研究多个群体如何协同操纵数据，影响分类模型决策。
Algorithmic Collective Action with Multiple Collectives
- 提出多群体算法集体行动的首个理论框架
- 揭示群体规模与目标一致性的协同作用机制
- 适用于关注数据操控与模型偏见的研究者
随着学习系统在日常决策中扮演越来越重要的角色，用户侧通过算法集体行动（ACA）——协调共享数据的修改——成为监管政策和企业模型设计之外的重要补充。尽管现实中的行动通常分散于多个具有共同目标但规模、策略和可操作目标各异的群体，现有ACA研究大多局限于单一群体场景。本文首次构建了多个群体在同一系统上开展ACA的理论框架。重点研究分类任务中，多个群体如何植入信号（即通过修改特征，使分类器学习到特定特征版本与一组选定目标类别的关联）。我们量化分析了群体规模及其目标对齐程度之间的相互作用。该框架结合先前的实证结果，为多群体算法集体行动提供了整体性研究路径。
原文摘要 · Abstract (English)
As learning systems increasingly influence everyday decisions, user-side steering via Algorithmic Collective Action (ACA)-coordinated changes to shared data-offers a complement to regulator-side policy and firm-side model design. Although real-world actions have been traditionally decentralized and fragmented into multiple collectives despite sharing overarching objectives-with each collective differing in size, strategy, and actionable goals, most of the ACA literature focused on single collective settings. In this work, we present the first theoretical framework for ACA with multiple collectives acting on the same system. In particular, we focus on collective action in classification, studying how multiple collectives can plant signals, i.e., bias a classifier to learn an association between an altered version of the features and a chosen, possibly overlapping, set of target classes. We provide quantitative results about the role and the interplay of collectives' sizes and their alignment of goals. Our framework, by also complementing previous empirical results, opens a path for a holistic treatment of ACA with multiple collectives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。