We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift.

However, the exact conditions under which transfer learning succeeds in a cross-domain cross-task setting are still poorly understood.

Due to its equivariance property, BITR can not only handle non-overlapped PCs, but also guarantee robustness against initial positions.

Penalizing the nuclear norm of a function's Jacobian encourages it to locally behave

Recent evidence suggests that, in some problems, NeSy models can achieve high accuracy on the reasoning task by learning concepts with incorrect semantics .

We consider sequential treatment regimes where each unit is exposed to combinations of interventions over time.

Deep learning models have advanced ETS modeling by effectively capturing sequence dependence. However, learning a generic representation of ETS data for various applications is challenging due to the inherently complex hierarchical structure of ETS data.

Extensive evaluations demonstrate that AMT yields significant improvements, up to 12.92% in