2026-07-22T08:26:22Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:20085 2024-06-10T05:20:53Z ddc:004 open_access

Incentivized Collaboration in Active Learning Cohen, Lee Shao, Han pool-based active learning individual rationality incentives Bayesian collaboration In collaborative active learning, where multiple agents try to learn labels from a common hypothesis, we introduce an innovative framework for incentivized collaboration. Here, rational agents aim to obtain labels for their data sets while keeping label complexity at a minimum. We focus on designing (strict) individually rational (IR) collaboration protocols, ensuring that agents cannot reduce their expected label complexity by acting individually. We first show that given any optimal active learning algorithm, the collaboration protocol that runs the algorithm as is over the entire data is already IR. However, computing the optimal algorithm is NP-hard. We therefore provide collaboration protocols that achieve (strict) IR and are comparable with the best known tractable approximation algorithm in terms of label complexity. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Lee Cohen and Han Shao 2024 Is Part Of LIPIcs, Volume 295, 5th Symposium on Foundations of Responsible Computing (FORC 2024) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.FORC.2024.2 urn:nbn:de:0030-drops-200851 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2024.2 eng https://creativecommons.org/licenses/by/4.0/legalcode