
12/17/2019

Analyzing Privacy Loss in Updates of Natural Language Models

To continuously improve quality and reflect changes in data, machine lea...
research
04/05/2020

Personalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff

AI systems that model and interact with users can update their models ov...
research
07/20/2023

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Backdoor attacks are serious security threats to machine learning models...
research
01/24/2018

Training Set Debugging Using Trusted Items

Training set bugs are flaws in the data that adversely affect machine le...
research
02/11/2019

Divergence-Based Motivation for Online EM and Combining Hidden Variable Models

Expectation-Maximization (EM) is the fallback method for parameter estim...
research
05/29/2023

Self Information Update for Large Language Models through Mitigating Exposure Bias

Current LLMs have demonstrated remarkable capabilities in addressing use...

Please sign up or login with your details

Forgot password? Click here to reset