Saved in:
Bibliographic Details
Main Authors: Kutt, Brody, Ramteke, Pralay, Mignot, Xavier, Toman, Pamela, Ramanan, Nandini, Chhetri, Sujit Rokka, Huang, Shan, Du, Min, Hewlett, William
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.09929
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911822047608832
author Kutt, Brody
Ramteke, Pralay
Mignot, Xavier
Toman, Pamela
Ramanan, Nandini
Chhetri, Sujit Rokka
Huang, Shan
Du, Min
Hewlett, William
author_facet Kutt, Brody
Ramteke, Pralay
Mignot, Xavier
Toman, Pamela
Ramanan, Nandini
Chhetri, Sujit Rokka
Huang, Shan
Du, Min
Hewlett, William
contents Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesome. Often, little is known about when and why an algorithm fails to outperform a supervised baseline. Using benchmark datasets, we craft five common real-world SSL data scenarios: few-label, open-set, noisy-label, and class distribution imbalance/misalignment in the labeled and unlabeled sets. We propose a novel algorithm called Contrastive Credibility Propagation (CCP) for deep SSL via iterative transductive pseudo-label refinement. CCP unifies semi-supervised learning and noisy label learning for the goal of reliably outperforming a supervised baseline in any data scenario. Compared to prior methods which focus on a subset of scenarios, CCP uniquely outperforms the supervised baseline in all scenarios, supporting practitioners when the qualities of labeled or unlabeled data are unknown.
format Preprint
id arxiv_https___arxiv_org_abs_2211_09929
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Contrastive Credibility Propagation for Reliable Semi-Supervised Learning
Kutt, Brody
Ramteke, Pralay
Mignot, Xavier
Toman, Pamela
Ramanan, Nandini
Chhetri, Sujit Rokka
Huang, Shan
Du, Min
Hewlett, William
Machine Learning
Producing labels for unlabeled data is error-prone, making semi-supervised learning (SSL) troublesome. Often, little is known about when and why an algorithm fails to outperform a supervised baseline. Using benchmark datasets, we craft five common real-world SSL data scenarios: few-label, open-set, noisy-label, and class distribution imbalance/misalignment in the labeled and unlabeled sets. We propose a novel algorithm called Contrastive Credibility Propagation (CCP) for deep SSL via iterative transductive pseudo-label refinement. CCP unifies semi-supervised learning and noisy label learning for the goal of reliably outperforming a supervised baseline in any data scenario. Compared to prior methods which focus on a subset of scenarios, CCP uniquely outperforms the supervised baseline in all scenarios, supporting practitioners when the qualities of labeled or unlabeled data are unknown.
title Contrastive Credibility Propagation for Reliable Semi-Supervised Learning
topic Machine Learning
url https://arxiv.org/abs/2211.09929