paper-with-me

홈 › Papers

Learning to Complement and to Defer to Multiple Users

2024-07-09 · Zheng Zhang, Wenjie Ai, Kevin Wells, David Rosewarne, Thanh-Toan Do, Gustavo Carneiro

With the development of Human-AI Collaboration in Classification (HAI-CC), integrating users and AI predictions becomes challenging due to the complex decision-making process. This process has three options: 1) AI autonomously classifies, 2) learning to complement, where AI collaborates with users, and 3) learning to defer, where AI defers to users. Despite their interconnected nature, these options have been studied in isolation rather than as components of a unified system. In this paper, we address this weakness with the novel HAI-CC methodology, called Learning to Complement and to Defer to Multiple Users (LECODU). LECODU not only combines learning to complement and learning to defer strategies, but it also incorporates an estimation of the optimal number of users to engage in the decision process. The training of LECODU maximises classification accuracy and minimises collaboration costs associated with user involvement. Comprehensive evaluations across real-world and synthesized datasets demonstrate LECODU's superior performance compared to state-of-the-art HAI-CC methods. Remarkably, even when relying on unreliable users with high rates of label noise, LECODU exhibits significant improvement over both human decision-makers alone and AI alone.

📄 PDF Abstract BibTeX arXiv:2407.07003

Code (1)

zhengzhang37/lecodu 공식 구현 pytorch

Tasks

Decision Making

Similar Papers 제목 키워드 기반

DeCoDe: Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models

2025-05-25 · Chengbo He, Bochao Zou, Junliang Xing, Jiansheng Chen 외

In human-AI collaboration, a central challenge is deciding whether the AI should handle a task, be deferred to a human expert, or be addressed through collaborative effort. Existing Learning to Defer approaches typically…

Decision Making

Characterizing and Predicting Email Deferral Behavior

2019-01-14 · Sarrafzadeh Bahareh, Awadallah Ahmed Hassan, Lin Christopher H., Lee Chia-Jung 외

Email triage involves going through unhandled emails and deciding what to do with them. This familiar process can become increasingly challenging as the number of unhandled email grows. During a triage session, users com…

Sample Efficient Learning of Predictors that Complement Humans

2022-07-19 · Mohammad-Amin Charusaie, Hussein Mozannar, David Sontag, Samira Samadi

One of the goals of learning algorithms is to complement and reduce the burden on human decision makers. The expert deferral setting wherein an algorithm can either predict on its own or defer the decision to a downstrea…

Active Learning

Coverage-Constrained Human-AI Cooperation with Multiple Experts

2024-11-18 · Zheng Zhang, Cuong Nguyen, Kevin Wells, Thanh-Toan Do 외

Human-AI cooperative classification (HAI-CC) approaches aim to develop hybrid intelligent systems that enhance decision-making in various high-stakes real-world scenarios by leveraging both human expertise and AI capabil…

Decision Making

An Advanced Reinforcement Learning Framework for Online Scheduling of Deferrable Workloads in Cloud Computing

2024-06-03 · Hang Dong, Liwen Zhu, Zhao Shan, Bo Qiao 외

Efficient resource utilization and perfect user experience usually conflict with each other in cloud computing platforms. Great efforts have been invested in increasing resource utilization but trying not to affect users…

Cloud ComputingDeep Reinforcement LearningScheduling