Identifiability of Label Noise Transition Matrix
Jul 24, 2023
Speakers
About
The noise transition matrix plays a central role in the problem of learning with noisy labels. Among many other reasons, a large number of existing solutions rely on the knowledge of it. Identifying and estimating the transition matrix without ground truth labels is a critical and challenging task. When label noise transition depends on each instance, the problem of identifying the instance-dependent noise transition matrix becomes substantially more challenging. Despite recent proposed solutions for learning from instance-dependent noisy labels, the literature lacks a unified understanding of when such a problem remains identifiable. The goal of this paper is to characterize the identifiability of the label noise transition matrix. Building on Kruskal's identifiability results, we are able to show the necessity of multiple noisy labels in identifying the noise transition matrix at the instance level. We further instantiate the results to explain the successes of the state-of-the-art solutions and how additional assumptions alleviated the requirement of multiple noisy labels. Our result reveals that disentangled features improve identification. This discovery led us to an approach that improves the estimation of the transition matrix using properly disentangled features.The noise transition matrix plays a central role in the problem of learning with noisy labels. Among many other reasons, a large number of existing solutions rely on the knowledge of it. Identifying and estimating the transition matrix without ground truth labels is a critical and challenging task. When label noise transition depends on each instance, the problem of identifying the instance-dependent noise transition matrix becomes substantially more challenging. Despite recent proposed solution…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Coupled Flow Approach to Imitation Learning
Watch later
Multi-class Graph Clustering via Approximated Effective p-Resistance
Watch later
Shota Saito, …
A Reinforcement Learning Framework for Dynamic Mediation Analysis
Watch later
Lin Ge, …
Finding Generalization Measures by Contrasting Signal and Noise
Watch later
Jiaye Teng, …
Generating Private Synthetic Data with Genetic Algorithms
Watch later
Terrance Liu, …
