Predicting values for a multitude of time series with target and input variables connected in a graph

A computer system comprising one or more hardware processors for training one or more machine learning—artificial intelligence (ML-AI) models for multiple prediction tasks which, alone or in combination, are configured to provide for execution of the following steps:

• inputting data for each task of a plurality of tasks and data for each additional data source of a plurality of additional data sources through a common trainable task representation function to obtain a resulting data representation for each task and each additional data source;
• inputting each resulting data representation through at least two individual trainable linear functions to obtain a corresponding prediction and a corresponding adversarial prediction;
• determining a prediction error for the plurality of tasks, an adversarial error across edges of a graph comprising the plurality of tasks and the plurality of additional data sources, an auxiliary error for the plurality of additional data sources, and a graph error between a given input graph and a graph induced by model weights;
• and
• training parameters of the common trainable task representation function and parameters of the two individual trainable linear functions based on a comparison against a weighted sum of the prediction error, the adversarial error, the auxiliary error, and the graph error.

A computer-implemented method for training one or more machine learning—artificial intelligence (ML-AI) models for multiple prediction tasks, the method comprising:

• inputting data for each of a plurality of additional data sources to a parametrized normalization function to output a normalized additional data source;
• inputting data for each of a plurality of tasks and data for each normalized additional data source to a selection layer;
• selecting, by the selection layer, data for a selected task of the plurality of tasks and data for a selected normalized additional data source of the normalized additional data sources;
• inputting data for the selected task and data for the selected normalized additional data source to a prediction layer;
• and
• outputting a prediction for the selected task.