analiza aiqbench
This paper applies machine learning to a public health problem: allocating a limited number of referral vouchers across participants and rounds in HIV-prevention peer-referral programs. Its core technical contribution is a censored count model for referral capacity, a conditional diffusion model for recruit covariates, and a structured value function that supports a greedy allocation with a (1-1/e) approximation guarantee. The reported 21.5% gain over the strongest baseline comes from two data-calibrated simulated environments, so readers should weigh it as simulation evidence rather than field results.
Reaching Hidden Populations: Generative Frontier Planning for Peer-Referral Recruitment
arXiv:2606.08360v2 Announce Type: replace-cross Abstract: Peer-referral programs help connect populations at high risk for HIV and other infectious diseases with testing and prevention services when conventional outreach is ineffective. However, referral vouchers and incentives are limited, and standard operational guidelines give each participant the same fixed number of vouchers, ignoring differences in referral capacity. Motivated by our collaboration with public health practitioners, we study how to allocate a fixed voucher budget adaptively across participants and rounds to maximize total recruitment. Prior work assumes future recruits are i.i.d. from a population-level distribution and summarizes the recruitment frontier only by its size, ignoring covariate-dependent recruitment potential. We propose Generative Frontier Planning (GFP), which learns referral capacity with a censored count model and referrer-conditioned recruit covariates with a conditional diffusion model. Its structured value function yields a deterministic Bellman backup shared by fitted value iteration and planning, while inducing diminishing returns that give intra-round greedy allocation a (1-1/e)-approximation guarantee for each fixed round budget. Cross-round selection then determines how much budget to spend. We evaluate GFP on two data-calibrated recruitment environments constructed from de-identified recruiter-recruit records: a public ICPSR respondent-driven sampling dataset and a dataset provided by FHI 360, an international global health nonprofit. GFP recruits up to 21.5% more individuals than the strongest baseline under the same budget, showing its potential for resource-limited peer-referral programs.
Authors:Lingkai Kong, Hezi Jiang, Andrew Ma, Keyu Wang, Akseli Kangaslahti, Davin Choo, Milind Tambe, Michael M. Cassell, Kayla Stankevitz, Alastair van Heerden, Cheryl Johnson
Abstract:Peer-referral programs help connect populations at high risk for HIV and other infectious diseases with testing and prevention services when conventional outreach is ineffective. However, referral vouchers and incentives are limited, and standard operational guidelines give each participant the same fixed number of vouchers, ignoring differences in referral capacity. Motivated by our collaboration with public health practitioners, we study how to allocate a fixed voucher budget adaptively across participants and rounds to maximize total recruitment. Prior work assumes future recruits are i.i.d. from a population-level distribution and summarizes the recruitment frontier only by its size, ignoring covariate-dependent recruitment potential. We propose Generative Frontier Planning (GFP), which learns referral capacity with a censored count model and referrer-conditioned recruit covariates with a conditional diffusion model. Its structured value function yields a deterministic Bellman backup shared by fitted value iteration and planning, while inducing diminishing returns that give intra-round greedy allocation a (1-1/e)-approximation guarantee for each fixed round budget. Cross-round selection then determines how much budget to spend. We evaluate GFP on two data-calibrated recruitment environments constructed from de-identified recruiter-recruit records: a public ICPSR respondent-driven sampling dataset and a dataset provided by FHI 360, an international global health nonprofit. GFP recruits up to 21.5% more individuals than the strongest baseline under the same budget, showing its potential for resource-limited peer-referral programs.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2606.08360 [cs.LG]
(or arXiv:2606.08360v2 [cs.LG] for this version)
Text integral sub licența deschisă a publicației · 256 cuvinte