arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.26035cs.AIcs.CLcs.IR
收藏

Decision4Rec:一种受Jev启发的、基于知识图和主动图的多智能体推荐系统决策模型框架

Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender Systems

Università degli studi di Bari Aldo Moro(巴里阿尔多·莫罗大学);Otto-von-Guericke University(奥托·冯·格里克大学);Leibniz Institute for Educational Media | Georg Eckert Institute(莱布尼茨教育媒体研究所|格奥尔格·埃克尔特研究所)

Marco Polignano, Het Darshan Mehta, Pasquale Lops, Ernesto William De Luca, Giovanni Semeraro

AI总结:

该研究提出Decision4Rec框架,将决策模型应用于多智能体推荐系统,在多个数据集上提升了推荐的NDCG@10指标,开源模型表现优于商业Jev。

摘要:

决策模型(如商业版Jev)是针对问题的每个选项返回一个概率而非生成文本的语言模型。我们提出Decision4Rec,这是一个开放且模块化的框架,可让决策模型应用于推荐任务。知识图将每个推荐场景的日志以定义好的尺度写成简短陈述,例如“销量:前10%”。智能体池提出候选,残差排序器保留最佳的30个。决策模型在三个场景的真实选择上训练一次,通过类型化问题的接口读取这些信息,融合步骤将其答案与排序器的分数结合。任何具备该接口的模型都可使用,我们运行了商业版Jev、已发布的开源Kev模型,以及我们针对推荐请求训练的Kev模型。该框架搭配训练好的4B决策模型,在三个稀疏Amazon目录(其中一个从未用于训练决策模型)的NDCG@10指标上比最佳训练基线高出25%至36%,在密集Steam数据集上与基线几乎持平。大部分增益来自智能体池,搭配训练好的推荐系统时,增益源于智能体对其候选的了解而非新候选。27B决策模型在四个领域中的三个上,比0.8B模型为智能体池增加了5%至6%的增益。训练好的0.8B开源模型在15个设置中的11个上击败了已发布的Jev,且从未更差。在训练时未见过的密集领域MovieLens-1M上,增益为5%至7%。代码、配置和训练好的模型可在两个指定URL获取。

英文摘要:

Decision models, such as the commercial Jev, are language models that return one probability for each option of a question instead of generating text. We present Decision4Rec, an open and modular framework that makes decision models useful for recommendation. A knowledge graph writes the logs of each recommendation scenario as short statements on a defined scale, such as "sold: top 10%". A pool of agents, proposes candidates, and a residual ranker keeps the best 30. A decision model, trained once on real choices of three scenarios, reads them through one interface of typed questions, and a fusion step combines its answers with the score of the ranker. Any model with this interface can be used, and we run the commercial Jev, the released open Kev and Kev models trained by us on recommendation requests. The framework with a trained 4B decision model is 25 to 36% above the best trained baseline in NDCG@10 in three sparse Amazon catalogues, one of them never used to train the decision model, and almost tie with baselines on the dense Steam dataset. Most of the gain comes from the pool, and with a trained recommender it comes from what the agents know about its candidates rather than from new candidates. The 27B decision model adds to the pool 5 to 6% above the 0.8B model in three of four domains. A trained 0.8B open model beats the released Jev in eleven of fifteen settings and is never worse. On MovieLens-1M, a dense domain never seen in training, the gain is 5 to 7%. Code, configurations and trained models are available at https://github.com/marcopoli/decision4rec and https://huggingface.co/m-polignano.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑