KnowMAN: Weakly Supervised Multinomial Adversarial Networks
This addresses the challenge of limited labeled data for training neural models, offering an incremental improvement in weakly supervised learning techniques.
The paper tackles the problem of over-reliance on noisy labeling functions in weakly supervised training, proposing KnowMAN to control their influence and improve generalization, resulting in strong performance gains over baseline methods.
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.