In this paper, we present a robust incremental learning model for regression tasks on temporal tabular datasets. Using commonly available tabular and time-series prediction models as building blocks, a machine-learning model is built incrementally to adapt to distributional shifts in data. Using the concept of self-similarity, the model uses only two basic building blocks of machine learning models, gradient boosting decision trees and neural networks to build models for any required complexity. The model is efficient as no specialised neural architectures are used and each model building block can be independently trained in parallel. The model is demonstrated to have robust performances under adverse situations such as regime changes, fat-tailed distributions and low signal-to-noise ratios. Model robustness are studied under different hyper-parameters and complexities.

翻译：本文提出了一种鲁棒增量学习模型，用于处理时间序列表格数据的回归任务。该模型以常用的表格与时间序列预测模型为基础组件，通过增量方式构建机器学习模型，以自适应数据中的分布漂移。基于自相似性概念，模型仅使用梯度提升决策树与神经网络这两种基本机器学习组件，即可构建任意复杂度的模型。由于无需采用专用神经架构，且各模型组件可独立并行训练，因此模型具有高效性。实验表明，该模型在机制转变、厚尾分布及低信噪比等不利条件下仍表现出鲁棒性能。此外，本文研究了不同超参数与模型复杂度下的鲁棒性特性。