Few-Shot Forecasting of Time-Series with Heterogeneous Channels

7 Apr 2022  ·  Lukas Brinkmeyer, Rafael Rego Drumond, Johannes Burchert, Lars Schmidt-Thieme ·

Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experience with similar datasets is a well-established technique for classification problems called few-shot classification. However, existing approaches cannot be applied to time-series forecasting because i) multivariate time-series datasets have different channels and ii) forecasting is principally different from classification. In this paper we formalize the problem of few-shot forecasting of time-series with heterogeneous channels for the first time. Extending recent work on heterogeneous attributes in vector data, we develop a model composed of permutation-invariant deep set-blocks which incorporate a temporal embedding. We assemble the first meta-dataset of 40 multivariate time-series datasets and show through experiments that our model provides a good generalization, outperforming baselines carried over from simpler scenarios that either fail to learn across tasks or miss temporal information.

PDF Abstract


Introduced in the Paper:


Used in the Paper:

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Time-Series Few-Shot Learning with Heterogeneous Channels TimeHetNet TimeHetNet MSE (t+1) 0.148 # 1
MSE (t+10) 0.389 # 1
MSE (t+80) 0.509 # 1
MSE (t+100) 0.579 # 1


No methods listed for this paper. Add relevant methods here