mlsanityData to 14 Oct 2026

Handling Missing Data via Max-Entropy Regularized Graph Autoencoder

arXiv 2211.16771 ↗First posted 30 Nov 2022cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 31 of its 68 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

31 of 68 references.

References · 31

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2019Simplifying Graph Convolutional Networkscited by 1,477
  3. 2016Variational Graph Auto-Encoderscited by 1,382
  4. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  5. 2015Image-based Recommendations on Styles and Substitutescited by 706
  6. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  7. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  8. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
  9. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  10. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 352
  11. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
  12. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
19 more
  1. 2020Handling Missing Data with Graph Representation Learningcited by 133
  2. 2019Graph Wavelet Neural Networkcited by 131
  3. 2014Matrix Completion and Low-Rank SVD via Fast Alternating Least Squarescited by 104
  4. 2020Missing Data Imputation using Optimal Transportcited by 100
  5. 2017Learning Structural Node Embeddings Via Diffusion Waveletscited by 97
  6. 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
  7. 2017Geometric Matrix Completion with Recurrent Multi-Graph Neural Networkscited by 88
  8. 2019Inductive Matrix Completion Based on Graph Neural Networkscited by 86
  9. 2020Graph Convolutional Networks using Heat Kernel for Semi-supervised Learningcited by 51
  10. 2021MIRACLE: Causally-Aware Imputation via Learning Missing Data Mechanismscited by 51
  11. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 47
  12. 2016Faster Kernels for Graphs with Continuous Attributes via Hashingcited by 31
  13. 2020Incomplete Graph Representation and Learning via Partial Graph Neural Networkscited by 16
  14. 2021Deconvolutional Networks on Graph Datacited by 16
  15. 2013Spectrum-Adapted Tight Graph Wavelet and Vertex-Frequency Framescited by 15
  16. 2014Multiple Imputation of Missing Categorical and Continuous Values via Bayesian Mixture Models with Local Dependencecited by 10
  17. 2020Graph Autoencoders with Deconvolutional Networkscited by 9
  18. 2021Siamese Attribute-missing Graph Auto-encodercited by 6
  19. 2019Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencodercited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 2; 2026: 1.

12 papers.

  1. 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transformcited by 71
  2. 2023Transformed Distribution Matching for Missing Value Imputationcited by 31
  3. 2023Alleviating Over-smoothing for Unsupervised Sentence Representationcited by 16
  4. 2024Optimal Transport for Structure Learning Under Missing Datacited by 6
  5. 2024stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data Imputationcited by 6
  6. 2024Deep Reinforcement Learning for Modelling Protein Complexescited by 5
  7. 2024A Context-Aware Approach for Enhancing Data Imputation with Pre-trained Language Modelscited by 5
  8. 2025Incomplete Graph Learning: A Comprehensive Surveycited by 3
  9. 2023Data Imputation from the Perspective of Graph Dirichlet Energycited by 1
  10. 2024DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphscited by 0
  11. 2025Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detectioncited by 0
  12. 2026Learning the Interaction Prior for Protein-Protein Interaction Prediction: A Model-Agnostic Approachcited by 0