Model card
Autoformer.
THUMLopen-sourceUnknown paramsTransformer
Time series forecasting model
§ 01 · Benchmarks
Every benchmark Autoformer has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | M4 Competition | Time Series · Time Series Forecasting | mase | 1.8% | #4 | 2021-06-24 | source ↗ |
| 02 | M4 Competition | Time Series · Time Series Forecasting | owa | 0.9% | #4 | 2021-06-24 | source ↗ |
| 03 | M4 Competition | Time Series · Time Series Forecasting | smapi | 12.9% | #4 | 2021-06-24 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for Autoformer.
- 2021-06-24· Time Series· 3 results
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
Haixu Wu, Jiehui Xu, Jianmin Wang, Mingsheng Long
§ 04 · Related models
Other THUML models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
TimeMixer++ Table 2
3
results
3 of 3 rows marked verified.