We allow the effective combination of design experience from different sources, so as to create an effective search space containing a variety of TSF models to support different TSF tasks.
Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments.
They are lack of self-evaluation ability, that is, to examine the rationality of their prediction results, thus failing to guide users to identify high-quality ones from their candidate results.
Although the Trajectory Prediction (TP) model has achieved great success in computer vision and robotics fields, its architecture and training scheme design rely on heavy manual work and domain knowledge, which is not friendly to common users.
Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem.
Recently, some Neural Architecture Search (NAS) techniques are proposed for the automatic design of Graph Convolutional Network (GCN) architectures.
In recent years, many spatial-temporal graph convolutional network (STGCN) models are proposed to deal with the spatial-temporal network data forecasting problem.
In our work, we present Auto-CASH, a pre-trained model based on meta-learning, to solve the CASH problem more efficiently.
To reduce searching cost, most NAS algorithms use fixed outer network level structure, and search the repeatable cell structure only.
However, most machine learning algorithms are sensitive to the hyper-parameters.
Motivated by this, we propose ExperienceThinking algorithm to quickly find the best possible hyperparameter configuration of machine learning algorithms within a few configuration evaluations.
In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems.