基本思想是:其他推荐系统推荐用户没有访问过的物品,本论文推荐用户已经访问过的物品(预测),在已经知道历史物品访问序列了,再次访问的概率。
实际上,只要把重复访问的物品放进用户历史序列当中,也允许最后推荐的时候,推荐已经访问的物品,这个问题就算解决了。
本文不同的是,本文是要在模型当中,显性的考虑re-click items。具体做法如下:
(1)将用户历史访问过的物品构成一个序列Is
(2)每一个item有一个embedding,将Is当中的item embedding依次输入到GRU当中,依次得到Is当中每一个物品的新的表达ht
(3)给定当前的t(当前考虑的item),以及一个extra parameter vector guiding attention model,就可以计算t之前每一个的item(包括t)attention/weight;
(4)上面学到的attention/weights,有两个作用:1)aggregate 相关的ht,构成一个新的vector representation;2)用weights构造物品被推荐的概率
(5)利用(3)和(4)的方法,可以分别为repeat和new recommendation tasks各学出一组weights以及相应的aggregation vector representations。
(6)两组aggregation vector representations分别被用来计算repeat和new recommendation tasks两个任务之间的概率分布,以及new item的概率分布。
(7)这样,在给定一个t时,首先判断t时候的物品是否在此之前出现过,根据其出现与否决定采用上述的不同概率表达(repeat or new recommendation)。
(8)最后极大似然已经观察到的样本,求出参数。
(9)得到参数以后,可以往后推一个t,得到新ht,以及对应的weights-score,做出相应推荐。
注意,本文存在的问题:依赖GRU,导致每一个item的序都很重要(严格的序问题,有时后session内部的item的序并不重要)。
文献题目 | 去谷歌学术搜索 | ||||||||||
RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation | |||||||||||
文献作者 | Pengjie Ren | ||||||||||
文献发表年限 | 2019 | ||||||||||
文献关键字 | |||||||||||
所谓的repeat,指的是推荐可重复消费的物品;GRU;session encoder; attention model; OOCHOOSE; DIGINETICA; LASTFM | |||||||||||
摘要描述 | |||||||||||
Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce, music, and TV program recommendations), where the same item is re-consumed repeatedly over time. However, no previous studies have emphasized repeat consumption with neural networks. An effective neural approach is needed to decide when to perform repeat recommendation. In this paper, we incorporate a repeat-explore mechanism into neural networks and propose a new model, called RepeatNet, with an encoder-decoder structure. RepeatNet integrates a regular neural recommendation approach in the decoder with a new repeat recommendation mechanism that can choose items from a user’s history and recommends them at the right time. We report on extensive experiments on three benchmark datasets. RepeatNet outperforms state-of-the-art baselines on all three datasets in terms of MRR and Recall. Furthermore, as the dataset size and the repeat ratio increase, the improvements of RepeatNet over the baselines also increase, which demonstrates its advantage in handling repeat recommendation scenarios. |