Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

Abstract

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to label training data. Prior work has explored learning accuracies for these sources even without ground truth labels, but they assume that a single accuracy parameter is sufficient to model the behavior of these sources over the entire training set. In particular, they fail to model latent subsets in the training data in which the supervision sources perform differently than on average. We present Socratic learning, a paradigm that uses feedback from a corresponding discriminative model to automatically identify these subsets and augments the structure of the generative model accordingly. Experimentally, we show that without any ground truth labels, the augmented generative model reduces error by up to 56.06% for a relation extraction task compared to a state-of-the-art weak supervision technique that utilizes generative models.

arXiv comment4 figures; 18 pages

Cited by in corpus (10)

• Avoiding Your Teacher's Mistakes: Training Neural Networks with Controlled Weak Supervision
• Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
• Infrastructure for Usable Machine Learning: The Stanford DAWN Project
• Learning Dependency Structures for Weak Supervision Models
• Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling
• Fidelity-Weighted Learning
• DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction
• Pairwise Feedback for Data Programming
• Defuse: Harnessing Unrestricted Adversarial Examples for Debugging Models Beyond Test Accuracy
• Robust Collaborative Learning with Noisy Labels