LibRec 精选
这世间从没有来日方长,许多人都是乍然离场。再见,2018。
今天的内容一定要翻到最后。
1. Comparison of Recommender Systems in an Ed-Tech Application
Alejandro Baldominos, David Quintana
https://arxiv.org/abs/1812.05465v2
Smile and Learn is an Ed-Tech company that runs a smart library with more that 100 applications, games and interactive stories, aimed at children aged 2 to 10 and their families. Given the complexity of navigating all the content, the library implements a recommender system. The results suggest a direct connection between the order of the recommendation and the interest raised, and the superiority of recommendations based on popularity against other alternatives.
2. Domain-to-Domain Translation Model for Recommender System
Linh Nguyen, Tsukasa Ishigaki
https://arxiv.org/abs/1812.06229v1
Recently multi-domain recommender systems have received much attention from researchers because they can solve cold-start problem as well as support for cross-selling. To handle the two problems, we propose a model that can extract both homogeneous and divergent features among domains and extract data in a domain can support for other domain equally: a so-called Domain-to-Domain Translation Model (D2D-TM). Experiments underscore the effectiveness of the proposed system over state-of-the-art methods by a large margin.
3. A Fuzzy Community-Based Recommender System Using PageRank
Maliheh Goliforoushani, Radin Hamidi Rad, Maryam Amir Haeri
https://arxiv.org/abs/1812.09380v1
This paper introduces a recommender system based on community detection. The recommendation is provided using the local and global similarities between users. Here, a new fuzzy community detection using the personalized PageRank metaphor is introduced.
4. Deep Heterogeneous Autoencoders for Collaborative Filtering
Tianyu Li, Yukun Ma, Jiu Xu, Bjorn Stenger, Chen Liu, Yu Hirate
https://arxiv.org/abs/1812.06610v1
This paper leverages heterogeneous auxiliary information to address the data sparsity problem of recommender systems. We propose a model that learns a shared feature space from heterogeneous data, such as item descriptions, product tags and online purchase history, to obtain better predictions. Our model consists of autoencoders, not only for numerical and categorical data, but also for sequential data, which enables capturing user tastes, item characteristics and the recent dynamics of user preference.
尾记:这是最好的时代,也是最坏的时代。
不知不觉间,LibRec也走过了几个春秋,发布了多个版本,当然也存在这样或那样的问题,大家在社区群的讨论我们也一直在关注。感谢各位朋友一直以来的支持和帮助,才促使它走到了今天。LibRec团队也正在积极调整,继续招募英才,培训选拔学生,愿早日充实力量,继续开发新版本,实现落地应用的目标。LibRec的两个关联项目:IdeaMan 和 LibDL 都已经在全力推进(具体内容见郭老师个人主页)。
再见,2018,这一年有了LibRec 3.0,也有了更多人的关注,Star数已超2000,Fork数超过780。展望,2019,希望这一年是快速发展,落地应用的转折年。除了 LibRec 团队的努力,也请求大家继续支持,多给我们提意见,时间或条件允许的话,也请贡献您的一份力量,谢谢!
感谢遇见!