arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00860cs.IR
收藏

GRN:用于上下文推荐的生成重排序网络

GRN: Generative Rerank Network for Context-wise Recommendation

Yufei Feng, Binbin Hu, Yu Gong, Fei Sun, Qingwen Liu, Wenwu Ou

摘要:

重新排序在推荐系统中引起了越来越多的关注,它将输入的排序列表重新排列成最终的排序列表,以更好地满足用户的需求。大多数现有的方法通过逐点或列表模型的评分对候选人进行重新排序。尽管有效,忽略了每个项目和它的上下文之间的相互影响,在最终的排名列表往往使贪婪的策略为基础的重排序方法次优。在这项工作中,我们提出了一个新的上下文明智的重排名框架命名为生成重排名网络(GRN)。具体来说,我们首先设计了评估器,它应用Bi-LSTM和自我注意力机制对带标签的最终排名列表中的上下文信息进行建模,更精确地预测每个项目的交互概率。然后,我们详细介绍了生成器,配备了GRU,注意力机制和指针网络,从输入的排名表中逐步选择项目。最后,我们应用交叉熵损失训练评估器,并随后,策略梯度,以优化生成器的指导下,评估器。实证结果表明,GRN一致和显着优于国家的最先进的逐点和列表的方法。此外,在淘宝应用的一个热门推荐场景中成功部署后,GRN在PV和IPV指标上分别实现了5.2%和6.1%的性能提升。

英文摘要:

Reranking is attracting incremental attention in the recommender systems, which rearranges the input ranking list into the final rank-ing list to better meet user demands. Most existing methods greedily rerank candidates through the rating scores from point-wise or list-wise models. Despite effectiveness, neglecting the mutual influence between each item and its contexts in the final ranking list often makes the greedy strategy based reranking methods sub-optimal. In this work, we propose a new context-wise reranking framework named Generative Rerank Network (GRN). Specifically, we first design the evaluator, which applies Bi-LSTM and self-attention mechanism to model the contextual information in the labeled final ranking list and predict the interaction probability of each item more precisely. Afterwards, we elaborate on the generator, equipped with GRU, attention mechanism and pointer network to select the item from the input ranking list step by step. Finally, we apply cross-entropy loss to train the evaluator and, subsequently, policy gradient to optimize the generator under the guidance of the evaluator. Empirical results show that GRN consistently and significantly outperforms state-of-the-art point-wise and list-wise methods. Moreover, GRN has achieved a performance improvement of 5.2% on PV and 6.1% on IPV metric after the successful deployment in one popular recommendation scenario of Taobao application.

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。

↑