Two-stage Learning-to-Defer for Multi-Task Learning
The Learning-to-Defer approach has been explored for classification and, more recently, regression tasks separately. Many contemporary learning tasks, however, involves both classification and regression components. In this paper, we introduce a Learning-to-Defer approach for multi-task learning tha...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Journal Article |
| Language: | English |
| Published: |
21-10-2024
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The Learning-to-Defer approach has been explored for classification and, more
recently, regression tasks separately. Many contemporary learning tasks,
however, involves both classification and regression components. In this paper,
we introduce a Learning-to-Defer approach for multi-task learning that
encompasses both classification and regression tasks. Our two-stage approach
utilizes a rejector that defers decisions to the most accurate agent among a
pre-trained joint classifier-regressor models and one or more external experts.
We show that our surrogate loss is $(\mathcal{H}, \mathcal{F}, \mathcal{R})$
and Bayes--consistent, ensuring an effective approximation of the optimal
solution. Additionally, we derive learning bounds that demonstrate the benefits
of employing multiple confident experts along a rich model in a two-stage
learning framework. Empirical experiments conducted on electronic health record
analysis tasks underscore the performance enhancements achieved through our
method. |
|---|---|
| DOI: | 10.48550/arxiv.2410.15729 |