{"data":{"full_name":"radrumond/timehetnet","name":"timehetnet","description":"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.","stars":44.0,"forks":10.0,"language":"Python","license":"MIT","archived":0.0,"subcategory":"time-series-forecasting","last_pushed_at":"2022-05-18T14:49:56+00:00","pypi_package":null,"npm_package":null,"downloads_monthly":0.0,"dependency_count":0.0,"commits_30d":null,"reverse_dep_count":0.0,"maintenance_score":0.0,"adoption_score":8.0,"maturity_score":16.0,"community_score":17.0,"quality_score":41.0,"quality_tier":"emerging","risk_flags":"['stale_6m', 'no_package', 'no_dependents']"},"meta":{"timestamp":"2026-04-06T17:22:28.288725+00:00"}}