2018/07/03 by William La Cava, Tilak Raj Singh, La Cava, William +7 · 2 citations
Computer Science · #Evolutionary Algorithms and Applications #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
paper · pdf · doi:10.48550/arxiv.1807.00981
openalex publication_date 2018/07/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition to other elementary functions. Differentiable features are trained via gradient descent, and the performance of features in a linear model is used to weight the rate of change among subcomponents of each representation. The search process maintains an archive of representations with accuracy-complexity trade-offs to assist in generalization and interpretation. We compare several stochastic optimization approaches within this framework. We benchmark these variants on 100 open-source regression problems in comparison to state-of-the-art machine learning approaches. Our main finding is that this approach produces the highest average test scores across problems while producing representations that are orders of magnitude smaller than the next best performing method (gradient boosting). We also report a negative result in which attempts to directly optimize the disentanglement of the representation result in more highly correlated features.