Learning to Select Pivotal Samples for Meta Re-weighting

02/09/2023
by   Yinjun Wu, et al.
0

Sample re-weighting strategies provide a promising mechanism to deal with imperfect training data in machine learning, such as noisily labeled or class-imbalanced data. One such strategy involves formulating a bi-level optimization problem called the meta re-weighting problem, whose goal is to optimize performance on a small set of perfect pivotal samples, called meta samples. Many approaches have been proposed to efficiently solve this problem. However, all of them assume that a perfect meta sample set is already provided while we observe that the selections of meta sample set is performance critical. In this paper, we study how to learn to identify such a meta sample set from a large, imperfect training set, that is subsequently cleaned and used to optimize performance in the meta re-weighting setting. We propose a learning framework which reduces the meta samples selection problem to a weighted K-means clustering problem through rigorously theoretical analysis. We propose two clustering methods within our learning framework, Representation-based clustering method (RBC) and Gradient-based clustering method (GBC), for balancing performance and computational efficiency. Empirical studies demonstrate the performance advantage of our methods over various baseline methods.

READ FULL TEXT
research
08/05/2022

Learning to Re-weight Examples with Optimal Transport for Imbalanced Classification

Imbalanced data pose challenges for deep learning based classification m...
research
11/13/2020

A Reweighted Meta Learning Framework for Robust Few Shot Learning

Model-Agnostic Meta-Learning (MAML) is a popular gradient-based meta-lea...
research
11/01/2018

META-DES.H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach

In Dynamic Ensemble Selection (DES) techniques, only the most competent ...
research
04/19/2021

Do We Really Need Gold Samples for Sample Weighting Under Label Noise?

Learning with labels noise has gained significant traction recently due ...
research
05/18/2020

Optimal Representative Sample Weighting

We consider the problem of assigning weights to a set of samples or data...
research
06/17/2022

Accelerating numerical methods by gradient-based meta-solving

In science and engineering applications, it is often required to solve s...
research
06/29/2023

Causal Meta-Analysis by Integrating Multiple Observational Studies with Multivariate Outcomes

Integrating multiple observational studies to make unconfounded causal o...

Please sign up or login with your details

Forgot password? Click here to reset