一作SIGIR 2026Poster· Information Retrieval (Industry)
Precision at Scale: An End-to-End Graph-based Framework for Mitigating Network Interference in TikTok A/B Tests
Yuhan Li · Jiayun Ni · Ao Li · Yue Wang · Seng You Paul Chee · Yongmin Hu · Runze Yu
摘要
Large-scale A/B tests on social platforms suffer from inherent network interference, violating the Stable Unit Treatment Value Assumption (SUTVA) and distorting measured results. Industrial practices for mitigating network interference face a foundational trade-off. For scalability, they often re...