A Supplementary Materials

A.1 Dataset Description We describe the additional details of each dataset in the followings. For electricity, we take 500k training windows between 2014-01-01 to 2014-09-01 by reference [14, 24]. And we use the first 90% for the training set and the last 10% as the validation set. Testing set is the next 7 days after the training set. We apply the z-score normalization to the real-valued inputs of each time series.