code ref 1 https://maciejkula.github.io/spotlight/sequence/representations.html#
code ref 2 https://github.com/hidasib/GRU4Rec
单个item（one-hot）作为输入，下一个item作为输出（这里的items在同一个session当中，且order aware，顺序是有意义的）——一个session涉及了多个前后对items可作为GRU的训练。其中the number of hidden units可以理解为隠向量的维度。
| 文献题目 | 去谷歌学术搜索 | ||||||||||
| Session-based recommendations with recurrent neural networks | |||||||||||
| 文献作者 | Bal´azs Hidasi | ||||||||||
| 文献发表年限 | 2016 | ||||||||||
| 文献关键字 | |||||||||||
| GRU4Rec-basic | |||||||||||
| 摘要描述 | |||||||||||
| We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNNbased approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches. | |||||||||||
