Fidelity-Weighted Learning

Abstract

Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing. This creates a fundamental quality versus-quantity trade-off in the learning process. Do we learn from the small amount of high-quality data or the potentially large amount of weakly-labeled data? We argue that if the learner could somehow know and take the label-quality into account when learning the data representation, we could get the best of both worlds. To this end, we propose "fidelity-weighted learning" (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data. FWL modulates the parameter updates to a student network (trained on the task we care about) on a per-sample basis according to the posterior confidence of its label-quality estimated by a teacher (who has access to the high-quality labels). Both student and teacher are learned from the data. We evaluate FWL on two tasks in information retrieval and natural language processing where we outperform state-of-the-art alternative semi-supervised methods, indicating that our approach makes better use of strong and weak labels, and leads to better task-dependent data representations.

Published as a conference paper at ICLR 2018

References in corpus (12)

• Distilling the Knowledge in a Neural Network
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Data Programming: Creating Large Training Sets, Quickly
• Scalable Variational Gaussian Process Classification
• Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)
• Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
• TF.Learn: TensorFlow's High-level Module for Distributed Machine Learning
• Learning to Learn from Weak Supervision by Full Supervision
• Incidental Supervision: Moving beyond Supervised Learning
• Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision
• Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data
• Estimation from Indirect Supervision with Linear Moments

Cited by in corpus (3)

• Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction
• Meta Corrupted Pixels Mining for Medical Image Segmentation