Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functions
원문 초록
One approach for interpreting black-box machine learning models is to find a global approximation of the model using simple interpretable functions, which is called a metamodel (a model of the model). Approximating the black-box with a metamodel can be used to 1) estimate instance-wise feature importance; 2) understand the functional form of the model; 3) analyze feature interactions. In this work, we propose a new method for finding interpretable metamodels. Our approach utilizes Kolmogorov superposition theorem, which expresses multivariate functions as a composition of univariate functions (our primitive parameterized functions). This composition can be represented in the form of a tree. Inspired by symbolic regression, we use a modified form of genetic programming to search over different tree configurations. Gradient descent (GD) is used to optimize the parameters of a given configuration. Our method is a novel memetic algorithm that uses GD not only for training numerical constants but also for the training of building blocks. Using several experiments, we show that our method outperforms recent metamodeling approaches suggested for interpreting black-boxes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Evolving Form and Function: Dual-Objective Optimization in Neural Symbolic Regression Networks
Neural Network-Guided Symbolic Regression for Interpretable Descriptor Discovery in Perovskite Catalysts
Discovering the underlying analytic structure within Standard Model constants using artificial intelligence
Structured Kolmogorov-Arnold Neural ODEs for Interpretable Learning and Symbolic Discovery of Nonlinear Dynamics
Enhancing interpretability of rule-based classifiers through feature graphs
syren-baryon: Analytic emulators for the impact of baryons on the matter power spectrum
토론
이 논문과 연결된 포럼 글이 아직 없습니다.