EGG-GAE: scalable graph neural networks for tabular data imputation

Lev Telyatnikov, Simone Scardapane
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, PMLR 206:2661-2676, 2023.

Abstract

Missing data imputation (MDI) is crucial when dealing with tabular datasets across various domains. Autoencoders can be trained to reconstruct missing values, and graph autoencoders (GAE) can additionally consider similar patterns in the dataset when imputing new values for a given instance. However, previously proposed GAEs suffer from scalability issues, requiring the user to define a similarity metric among patterns to build the graph connectivity beforehand. In this paper, we leverage recent progress in latent graph learning to propose a novel EdGe Generation Graph AutoEncoder (EGG-GAE) for missing data imputation that overcomes these two drawbacks. EGG-GAE works on randomly sampled mini-batches of the input data (hence scaling to larger datasets), and it automatically infers the best connectivity across the mini-batch for each architecture layer. We also experiment with several extensions, including an ensemble strategy for inference and the inclusion of what we call prototype nodes, obtaining significant improvements, both in terms of imputation error and final downstream accuracy, across multiple benchmarks and baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v206-telyatnikov23a, title = {EGG-GAE: scalable graph neural networks for tabular data imputation}, author = {Telyatnikov, Lev and Scardapane, Simone}, booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics}, pages = {2661--2676}, year = {2023}, editor = {Ruiz, Francisco and Dy, Jennifer and van de Meent, Jan-Willem}, volume = {206}, series = {Proceedings of Machine Learning Research}, month = {25--27 Apr}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v206/telyatnikov23a/telyatnikov23a.pdf}, url = {https://proceedings.mlr.press/v206/telyatnikov23a.html}, abstract = {Missing data imputation (MDI) is crucial when dealing with tabular datasets across various domains. Autoencoders can be trained to reconstruct missing values, and graph autoencoders (GAE) can additionally consider similar patterns in the dataset when imputing new values for a given instance. However, previously proposed GAEs suffer from scalability issues, requiring the user to define a similarity metric among patterns to build the graph connectivity beforehand. In this paper, we leverage recent progress in latent graph learning to propose a novel EdGe Generation Graph AutoEncoder (EGG-GAE) for missing data imputation that overcomes these two drawbacks. EGG-GAE works on randomly sampled mini-batches of the input data (hence scaling to larger datasets), and it automatically infers the best connectivity across the mini-batch for each architecture layer. We also experiment with several extensions, including an ensemble strategy for inference and the inclusion of what we call prototype nodes, obtaining significant improvements, both in terms of imputation error and final downstream accuracy, across multiple benchmarks and baselines.} }
Endnote
%0 Conference Paper %T EGG-GAE: scalable graph neural networks for tabular data imputation %A Lev Telyatnikov %A Simone Scardapane %B Proceedings of The 26th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2023 %E Francisco Ruiz %E Jennifer Dy %E Jan-Willem van de Meent %F pmlr-v206-telyatnikov23a %I PMLR %P 2661--2676 %U https://proceedings.mlr.press/v206/telyatnikov23a.html %V 206 %X Missing data imputation (MDI) is crucial when dealing with tabular datasets across various domains. Autoencoders can be trained to reconstruct missing values, and graph autoencoders (GAE) can additionally consider similar patterns in the dataset when imputing new values for a given instance. However, previously proposed GAEs suffer from scalability issues, requiring the user to define a similarity metric among patterns to build the graph connectivity beforehand. In this paper, we leverage recent progress in latent graph learning to propose a novel EdGe Generation Graph AutoEncoder (EGG-GAE) for missing data imputation that overcomes these two drawbacks. EGG-GAE works on randomly sampled mini-batches of the input data (hence scaling to larger datasets), and it automatically infers the best connectivity across the mini-batch for each architecture layer. We also experiment with several extensions, including an ensemble strategy for inference and the inclusion of what we call prototype nodes, obtaining significant improvements, both in terms of imputation error and final downstream accuracy, across multiple benchmarks and baselines.
APA
Telyatnikov, L. & Scardapane, S.. (2023). EGG-GAE: scalable graph neural networks for tabular data imputation. Proceedings of The 26th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 206:2661-2676 Available from https://proceedings.mlr.press/v206/telyatnikov23a.html.

Related Material