提出一种高效精准的傅里叶特征归因方法，提升模型可解释性。
Fast Fourier Correlation is a Highly Efficient and Accurate Feature Attribution Algorithm from the Perspective of Control Theory and Game Theory
- 基于信号分解理论构建傅里叶特征归因新方法。
- ViT在ImageNet上仅用8%傅里叶特征即可保持80%样本原预测。
- 傅里叶特征更具类内集中、类间区分特性，适合可解释AI。
从傅里叶特征视角研究神经网络已受广泛关注。尽管已有研究指出神经网络倾向于学习低频特征，但缺乏明确的傅里叶特征归因方法。为此，我们提出一种基于信号分解理论的新型傅里叶特征归因方法，并分析了博弈论归因指标在傅里叶域与空间域的差异，证明其更适用于傅里叶特征归因。实验表明，傅里叶特征归因在特征选择能力上优于空间域方法：例如，在ImageNet上的Vision Transformers（ViTs）仅需8%的傅里叶特征即可维持80%样本的原始预测。此外，对比传统空间域方法，本方法识别的特征具有更强的类内集中性和类间区分性，表明其在高效分类与可解释人工智能算法中具备潜力。
原文摘要 · Abstract (English)
The study of neural networks from the perspective of Fourier features has garnered significant attention. While existing analytical research suggests that neural networks tend to learn low-frequency features, a clear attribution method for identifying the specific learned Fourier features has remained elusive. To bridge this gap, we propose a novel Fourier feature attribution method grounded in signal decomposition theory. Additionally, we analyze the differences between game-theoretic attribution metrics for Fourier and spatial domain features, demonstrating that game-theoretic evaluation metrics are better suited for Fourier-based feature attribution. Our experiments show that Fourier feature attribution exhibits superior feature selection capabilities compared to spatial domain attribution methods. For instance, in the case of Vision Transformers (ViTs) on the ImageNet dataset, only $8\%$ of the Fourier features are required to maintain the original predictions for $80\%$ of the samples. Furthermore, we compare the specificity of features identified by our method against traditional spatial domain attribution methods. Results reveal that Fourier features exhibit greater intra-class concentration and inter-class distinctiveness, indicating their potential for more efficient classification and explainable AI algorithms.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。