Neural Information Processing Systems http://nips.cc/

In recent years, research on Automated Machine Learning (AutoML) [1] has made great strides in the data-driven design of neural network architectures [2, 3] and training hyperparameters [4].

However, clear patterns are still hard to extract since time series are often composed of several intricately entangled components.

From these temporally-aware slots, the training objective is to reconstruct the middle frame in a high-level semantic feature space. We propose a masking strategy by dropping a significant portion of tokens in the feature space for efficiency and regularization. Additionally, we address over-clustering by merging slots based on similarity.