Towards Robust Model Evolution with Algorithmic Recourse
원문 초록
Algorithmic Recourse is a way for users to modify their attributes to align with a model's expectations, thereby improving their outcomes after receiving unfavorable decisions. In real-world scenarios, users often need to strategically adjust their attributes to compete for limited resources. However, such strategic behavior induces users to "game" algorithms, causing model collapse due to distribution shifts. These shifts arise from user competition, resource constraints, and adaptive user responses. While prior research on Algorithmic Recourse has explored its effects on both systems and users, the impact of resource constraints and competition over time remains underexplored. In this work, we develop a general framework to model user strategic behaviors and their interactions with decision-making systems under resource constraints and competitive dynamics. Through theoretical analysis and empirical evaluation, we identify three key phenomena that arise consistently in both synthetic and real-world datasets: escalating decision boundaries, non-robust model predictions, and inequitable recourse actions. Finally, we discuss the broader social implications of these findings and present two algorithmic strategies aimed at mitigating these challenges.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sparse Imagination for Efficient Visual World Model Planning
DiCoFlex: Model-agnostic diverse counterfactuals with flexible control
Graph-Structured Data Analysis of Component Failure in Autonomous Cargo Ships Based on Feature Fusion
Making Language Model a Hierarchical Classifier and Generator
Guiding LLM Decision-Making with Fairness Reward Models
Implementing Adaptations for Vision AutoRegressive Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.