Improving Learning-to-Defer Algorithms Through Fine-Tuning
The ubiquity of AI leads to situations where humans and AI work together, creating the need for learning-to-defer algorithms that determine how to partition tasks between AI and humans. We work to improve learning-to-defer algorithms when paired with specific individuals by incorporating two fine-tuning algorithms and testing their efficacy using both synthetic and image datasets. We find that fine-tuning can pick up on simple human skill patterns, but struggles with nuance, and we suggest future work that uses robust semi-supervised to improve learning.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
I Know What I Don't Know: Improving Model Cascades Through Confidence Tuning
Large-scale machine learning models deliver strong performance across a wide range of tasks but come with significant computational and resource constraints. To mitigate these challenges, local smaller models are often d…
Decoderimage-classificationImage ClassificationLanguage Modeling+1Principled Approaches for Learning to Defer with Multiple Experts
We present a study of surrogate losses and algorithms for the general problem of learning to defer with multiple experts. We first introduce a new family of surrogate losses specifically tailored for the multiple-expert …
Budgeted Multiple-Expert Deferral
Learning to defer uncertain predictions to costly experts offers a powerful strategy for improving the accuracy and efficiency of machine learning systems. However, standard training procedures for deferral algorithms ty…
Active LearningOptimized Deferral for Imbalanced Settings
Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in doma…
Image ClassificationMedical DiagnosisUnlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
Deep learning models are vulnerable to backdoor attacks, where adversaries inject malicious functionality during training that activates on trigger inputs at inference time. Extensive research has focused on developing s…
Backdoor Attack