# Feature Selection and Extraction for Graph Neural Networks

arXiv: https://arxiv.org/abs/1910.10682 · HTML: https://mlsanity.com/paper/1910.10682/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 6 of 6)

- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Data-centric Graph Learning: A Survey](https://mlsanity.com/paper/2310.04987/) (2023)
- [Weighted Graph Nodes Clustering via Gumbel Softmax](https://mlsanity.com/paper/2102.10775/) (2021)
- [Hyperedge Modeling in Hypergraph Neural Networks by using Densest Overlapping Subgraphs](https://mlsanity.com/paper/2409.10340/) (2024)
- [A Decision-Based Heterogenous Graph Attention Network for Multi-Class Fake News Detection](https://mlsanity.com/paper/2501.03290/) (2025)
- [Adaptive Node Feature Selection For Graph Neural Networks](https://mlsanity.com/paper/2510.03096/) (2025)

## Abstract (arXiv)

Graph Neural Networks (GNNs) have been a latest hot research topic in data science, due to the fact that they use the ubiquitous data structure graphs as the underlying elements for constructing and training neural networks. In a GNN, each node has numerous features associated with it. The entire task (for example, classification, or clustering) utilizes the features of the nodes to make decisions, at node level or graph level. In this paper, (1) we extend the feature selection algorithm presented in via Gumbel Softmax to GNNs. We conduct a series of experiments on our feature selection algorithms, using various benchmark datasets: Cora, Citeseer and Pubmed. (2) We implement a mechanism to rank the extracted features. We demonstrate the effectiveness of our algorithms, for both feature selection and ranking. For the Cora dataset, (1) we use the algorithm to select 225 features out of 1433 features. Our experimental results demonstrate their effectiveness for the same classification problem. (2) We extract features such that they are linear combinations of the original features, where the coefficients for each extracted features are non-negative and sum up to one. We propose an algorithm to rank the extracted features in the sense that when using them for the same classification problem, the accuracy goes down gradually for the extracted features within the rank 1 - 50, 51 - 100, 100 - 150, and 151 - 200.