提出双机制拒绝异常与新数据，提升时间序列预测可靠性。
Towards Reliable Time Series Forecasting under Future Uncertainty: Ambiguity and Novelty Rejection Mechanisms
- 用预测误差方差判断不确定性，低置信时主动拒绝
- 通过变分自编码器和马氏距离检测训练外的新数据
- 适合动态环境下的高可靠性预测需求
真实世界的时间序列预测面临不确定性与缺乏可靠评估的挑战。预测误差常源于对分布内数据的欠拟合以及对分布外输入的处理失败。为提升模型可靠性，本文提出结合模糊性拒绝与新颖性拒绝的双重拒绝机制。模糊性拒绝基于预测误差方差，通过历史误差方差分析判断置信度，无需未来真值即可决定是否拒绝预测；新颖性拒绝采用变分自编码器与马氏距离，识别偏离训练数据分布的输入。该双重策略在动态环境中有效降低误差并适应数据变化，显著提升复杂场景下的预测可靠性。
原文摘要 · Abstract (English)
In real-world time series forecasting, uncertainty and lack of reliable evaluation pose significant challenges. Notably, forecasting errors often arise from underfitting in-distribution data and failing to handle out-of-distribution inputs. To enhance model reliability, we introduce a dual rejection mechanism combining ambiguity and novelty rejection. Ambiguity rejection, using prediction error variance, allows the model to abstain under low confidence, assessed through historical error variance analysis without future ground truth. Novelty rejection, employing Variational Autoencoders and Mahalanobis distance, detects deviations from training data. This dual approach improves forecasting reliability in dynamic environments by reducing errors and adapting to data changes, advancing reliability in complex scenarios.
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。