Bandit Label Inference for Weakly Supervised Learning

09/22/2015
by   Ke Li, et al.
0

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.

READ FULL TEXT
research
10/07/2022

Label Propagation with Weak Supervision

Semi-supervised learning and weakly supervised learning are important pa...
research
03/19/2019

Cross-task weakly supervised learning from instructional videos

In this paper we investigate learning visual models for the steps of ord...
research
07/06/2019

Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss

In many machine learning scenarios, supervision by gold labels is not av...
research
06/02/2021

Weakly Supervised Learning Creates a Fusion of Modeling Cultures

The past two decades have witnessed the great success of the algorithmic...
research
12/19/2020

Learning by Fixing: Solving Math Word Problems with Weak Supervision

Previous neural solvers of math word problems (MWPs) are learned with fu...
research
11/29/2019

Merging Weak and Active Supervision for Semantic Parsing

A semantic parser maps natural language commands (NLs) from the users to...
research
06/03/2019

Weakly Supervised Disentanglement by Pairwise Similarities

Recently, researches related to unsupervised disentanglement learning wi...

Please sign up or login with your details

Forgot password? Click here to reset