这篇文章利用user-user,item-item,以及user-item三类关系构建了推荐系统。本质上有点像graph embedding,切借鉴了LSTM的思想(尤其是类似于OD pair一样将graph中的边也表示成vector)。
文中,user-user relationships可以采用社交关系,比如考虑了path长度为1的(first-order influences from neighbors,直接朋友),和path长度为2的(second-order,朋友的朋友,这种组合是不是特别大!采样?)。这样为有关联的两个用户两两之间的关系建立一个vector representation。
item-item relationships可以通过物品分类,为同一个类别当中的物品,两两建立一个vector representation。
在有了以上的各种边的表达后,就可以通过一定的方法组合这些表达。例如根据当前user社交关系网络,构建一个综合表达(item方面以同样的方式处理)。最后将这些表达,以及最原始的user/item表达整合到一起,进行推荐。这里有意思的是,加权参数是利用gate neural network自动学习出来的。如,采样sigmoid function。
文献题目 | 去谷歌学术搜索 | ||||||||||
HERS: Modeling Influential Contexts with Heterogeneous Relations for Sparse and Cold-start Recommendation | |||||||||||
文献作者 | Liang Hu | ||||||||||
文献发表年限 | 2019 | ||||||||||
文献关键字 | |||||||||||
通过gate neural network自动学习加权参加;为边建立vector representation;类似于OD pair一样将graph中的边也表示成vector;user-user; item-item; user-item | |||||||||||
摘要描述 | |||||||||||
Classic recommender systems face challenges in addressing the data sparsity and cold-start problems with only modeling the user-item relation. An essential direction is to incorporate and understand the additional heterogeneous relations, e.g., user-user and item-item relations, since each user-item inter- action is often influenced by other users and items, which form the user’s/item’s influential contexts. This induces im- portant yet challenging issues, including modeling heteroge- neous relations, interactions, and the strength of the influence from users/items in the influential contexts. To this end, we design Influential-Context Aggregation Units (ICAU) to ag- gregate the user-user/item-item relations within a given con- text as the influential context embeddings. Accordingly, we propose a Heterogeneous relations-Embedded Recommender System (HERS) based on ICAUs to model and interpret the underlying motivation of user-item interactions by consider- ing user-user and item-item influences. The experiments on two real-world datasets show the highly improved recommen- dation quality made by HERS and its superiority in handling the cold-start problem. In addition, we demonstrate the inter- pretability of modeling influential contexts in explaining the recommendation results. |