Variational Session-based Recommendation Using Normalizing Flows
Variational Session-based Recommendation Using Normalizing Flows
复制标题
DOI：
10.1145/3308558.3313615
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Fan Zhou;Zijing Wen;Kunpeng Zhang;Goce Trajcevski;Ting Zhong
中科院分区：
文献类型：
--
作者：
Fan Zhou;Zijing Wen;Kunpeng Zhang;Goce Trajcevski;Ting Zhong
提出了一种新的产生式基于会话的推荐(SBR)框架，称为基于会话的可变推荐(VASER)，这是一种允许贝叶斯推理的非线性概率方法，可以灵活地估计序贯推荐的参数。该方法不是直接将扩展变分自动编码器(VAE)应用于SBR，而是引入归一化流程来估计概率后验估计，这比现有的深度生成推荐方法中使用的不可知的假设先验近似更有效。Vaser探索了软注意力机制，以增加会话中重要点击的权重。我们的经验表明，该模型的性能明显优于几种最先进的基线，包括最近提出的基于真实世界数据集的RNN/VAE方法。
We present a novel generative Session-Based Recommendation (SBR) framework, called VAriational SEssion-based Recommendation (VASER) - a non-linear probabilistic methodology allowing Bayesian inference for flexible parameter estimation of sequential recommendations. Instead of directly applying extended Variational AutoEncoders (VAE) to SBR, the proposed method introduces normalizing flows to estimate the probabilistic posterior, which is more effective than the agnostic presumed prior approximation used in existing deep generative recommendation approaches. VASER explores soft attention mechanism to upweight the important clicks in a session. We empirically demonstrate that the proposed model significantly outperforms several state-of-the-art baselines, including the recently-proposed RNN/VAE-based approaches on real-world datasets.