Learning from Label Proportions with Consistency Regularization

10/29/2019
by   Kuen-Han Tsai, et al.
11

The problem of learning from label proportions (LLP) involves training classifiers with weak labels on bags of instances, rather than strong labels on individual instances. The weak labels only contain the label proportion of each bag. The LLP problem is important for many practical applications that only allow label proportions to be collected because of data privacy or annotation cost, and has recently received lots of research attention. Most existing works focus on extending supervised learning models to solve the LLP problem, but the weak learning nature makes it hard to further improve LLP performance with a supervised angle. In this paper, we take a different angle from semi-supervised learning. In particular, we propose a novel model inspired by consistency regularization, a popular concept in semi-supervised learning that encourages the model to produce a decision boundary that better describes the data manifold. With the introduction of consistency regularization, we further extend our study to non-uniform bag-generation and validation-based parameter-selection procedures that better match practical needs. Experiments not only justify that LLP with consistency regularization achieves superior performance, but also demonstrate the practical usability of the proposed procedures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/09/2021

RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss

Semi-supervised learning (SSL) has played an important role in leveragin...
research
11/23/2021

CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning

Labels are costly and sometimes unreliable. Noisy label learning, semi-s...
research
05/08/2023

Q A Label Learning

Assigning labels to instances is crucial for supervised machine learning...
research
10/13/2021

Life is not black and white – Combining Semi-Supervised Learning with fuzzy labels

The required amount of labeled data is one of the biggest issues in deep...
research
10/16/2022

PCR: Pessimistic Consistency Regularization for Semi-Supervised Segmentation

Currently, state-of-the-art semi-supervised learning (SSL) segmentation ...
research
04/19/2021

Epsilon Consistent Mixup: An Adaptive Consistency-Interpolation Tradeoff

In this paper we propose ϵ-Consistent Mixup (ϵmu). ϵmu is a data-based s...
research
07/19/2023

STRAPPER: Preference-based Reinforcement Learning via Self-training Augmentation and Peer Regularization

Preference-based reinforcement learning (PbRL) promises to learn a compl...

Please sign up or login with your details

Forgot password? Click here to reset