arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.10012quant-phcond-mat.dis-nn
收藏

表征神经网络的分布外泛化:在无序 Su-Schrieffer-Heeger 模型中的应用

Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model

Kacper Cybiński, Marcin Płodzień, Michał Tomza, Maciej Lewenstein, Alexandre Dauphin, Anna Dawid

AI总结:

研究通过类激活映射(CAM)和主成分分析(PCA)提升神经网络分类量子相态的可解释性与分布外泛化能力,以无序SSH模型为例,证明系统运用可解释性方法能改善神经网络在科学问题中的性能。

摘要:

机器学习(ML)是检测物质相态的有前景的工具。然而,ML 模型也因其黑盒结构而闻名,这阻碍了理解它们从数据中学习到了什么,并使其应用于新数据时存在风险。此外,ML 的核心挑战是确保其良好的泛化能力,即在训练集之外的数据上表现良好。在这里,我们展示了如何通过知性地使用一种称为类激活映射(CAM)的可解释性方法,并结合主成分分析(PCA)对数据潜在表示的分析,来增加对训练用于分类量子相的神经网络(NN)预测结果的信任。特别是,我们展示了通过选择在问题的简化版本中学习已知相态特征的 NN,可以确保在这个复杂分类问题中实现更好的分布外泛化。我们在带有和不带无序的拓扑 Su-Schrieffer-Heeger(SSH)模型的示例上展示了这一点,该模型对于以监督方式训练的 NN 来说是一个令人惊讶的挑战。这项工作是系统使用可解释性方法如何改善 NN 在科学问题中性能的一个示例。

英文摘要:

Machine learning (ML) is a promising tool for the detection of phases of matter. However, ML models are also known for their black-box construction, which hinders understanding of what they learn from the data and makes their application to novel data risky. Moreover, the central challenge of ML is to ensure its good generalization abilities, i.e., good performance on data outside the training set. Here, we show how the informed use of an interpretability method called class activation mapping (CAM), and the analysis of the latent representation of the data with the principal component analysis (PCA) can increase trust in predictions of a neural network (NN) trained to classify quantum phases. In particular, we show that we can ensure better out-of-distribution generalization in the complex classification problem by choosing such an NN that, in the simplified version of the problem, learns a known characteristic of the phase. We show this on an example of the topological Su-Schrieffer-Heeger (SSH) model with and without disorder, which turned out to be surprisingly challenging for NNs trained in a supervised way. This work is an example of how the systematic use of interpretability methods can improve the performance of NNs in scientific problems.

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。

↑