GAIS: A Novel Approach to Instance Selection with Graph Attention Networks
This is an incremental improvement for machine learning practitioners needing efficient data selection, as it enhances existing instance selection techniques with graph-based attention mechanisms.
The paper tackles the problem of reducing dataset size while preserving model performance by introducing GAIS, a graph attention network-based instance selection method, which achieves an average 96% reduction rate and maintains or improves accuracy across 13 datasets.
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.