Search Results for author:
Found 7 papers, 2 papers with code
Multi-Resolution Weak Supervision for Sequential Data
Multi-resolution sources exacerbate this challenge due to complex correlations and sample complexity that scales in the length of the sequence.
Scene Graph Prediction with Limited Labels
All scene graph models to date are limited to training on a small set of visual relationships that have thousands of training labels each.
Ranked #1 on
Scene Graph Detection
on VRD
Weak Supervision for Time Series: Wearable Sensor Classification with Limited Labeled Data
Using modern deep learning models to make predictions on time series data from wearable sensors generally requires large amounts of labeled data.
Learning Dependency Structures for Weak Supervision Models
Labeling training data is a key bottleneck in the modern machine learning pipeline.
Training Classifiers with Natural Language Explanations
Training accurate classifiers requires many labels, but each label provides only limited information (one bit for binary classification).
Inferring Generative Model Structure with Static Analysis
Obtaining enough labeled data to robustly train complex discriminative models is a major bottleneck in the machine learning pipeline.
Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in 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.
