Gradient Importance Learning for Incomplete Observations-猫眼课题宝

DOI：

发表时间：

2021-07

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Qitong Gao;Dong Wang;Joshua D. Amason;Siyang Yuan;Chenyang Tao;Ricardo Henao;M. Hadziahmetovic;L. Carin;Miroslav Pajic

尽管最近的工作已经开发出可以生成数据集中缺失条目的估计(或推算)以便于下游分析的方法，但大多数方法依赖于可能与现实世界应用不一致的假设，并且在后续任务(如分类)中可能会受到较差的性能影响。如果数据有很大的缺失率或样本量很小，这一点尤其正确。更重要的是，补偿误差可能会传播到随后的预测步骤中，这可能会限制预测模型的能力。在这项工作中，我们引入了梯度重要性学习(GIL)方法来训练多层感知器(MLP)和长短期记忆(LSTM)，以便直接从包含缺失值的输入进行推理，而不需要补充。具体地说，我们使用强化学习(RL)来调整用于通过反向传播训练这些模型的梯度。这使得该模型能够利用缺失模式背后的潜在信息。我们在真实世界的时间序列(即MIMIC-III)、从眼科诊所获得的表格数据和标准数据集(即MNIST)上测试了该方法，在这些数据集上，我们的非归并预测优于使用最先进的归算方法的传统的基于两步归算的预测。

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.

Gradient Importance Learning for Incomplete Observations

文献摘要

被引文献

相似文献