基于异常的对比时间序列预测
Contrastive Time Series Forecasting with Anomalies
AI总结：
Co-TSFA通过对比学习区分异常事件的影响，提升时间序列预测在异常条件下的性能。
摘要：
时间序列预测是从历史数据中预测未来值。在现实环境中，某些异常事件有持久影响并影响预测，而另一些则是短暂的，应被忽略。标准预测模型无法区分这两种情况，通常要么过度反应噪声，要么错过持续的转变。我们提出Co-TSFA（基于异常的对比时间序列预测），一种正则化框架，学习何时忽略异常和何时响应。Co-TSFA生成仅输入和输入-输出增强，以建模与预测无关和相关的异常，并引入一个潜在输出对齐损失，将表示变化与预测变化联系起来。这鼓励对无关扰动的不变性，同时保持对有意义分布变化的敏感性。在交通和电力基准以及一个现实的现金需求数据集上的实验表明，Co-TSFA在异常条件下提高了性能，同时在正常数据上保持准确性。一个匿名的GitHub仓库提供了Co-TSFA的实现，并将在接受后公开。
英文摘要：
Time series forecasting predicts future values from past data. In real-world settings, some anomalous events have lasting effects and influence the forecast, while others are short-lived and should be ignored. Standard forecasting models fail to make this distinction, often either overreacting to noise or missing persistent shifts. We propose Co-TSFA (Contrastive Time Series Forecasting with Anomalies), a regularization framework that learns when to ignore anomalies and when to respond. Co-TSFA generates input-only and input-output augmentations to model forecast-irrelevant and forecast-relevant anomalies, and introduces a latent-output alignment loss that ties representation changes to forecast changes. This encourages invariance to irrelevant perturbations while preserving sensitivity to meaningful distributional shifts. Experiments on the Traffic and Electricity benchmarks, as well as on a real-world cash-demand dataset, demonstrate that Co-TSFA improves performance under anomalous conditions while maintaining accuracy on normal data. An anonymized GitHub repository with the implementation of Co-TSFA is provided and will be made public upon acceptance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
