
CQ
Chen Qiu, Zhigang Hua, Qi Xu, Jizhe Zhang, Sha Hua, Ren Mao, Luke Simon
· 1 min read
ResearcharXiv cs.AI
Learning Generative Ranking Policies for Whole-Page Optimization
arXiv:2611.25527v1 Announce Type: cross
Abstract: A recommendation page is consumed as a whole: the items on it compete for attention and complement one another, so the best page is not simply the individually best items placed side by side. We study whole-page optimization, which selects and orders the items on a page jointly to maximize the score of the page. The number of possible pages grows combinatorially, so good pages must be generated rather than enumerated. Some generative re-ranking methods use the same page-level training signal for every choice in a sampled page. Others imitate target pages built before training, which remain largely fixed as the generator improves. We address both limitations with one local page-level objective, which repeatedly moves the current generator toward pages with higher score. This objective splits exactly into one training target per position, and each target compares candidates at the same partial page by the scores of the complete pages they lead to. Every position therefore learns to choose the item that is better for the whole page, rather than the item that looks best on its own. We call this procedure whole-page policy improvement. On two public datasets, KuaiRand-1K and RL4RS-SeqSlate, which cover multi-objective item selection and constrained ordering, and on an industrial dataset of logged pages, our method outperforms the evaluated generative re-ranking baselines. On a synthetic benchmark with a known optimal page, it also comes closest to the optimum, showing that its improvements come from better whole-page decisions.
Original source
This story was published by arXiv cs.AI and written by Chen Qiu, Zhigang Hua, Qi Xu, Jizhe Zhang, Sha Hua, Ren Mao, Luke Simon. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


