<ul data-eligibleForWebStory="false"><li>A new paper introduces a unified framework for N-tuples weak supervision in supervised learning to reduce annotation burden.</li><li>The framework is based on empirical risk minimization and incorporates pointwise unlabeled data to improve learning performance.</li><li>The paper unifies data generation processes for N-tuples and pointwise unlabeled data and provides a generalization error bound for theoretical support.</li><li>Extensive experiments on benchmark datasets confirm the effectiveness of the framework in improving generalization across different N-tuples learning tasks.</li></ul>

A Unified Empirical Risk Minimization Framework for Flexible N-Tuples Weak Supervision

Discover more