Adapting, Fast and Slow: Transportable Circuits for Few-Shot Learning
By: Kasra Jalaldoust, Elias Bareinboim
Generalization across the domains is not possible without asserting a structure that constrains the unseen target domain w.r.t. the source domain. Building on causal transportability theory, we design an algorithm for zero-shot compositional generalization which relies on access to qualitative domain knowledge in form of a causal graph for intra-domain structure and discrepancies oracle for inter-domain mechanism sharing. \textit{Circuit-TR} learns a collection of modules (i.e., local predictors) from the source data, and transport/compose them to obtain a circuit for prediction in the target domain if the causal structure licenses. Furthermore, circuit transportability enables us to design a supervised domain adaptation scheme that operates without access to an explicit causal structure, and instead uses limited target data. Our theoretical results characterize classes of few-shot learnable tasks in terms of graphical circuit transportability criteria, and connects few-shot generalizability with the established notion of circuit size complexity; controlled simulations corroborate our theoretical results.
Similar Papers
On Transportability for Structural Causal Bandits
Machine Learning (CS)
Teaches computers to learn better from different experiences.
An explainable transformer circuit for compositional generalization
Machine Learning (CS)
Teaches computers to build new ideas from old.
Domain Generalizable Continual Learning
Machine Learning (CS)
Teaches computers to learn new things in new places.