DeepAI AI Chat
Log In Sign Up

Learning to Select Pivotal Samples for Meta Re-weighting

by   Yinjun Wu, et al.
University of Pennsylvania

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.


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

Imbalanced data pose challenges for deep learning based classification m...

A Reweighted Meta Learning Framework for Robust Few Shot Learning

Model-Agnostic Meta-Learning (MAML) is a popular gradient-based meta-lea...

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 ...

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

Learning with labels noise has gained significant traction recently due ...

Optimal Representative Sample Weighting

We consider the problem of assigning weights to a set of samples or data...

Accelerating numerical methods by gradient-based meta-solving

In science and engineering applications, it is often required to solve s...

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

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

Code Repositories