paper-with-me

홈 › Papers

Improving Learning-to-Defer Algorithms Through Fine-Tuning

2021-12-18 · Naveen Raman, Michael Yee

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.

📄 PDF Abstract BibTeX arXiv:2112.10768

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

I Know What I Don't Know: Improving Model Cascades Through Confidence Tuning

2025-02-26 · Stephan Rabanser, Nathalie Rauschmayr, Achin Kulshrestha, Petra Poklukar 외

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+1

Principled Approaches for Learning to Defer with Multiple Experts

2023-10-23 · Anqi Mao, Mehryar Mohri, Yutao Zhong

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

2025-10-30 · Giulia DeSalvo, Clara Mohri, Mehryar Mohri, Yutao Zhong arxiv

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 Learning

Optimized Deferral for Imbalanced Settings

2026-04-30 · Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong arxiv

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 Diagnosis

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models

2024-11-10 · Jeongjin Shin, Sangdon Park

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