Bandit Label Inference for Weakly Supervised Learning

TL;DR

This paper introduces a versatile method that transforms any strong classifier into a weakly supervised one, adaptable to various regimes and data types, simplifying the application of weak supervision across different tasks.

Contribution

The authors propose a general-purpose approach that converts any off-the-shelf classifier into a weakly supervised model, flexible across different weak supervision regimes and data forms.

Findings

Achieves competitive results across multiple weak supervision regimes.

Simplifies the adaptation process for weakly supervised learning.

Demonstrates broad applicability of the proposed method.

Abstract

The scarcity of data annotated at the desired level of granularity is a recurring issue in many applications. Significant amounts of effort have been devoted to developing weakly supervised methods tailored to each individual setting, which are often carefully designed to take advantage of the particular properties of weak supervision regimes, form of available data and prior knowledge of the task at hand. Unfortunately, it is difficult to adapt these methods to new tasks and/or forms of data, which often require different weak supervision regimes or models. We present a general-purpose method that can solve any weakly supervised learning problem irrespective of the weak supervision regime or the model. The proposed method turns any off-the-shelf strongly supervised classifier into a weakly supervised classifier and allows the user to specify any arbitrary weakly supervision regime via a loss function. We apply the method to several different weak supervision regimes and demonstrate competitive results compared to methods specifically engineered for those settings.