Searching to Exploit Memorization Effect in Learning from Corrupted Labels

Abstract

Sample selection approaches are popular in robust learning from noisy labels. However, how to properly control the selection process so that deep networks can benefit from the memorization effect is a hard problem. In this paper, motivated by the success of automated machine learning (AutoML), we model this issue as a function approximation problem. Specifically, we design a domain-specific search space based on general patterns of the memorization effect and propose a novel Newton algorithm to solve the bi-level optimization problem efficiently. We further provide theoretical analysis of the algorithm, which ensures a good approximation to critical points. Experiments are performed on benchmark data sets. Results demonstrate that the proposed method is much better than the state-of-the-art noisy-label-learning approaches, and also much more efficient than existing AutoML algorithms.

References in corpus (11)

• Practical Bayesian Optimization of Machine Learning Algorithms
• Neural Architecture Search with Reinforcement Learning
• DARTS: Differentiable Architecture Search
• Understanding deep learning requires rethinking generalization
• Learning to Reweight Examples for Robust Deep Learning
• Classification with Noisy Labels by Importance Reweighting
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Designing Neural Network Architectures using Reinforcement Learning
• A Closer Look at Memorization in Deep Networks
• Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
• Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

Cited by in corpus (3)

• Identifying Mislabeled Data using the Area Under the Margin Ranking
• Unsupervised Domain Adaptation of Black-Box Source Models
• Combining Self-Supervised and Supervised Learning with Noisy Labels