Problem
Research questions and friction points this paper is trying to address.
irregular time series forecasting
evaluation metric
mean squared error
timestamp sampling distributions
continuous-time predictive performance
Beyond MSE: Rethinking the Evaluation Metric and Benchmarking for Irregular Time Series Forecasting
🤖 AI Summary
本文针对不规则时间序列预测中MSE评估指标的偏差问题，提出了一种新的评估方法CSE，并通过理论和实验证明了其有效性。
📝 Abstract
Existing research on irregular time-series forecasting has primarily focused on model design, while evaluation metrics remain insufficiently studied. Existing benchmarks typically use mean squared error (MSE) as the evaluation metric. We show that, in irregular forecasting, MSE is determined not only by the model prediction but also by the sample-specific timestamp sampling distributions, leading to a biased assessment of the models' continuous-time predictive performance. To address this issue, we propose the Continuous-time Squared Error (CSE), which employs importance weighting to eliminate the influence of the timestamp sampling distributions. We further theoretically prove that CSE's asymptotic estimation error with respect to continuous-time risk is no greater than that of MSE. Finally, we construct a systematic benchmark covering synthetic, semi-synthetic, and eight real-world datasets to validate the effectiveness of CSE and systematically evaluate models' continuous-time predictive performance. Experiments show that CSE can recover continuous-time risk more accurately than MSE, while relying solely on MSE may not fully reflect models' continuous-time predictive performance in real-world scenarios. Our code can be obtained at https://github.com/hnu-vis/ITS-Bench.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Continuous-time Squared Error
importance weighting
irregular time series forecasting
benchmarking
🔎 Similar Papers
No similar papers found.
