arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.19201cs.LG
收藏

GAIS:一种基于图注意力网络的实例选择新方法

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

College of Information Technology, United Arab Emirates University(阿联酋大学信息技术学院);KU Leuven(鲁汶大学);College of Science, United Arab Emirates University(阿联酋大学理学院)

Zahiriddin Rustamov, Ayham Zaitouny, Rafat Damseh, Nazar Zaki

AI总结:

本文提出 GAIS 方法,利用图注意力网络建模实例间复杂关系,通过分块处理、随机掩码和置信度选择实例,在 13 个数据集上平均缩减 96% 数据的同时保持或提升模型性能。

摘要:

实例选择(IS)是机器学习中的一项关键技术,旨在减小数据集规模,同时保持模型性能。本文提出了一种名为基于图注意力的实例选择(GAIS)的新方法,该方法利用图注意力网络(GATs)识别数据集中最具信息量的实例。GAIS 将数据表示为图,并使用 GATs 学习节点表示,使其能够捕捉实例之间的复杂关系。该方法分块处理数据,在图构建过程中应用随机掩码和相似度阈值,并根据训练后的 GAT 模型给出的置信度分数选择实例。在 13 个不同数据集上的实验表明,GAIS 在有效性方面始终优于传统 IS 方法,实现了高缩减率(平均 96%),同时保持或提高了模型性能。尽管 GAIS 的计算成本略高,但其在显著减少训练数据的同时保持准确率方面的优越性能,使其成为一种有前景的基于图的数据选择方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑