Compact Broad Learning System Based on Fused Lasso and Smooth Lasso
提出一种紧凑型宽度学习系统，利用L1正则化和融合项同时考虑节点与输出、节点间的相关性，在保持预测精度的前提下简化网络结构，输出稀疏平滑的权重解。
Aiming at simplifying the network structure of broad learning system (BLS), this article proposes a novel simplification method called compact BLS (CBLS). Groups of nodes play an important role in the modeling process of BLS, and it means that there may be a correlation between nodes. The proposed CBLS not only focuses on the compactness of network structure but also pays closer attention to the correlation between nodes. Learning from the idea of Fused Lasso and Smooth Lasso, it uses the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> -regularization term and the fusion term to penalize each output weight and the difference between adjacent output weights, respectively. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$L_{1}$ </tex-math></inline-formula> -regularization term determines the correlation between the nodes and the outputs, whereas the fusion term captures the correlation between nodes. By optimizing the output weights iteratively, the correlation between the nodes and the outputs and the correlation between nodes are attempted to be considered in the simplification process simultaneously. Without reducing the prediction accuracy, finally, the network structure is simplified more reasonably and a sparse and smooth output weights solution is provided, which can reflect the characteristic of group learning of BLS. Furthermore, according to the fusion terms used in Fused Lasso and Smooth Lasso, two different simplification strategies are developed and compared. Multiple experiments based on public datasets are used to demonstrate the feasibility and effectiveness of the proposed methods.