本文的想法跟我的文章的基本想法很像。即，融入item的structure information （也就是category）
区别是：
（1）构造category-embedding 的形式不同（我们是aggregate items based on attention model； 他们是先利用物品所属的类别情况-path，构造category graph，然后利用现有graph embedding的方法学出每个category的表达）
（2）融合item embedding和category embedding的方式不同（我们利用category加权items的embedding；他们是concatenate 两者的embeddings）
（3）each-hop using a level of the category
（4）本文没有用user static representation
本文具体做法：
（1）最先利用GRU和用户的item sequences构造一个表达1
（2）选定特定数量的items (A=20)构造memory matrix；（会update这个matrix： first-in-first-out），每个items连同他的category 的embedding一起构造矩阵的一行向量
（3）通过GRU的输出，寻找（2）中的向量（加权）
（4）每一个GRU unit对应一个category level。这样就可以输出每个category 对应的表达
（5）将（4）以及（1）中的表达整合到一起形成用户最终的表达
（6）构造一个蕴含分类信息的item embedding （concatenate 原始的item embedding和该item 所属category embedding）
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Taxonomy-Aware Multi-Hop Reasoning Networks for Sequential Recommendation | |||||||||||
| 文献作者 | Jin Huang; Wayne Xin Zhao | ||||||||||
| 文献发表年限 | 2019 | ||||||||||
| 文献关键字 | |||||||||||
| Sequential recommendation, multi-hop reasoning, taxonomy, category; memory model； wsdm 19 | |||||||||||
| 摘要描述 | |||||||||||
| In this paper, we focus on the task of sequential recommendation using taxonomy data. Existing sequential recommendation methods usually adopt a single vectorized representation for learning the overall sequential characteristics, and have a limited modeling capacity in capturing multi-grained sequential characteristics over context information. Besides, existing methods often directly take the feature vectors derived from context information as auxiliary input, which is difficult to fully exploit the structural patterns in context information for learning preference representations. To address above issues, we propose a novel Taxonomy-aware Multi-hop Reasoning Network, named TMRN, which integrates a basic GRU-based sequential recommender with an elaborately designed memory-based multi-hop reasoning architecture. For enhancing the reasoning capacity, we incorporate taxonomy data as structural knowledge to instruct the learning of our model. We associate the learning of user preference in sequential recommendation with the category hierarchy in the taxonomy. Given a user, for each recommendation, we learn a unique preference representation corresponding to each level in the taxonomy based on her/his overall sequential preference. In this way, the overall, coarse-grained pref- erence representation can be gradually refined in different levels from general to specific, and we are able to capture the evolvement and refinement of user preference over the taxonomy, which makes our model highly explainable. Extensive experiments show that our proposed model is superior to state-of-the-art baselines in terms of both effectiveness and interpretability. | |||||||||||
