Learning from Time Series under Temporal Label Noise
CoRR(2024)
摘要
Many sequential classification tasks are affected by label noise that varies
over time. Such noise can cause label quality to improve, worsen, or
periodically change over time. We first propose and formalize temporal label
noise, an unstudied problem for sequential classification of time series. In
this setting, multiple labels are recorded in sequence while being corrupted by
a time-dependent noise function. We first demonstrate the importance of
modelling the temporal nature of the label noise function and how existing
methods will consistently underperform. We then propose methods that can train
noise-tolerant classifiers by estimating the temporal label noise function
directly from data. We show that our methods lead to state-of-the-art
performance in the presence of diverse temporal label noise functions using
real and synthetic data.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要