Time Series Forecasting
PulseAugur coverage of Time Series Forecasting — every cluster mentioning Time Series Forecasting across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
TimeGuard 防御机制应对时间序列预测中的后门攻击
研究人员开发了TimeGuard，一种专门针对时间序列预测（TSF）的后门攻击的新防御机制。现有的防御机制在TSF方面存在困难，因为数据纠缠和任务制定转移会稀释信号，并使被污染的数据与干净数据无法区分。TimeGuard通过采用通道级池训练和基于时间感知标准初始化的置信度高的池，以及距离正则化损失选择来管理训练退化，从而解决了这些问题。实验表明，TimeGuard在保持干净性能的同时，显著增强了对TSF后门攻击的鲁棒性。
-
Study reveals model selection failures in time series forecasting across data regimes
A new research paper published on arXiv investigates the challenges of selecting appropriate models for time series forecasting. The study reveals that rule-based selection methods, which rely on simple data characteris…
-
Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning
Researchers have developed a new activation function called squared sigmoid-tanh (SST) designed to improve the performance of Gated Recurrent Units (GRUs) in sequence learning tasks, particularly when training data is l…