paper-with-me

Papers

Handling Missing Data via Max-Entropy Regularized Graph Autoencoder

2022-11-30 · Ziqi Gao, Yifan Niu, Jiashun Cheng, Jianheng Tang, Tingyang Xu, Peilin Zhao, Lanqing Li, Fugee Tsung, Jia Li

Graph neural networks (GNNs) are popular weapons for modeling relational data. Existing GNNs are not specified for attribute-incomplete graphs, making missing attribute imputation a burning issue. Until recently, many works notice that GNNs are coupled with spectral concentration, which means the spectrum obtained by GNNs concentrates on a local part in spectral domain, e.g., low-frequency due to oversmoothing issue. As a consequence, GNNs may be seriously flawed for reconstructing graph attributes as graph spectral concentration tends to cause a low imputation precision. In this work, we present a regularized graph autoencoder for graph attribute imputation, named MEGAE, which aims at mitigating spectral concentration problem by maximizing the graph spectral entropy. Notably, we first present the method for estimating graph spectral entropy without the eigen-decomposition of Laplacian matrix and provide the theoretical upper error bound. A maximum entropy regularization then acts in the latent space, which directly increases the graph spectral entropy. Extensive experiments show that MEGAE outperforms all the other state-of-the-art imputation methods on a variety of benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2211.16771

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeImputation

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음

Similar Papers 제목 키워드 기반

Statistical inference using Regularized M-estimation in the reproducing kernel Hilbert space for handling missing data

2021-07-15 · Hengfang Wang, Jae Kwang Kim

Imputation and propensity score weighting are two popular techniques for handling missing data. We address these problems using the regularized M-estimation techniques in the reproducing kernel Hilbert space. Specificall…

Imputationregression

High-dimensional Time Series Prediction with Missing Values

2015-09-28 · Hsiang-Fu Yu, Nikhil Rao, Inderjit S. Dhillon

High-dimensional time series prediction is needed in applications as diverse as demand forecasting and climatology. Often, such applications require methods that are both highly scalable, and deal with noisy data in term…

Demand ForecastingMatrix CompletionMissing ValuesPrediction+4

Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains

2026-07-06 · Iman Islam, Esther Puyol-Antón, Bram Ruijsink, Andrew J. Reader 외 arxiv

Echocardiography is the first imaging modality used for assessing cardiac function, and accurate segmentation of cardiac structures is essential for deriving biomarkers. However, the development of effective automated se…

Temporal Regularized Matrix Factorization for High-dimensional Time Series Prediction

2016-12-01 · NeurIPS 2016 12 · Hsiang-Fu Yu, Nikhil Rao, Inderjit S. Dhillon

Time series prediction problems are becoming increasingly high-dimensional in modern applications, such as climatology and demand forecasting. For example, in the latter problem, the number of items for which demand need…

Demand ForecastingMissing ValuesTime SeriesTime Series Analysis+2

Regularized HessELM and Inclined Entropy Measurement for Congestive Heart Failure Prediction

2019-07-12 · Apdullah Yayık, Yakup Kutlu, Gökhan Altan

Our study concerns with automated predicting of congestive heart failure (CHF) through the analysis of electrocardiography (ECG) signals. A novel machine learning approach, regularized hessenberg decomposition based extr…

BIG-bench Machine LearningElectrocardiography (ECG)