Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

期待更强的模型 #1

Open
kpmokpmo opened this issue Aug 23, 2021 · 2 comments
Open

期待更强的模型 #1

kpmokpmo opened this issue Aug 23, 2021 · 2 comments

Comments

@kpmokpmo
Copy link

非常感谢你们的工作,很系统并有指导意义,相信持续更新可以做成相关领域的重要指南。根据我个人的经验有几个模型,可能会有更亮眼表现。

  1. StemGNN: Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
  2. TS2VEC:Learning Timestamp-Level Representations for Time Series with Hierarchical Contrastive Loss
  3. Query Selector:LONG-TERM SERIES FORECASTING WITH QUERY SELECTOR – EFFICIENT MODEL OF SPARSE ATTENTION

它们主要适用于Graph类的数据集,stemgnn在我的私有数据集上显著优于MTGNN。TS2VEC是multivariates的非监督型的模型,需要调参。Query Selector只是sparse版的transformer,但它自己列的表现较为优秀,优于Informer。如果您对以上三个可能SOTA的候选感兴趣的话不妨实验一下,如果没精力就算了哈:p。

感谢!

@deepkashiwa20
Copy link
Owner

deepkashiwa20 commented Aug 24, 2021 via email

@kpmokpmo
Copy link
Author

谢谢,会持续关注你们的工作,已经watch & star

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants