Searching to Exploit Memorization Effect in Learning from Corrupted Labels

Understand

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.