Gradient Importance Learning for Incomplete Observations

Abstract

Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification. This is particularly true if the data have large missingness rates or a small sample size. More importantly, the imputation error could be propagated into the prediction step that follows, which may constrain the capabilities of the prediction model. In this work, we introduce the gradient importance learning (GIL) method to train multilayer perceptrons (MLPs) and long short-term memories (LSTMs) to directly perform inference from inputs containing missing values without imputation. Specifically, we employ reinforcement learning (RL) to adjust the gradients used to train these models via back-propagation. This allows the model to exploit the underlying information behind missingness patterns. We test the approach on real-world time-series (i.e., MIMIC-III), tabular data obtained from an eye clinic, and a standard dataset (i.e., MNIST), where our imputation-free predictions outperform the traditional two-step imputation-based predictions using state-of-the-art imputation methods.

References in corpus (16)

• Auto-Encoding Variational Bayes
• Continuous control with deep reinforcement learning
• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• MissForest - nonparametric missing value imputation for mixed-type data
• Recurrent Models of Visual Attention
• Multiple Object Recognition with Visual Attention
• GAIN: Missing Data Imputation using Generative Adversarial Nets
• BRITS: Bidirectional Recurrent Imputation for Time Series
• Learning to Optimize
• Recommendations as Treatments: Debiasing Learning and Evaluation
• Deep Compressed Sensing
• EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
• NeuMiss networks: differentiable programming for supervised learning with missing values
• Scalable Gaussian Processes on Discrete Domains
• Temporal Pattern Discovery for Accurate Sepsis Diagnosis in ICU Patients
• Blood lactate concentration prediction in critical care patients: handling missing values