Meta-Learning With Hierarchical Models Based on Similarity of Causal Mechanisms

2 code implementations • 19 Oct 2023 • Sophie Wharrie, Samuel Kaski

In this work the goal is to generalise to new data in a non-iid setting where datasets from related tasks are observed, each generated by a different causal mechanism, and the test dataset comes from the same task distribution.

Meta-Learning Multi-Task Learning