Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)

TL;DR

This workshop focuses on advancing weakly supervised learning techniques that enable deep neural networks to learn effectively from expert-provided prior knowledge and unlabeled data.

Contribution

It introduces new methods and tools for integrating expert knowledge into machine learning models to improve data annotation and model generalization.

Findings

Development of novel weak supervision algorithms

Improved model performance with limited labeled data

Enhanced understanding of weakly supervised learning principles

Abstract

Welcome to WeaSuL 2021, the First Workshop on Weakly Supervised Learning, co-located with ICLR 2021. In this workshop, we want to advance theory, methods and tools for allowing experts to express prior coded knowledge for automatic data annotations that can be used to train arbitrary deep neural networks for prediction. The ICLR 2021 Workshop on Weak Supervision aims at advancing methods that help modern machine-learning methods to generalize from knowledge provided by experts, in interaction with observable (unlabeled) data. In total, 15 papers were accepted. All the accepted contributions are listed in these Proceedings.