diff --git a/README.md b/README.md index 233971d..8c44807 100644 --- a/README.md +++ b/README.md @@ -8,6 +8,11 @@ Official PyTorch code repository for the [DeepTIMe paper](https://arxiv.org/abs/2207.06046). +* DeepTIMe is a deep time-index based model trained via a meta-learning formulation, yielding a strong method for + non-stationary time-series forecasting. +* Experiments on real world datases in the long sequence time-series forecasting setting demonstrates that DeepTIMe + achieves competitive results with state-of-the-art methods and is highly efficient. + ## Requirements Dependencies for this project can be installed by: @@ -48,6 +53,16 @@ __Option B__: Directly run the experiments with hyperparameters provided in the Finally, results can be viewed on tensorboard by running `tensorboard --logdir storage/experiments/`, or in the `storage/experiments/experiment_name/metrics.npy` file. +## Main Results + +We conduct extensive experiments on both synthetic and real world datasets, showing that DeepTIMe has extremely +competitive performance, achieving state-of-the-art results on 20 out of 24 settings for the multivariate forecasting +benchmark based on MSE. +

+ +

+

+ ## Detailed Usage Further details of the code repository can be found here. The codebase is structured to generate experiments from diff --git a/pics/deeptime.png b/pics/deeptime.png index 040e258..ab2801a 100644 Binary files a/pics/deeptime.png and b/pics/deeptime.png differ diff --git a/pics/results.png b/pics/results.png new file mode 100644 index 0000000..c36efee Binary files /dev/null and b/pics/results.png differ