mlsanityData to 7 Oct 2026

Deconvolutional Networks on Graph Data

arXiv 2110.15528 ↗First posted 29 Oct 2021cs.LGcited by 16

Not on the map. Why?

Abstract (arXiv)

In this paper, we consider an inverse problem in graph learning domain -- ``given the graph representations smoothed by Graph Convolutional Network (GCN), how can we reconstruct the input graph signal?" We propose Graph Deconvolutional Network (GDN) and motivate the design of GDN via a combination of inverse filters in spectral domain and de-noising layers in wavelet domain, as the inverse operation results in a high frequency amplifier and may amplify the noise. We demonstrate the effectiveness of the proposed method on several tasks including graph feature imputation and graph structure generation.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 29 of its 58 references that are in the map. First posted on arXiv 29 Oct 2021.

Builds on

29 of 58 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2019Graph Neural Networks for Social Recommendationcited by 711
  9. 2015Image-based Recommendations on Styles and Substitutescited by 702
  10. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 375
17 more
  1. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  2. 2018GAIN: Missing Data Imputation using Generative Adversarial Netscited by 349
  3. 2015A note on the evaluation of generative modelscited by 291
  4. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
  5. 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 182
  6. 2020Handling Missing Data with Graph Representation Learningcited by 132
  7. 2019Graph Wavelet Neural Networkcited by 131
  8. 2018Graphite: Iterative Generative Modeling of Graphscited by 112
  9. 2017Learning Structural Node Embeddings Via Diffusion Waveletscited by 97
  10. 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
  11. 2017Geometric Matrix Completion with Recurrent Multi-Graph Neural Networkscited by 88
  12. 2019GraphZoom: A multi-level spectral approach for accurate and scalable graph embeddingcited by 58
  13. 2019Predicting Path Failure In Time-Evolving Graphscited by 54
  14. 2020Graph Convolutional Networks for Graphs Containing Missing Featurescited by 46
  15. 2020Dirichlet Graph Variational Autoencodercited by 40
  16. 2020Deep Graph Generators: A Surveycited by 36
  17. 2018Enhancing Geometric Deep Learning via Graph Filter Deconvolutioncited by 4

Built on by

Cited by year

Citing papers per year: 2022: 6; 2023: 6; 2024: 3; 2025: 1.

16 papers.

Sort:

  1. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  2. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  3. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  4. 2023Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transportcited by 15
  5. 2022Wiener Graph Deconvolutional Network Improves Graph Self-Supervised Learningcited by 13
  6. 2022Handling Missing Data via Max-Entropy Regularized Graph Autoencodercited by 12
  7. 2023Deep Insights into Noisy Pseudo Labeling on Graph Datacited by 11
  8. 2022Learning Graph Structure from Convolutional Mixturescited by 5
  9. 2023A Contrastive Variational Graph Auto-Encoder for Node Clusteringcited by 4
  10. 2024Sampling-guided Heterogeneous Graph Neural Network with Temporal Smoothing for Scalable Longitudinal Data Imputationcited by 2
  11. 2023Data Imputation from the Perspective of Graph Dirichlet Energycited by 1
  12. 2025GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)cited by 1
4 more
  1. 2022Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Papercited by 0
  2. 2023Decision Support System for Chronic Diseases Based on Drug-Drug Interactionscited by 0
  3. 2023A Graph Encoder-Decoder Network for Unsupervised Anomaly Detectioncited by 0
  4. 2024Enhancing Missing Data Imputation through Combined Bipartite Graph and Complete Directed Graphcited by 0