Learning to Learn from Weak Supervision by Full Supervision
This addresses the challenge of leveraging noisy data for machine learning, but it is incremental as it builds on existing weak supervision methods.
The paper tackles the problem of training neural networks with a large set of weakly labeled data and a small amount of true labels by using a confidence network to control gradient updates, avoiding harm from noisy labels.
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to perform a given task and is trained using a large set of unlabeled data that are weakly annotated. We propose to control the magnitude of the gradient updates to the target network using the scores provided by the second confidence network, which is trained on a small amount of supervised data. Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model.