VARNN通过记忆预测误差，提升时序回归在波动环境下的鲁棒性。
Variability Aware Recursive Neural Network (VARNN): A Residual-Memory Model for Capturing Temporal Deviation in Sequence Regression Modeling
- 引入误差记忆机制，动态更新短期残差以捕捉变化趋势。
- 在多领域数据上测试均低于基线模型的均方误差。
- 适合处理噪声波动、模式漂移的现实时序数据任务。
真实世界的时间序列数据普遍存在非平稳性、状态切换和随时间变化的噪声（异方差性），导致传统回归模型鲁棒性下降。我们提出变异性感知递归神经网络（VARNN），一种新型残差感知架构，用于监督式时序回归。VARNN 在前馈预测器基础上引入可学习的误差记忆状态，该状态基于短窗口内的预测残差更新，作为变异性和漂移的信号，并用于校准当前时刻的最终预测。在家电能耗、医疗健康和环境监测等多个数据集上，实验表明VARNN在保持极低计算开销的前提下，性能优于静态、动态及循环基线模型，测试均方误差更低。结果表明，VARNN在漂移与高波动环境下仍能提供稳健预测，展现出作为时序学习通用框架的巨大潜力。
原文摘要 · Abstract (English)
Real-world time series data exhibit non-stationary behavior, regime shifts, and temporally varying noise (heteroscedastic) that degrade the robustness of standard regression models. We introduce the Variability-Aware Recursive Neural Network (VARNN), a novel residual-aware architecture for supervised time-series regression that learns an explicit error memory from recent prediction residuals and uses it to recalibrate subsequent predictions. VARNN augments a feed-forward predictor with a learned error-memory state that is updated from residuals over a short context steps as a signal of variability and drift, and then conditions the final prediction at the current time step. Across diverse dataset domains, appliance energy, healthcare, and environmental monitoring, experimental results demonstrate VARNN achieves superior performance and attains lower test MSE with minimal computational overhead over static, dynamic, and recurrent baselines. Our findings show that the VARNN model offers robust predictions under a drift and volatility environment, highlighting its potential as a promising framework for time-series learning.
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。