# GAIS: A Novel Approach to Instance Selection with Graph Attention Networks

arXiv: https://arxiv.org/abs/2412.19201 · HTML: https://mlsanity.com/paper/2412.19201/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 19 references that are in the map.
- First posted on arXiv 26 Dec 2024.

## Builds on (most cited first, 2 of 2)

- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [Instance Selection for GANs](https://mlsanity.com/paper/2007.15255/) (2020)

## Built on by (most cited first, 1 of 1)

- [Scalable Graph Attention-based Instance Selection via Mini-Batch Sampling and Hierarchical Hashing](https://mlsanity.com/paper/2502.20293/) (2025)

## Abstract (arXiv)

Instance selection (IS) is a crucial technique in machine learning that aims to reduce dataset size while maintaining model performance. This paper introduces a novel method called Graph Attention-based Instance Selection (GAIS), which leverages Graph Attention Networks (GATs) to identify the most informative instances in a dataset. GAIS represents the data as a graph and uses GATs to learn node representations, enabling it to capture complex relationships between instances. The method processes data in chunks, applies random masking and similarity thresholding during graph construction, and selects instances based on confidence scores from the trained GAT model. Experiments on 13 diverse datasets demonstrate that GAIS consistently outperforms traditional IS methods in terms of effectiveness, achieving high reduction rates (average 96%) while maintaining or improving model performance. Although GAIS exhibits slightly higher computational costs, its superior performance in maintaining accuracy with significantly reduced training data makes it a promising approach for graph-based data selection.