KnowMAN: Weakly Supervised Multinomial Adversarial Networks

TL;DR

KnowMAN is a novel adversarial framework that enhances weakly supervised neural models by learning label-invariant representations, thereby improving generalization beyond noisy heuristic labels.

Contribution

It introduces an adversarial scheme to control the influence of labeling function signals, promoting more robust and generalizable representations in weakly supervised learning.

Findings

Significant performance improvements over baseline methods.

Effective in learning invariant representations.

Enhances generalization in weakly supervised models.

Abstract

The absence of labeled data for training neural models is often addressed by leveraging knowledge about the specific task, resulting in heuristic but noisy labels. The knowledge is captured in labeling functions, which detect certain regularities or patterns in the training samples and annotate corresponding labels for training. This process of weakly supervised training may result in an over-reliance on the signals captured by the labeling functions and hinder models to exploit other signals or to generalize well. We propose KnowMAN, an adversarial scheme that enables to control influence of signals associated with specific labeling functions. KnowMAN forces the network to learn representations that are invariant to those signals and to pick up other signals that are more generally associated with an output label. KnowMAN strongly improves results compared to direct weakly supervised learning with a pre-trained transformer language model and a feature-based baseline.