arXiv cs.AI· Claudio Battiloro, Pietro Greiner, Dario Rancati, Bret Nestor, Oumaima Amezgar, Francesca Dominici·· 10 小时前AI 评分27
面向多集体算法集体行动的统计框架
A Statistical Framework for Algorithmic Collective Action with Multiple Collectives
AI 导读
研究者提出首个针对多个集体同时作用于同一分类系统的算法集体行动（ACA）统计框架，给出集体行动成功率的定量统计界，并刻画各集体规模与目标一致性之间的相互作用。这些界可由每个集体在仅掌握其他集体规模与策略的部分信息时自行计算。基于智慧城市气候适应干预的模拟实验验证了该界的实用性，成果被 NeurIPS 2026 接收。
正文 · 原文
Abstract:As learning systems increasingly shape everyday decisions, Algorithmic Collective Action (ACA), i.e., users coordinating changes to shared data to steer model behavior, offers a complement to regulator-side policy and corporate model design. Real-world collective actions have traditionally been decentralized and fragmented into multiple collectives, despite sharing overarching objectives, with each collective differing in size, strategy, and actionable goals. However, most of the ACA literature focuses on single collective settings. To address this, we propose the first comprehensive statistical 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 influence a classifier's behavior. We provide quantitative statistical bounds on the success of the collectives, considering the role and the interplay of the collectives' sizes and the alignment of their goals. We make such bounds computable by each collective with only partial knowledge of other collectives' sizes and strategies. Finally, we numerically illustrate our framework on simulations inspired by interventions for climate adaptation in smart cities, demonstrating the usefulness of our bounds.
| Comments: | NeurIPS 2026. 35 pages, 17 figures, 4 tables |
| Subjects: | Methodology (stat.ME); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.06749 [stat.ME] |
| (or arXiv:2605.06749v3 [stat.ME] for this version) | |
| https://doi.org/10.48550/arXiv.2605.06749 arXiv-issued DOI via DataCite |
Submission history
From: Claudio Battiloro Dr [view email]
[v1]
Thu, 7 May 2026 15:45:53 UTC (5,094 KB)
[v2]
Mon, 9 Nov 2026 18:42:38 UTC (5,710 KB)
[v3]
Tue, 10 Nov 2026 14:59:01 UTC (5,710 KB)
来源：arXiv cs.AI · arxiv.org