Strength from Weakness: Fast Learning Using Weak Supervision

02/19/2020
by   Joshua Robinson, et al.
8

We study generalization properties of weakly supervised learning. That is, learning where only a few "strong" labels (the actual target of our prediction) are present but many more "weak" labels are available. In particular, we show that having access to weak labels can significantly accelerate the learning rate for the strong task to the fast rate of O(1/n), where n denotes the number of strongly labeled data points. This acceleration can happen even if by itself the strongly labeled data admits only the slower O(1/√(n)) rate. The actual acceleration depends continuously on the number of weak labels available, and on the relation between the two tasks. Our theoretical results are reflected empirically across a range of tasks and illustrate how weak labels speed up learning on the strong task.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/05/2020

Limitations of weak labels for embedding and tagging

While many datasets and approaches in ambient sound analysis use weakly ...
research
12/02/2014

Detector Discovery in the Wild: Joint Multiple Instance and Representation Learning

We develop methods for detector learning which exploit joint training ov...
research
06/16/2021

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

Weak supervision has shown promising results in many natural language pr...
research
05/14/2021

The Benefit Of Temporally-Strong Labels In Audio Event Classification

To reveal the importance of temporal precision in ground truth audio eve...
research
11/29/2022

Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT

Modern machine learning pipelines, in particular those based on deep lea...
research
11/16/2018

Coupling weak and strong supervision for classification of prostate cancer histopathology images

Automated grading of prostate cancer histopathology images is a challeng...
research
05/12/2020

Learning to Estimate Driver Drowsiness from Car Acceleration Sensors using Weakly Labeled Data

This paper addresses the learning task of estimating driver drowsiness f...

Please sign up or login with your details

Forgot password? Click here to reset