Learning to Select Pivotal Samples for Meta Re-weighting

TL;DR

This paper introduces a learning framework to identify optimal meta samples from large, imperfect datasets for improved re-weighting in machine learning, using clustering methods to enhance performance.

Contribution

It proposes a novel approach that learns to select meta samples via clustering, addressing the challenge of imperfect data in meta re-weighting.

Findings

RBC and GBC outperform baseline methods in experiments.

Theoretical analysis supports the clustering approach.

Methods improve model robustness with noisy data.

Abstract

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.