LibRec 精选：位置感知的长序列会话推荐

LibRec 精选

LibRec智能推荐 第 32 期（至2019.5.16），更新 4 篇精选内容。

因着内心的向往，我们会在命运的道路上最终遇到属于自己的电影。

1

【数据集】Google发布了新版本的地标识别和抽取数据集，链接: https://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html

近期热点论文

---

导读：本期更新的论文较少，推荐第1篇论文，讨论的是位置信息对基于长观看序列的视频推荐的影响。

1. The Order of Things: Position-Aware Network-friendly Recommendations in  Long Viewing Sessions

Theodoros Giannakas, Thrasyvoulos Spyropoulos, Pavlos Sermpezis

https://arxiv.org/abs/1905.04947v1

At the same time, recent works have shown that recommendations of popular content apps are responsible for a significant percentage of users requests. As a result, some very recent works have considered how to nudge recommendations to facilitate the network (e.g., increase cache hit rates). Finally, we use a range of real datasets we collected to investigate the impact of position preference in recommendations on the proposed optimal algorithm.

2. PrivateJobMatch: A Privacy-Oriented Deferred Multi-Match Recommender  System for Stable Employment

Amar Saini

https://arxiv.org/abs/1905.04564v1

Centralized job search engines provide a platform that connects directly employers with job-seekers. In this paper, we present PrivateJobMatch -- a privacy-oriented deferred multi-match recommender system -- which generates stable pairings while requiring users to provide only a partial ranking of their preferences. Over the past year, we have implemented a PrivateJobMatch prototype and deployed it in an active job market economy.

3. A resource-based rule engine for energy savings recommendations in  educational buildings

Giovanni Cuffaro, Federica Paganelli, Georgios Mylonas

https://arxiv.org/abs/1905.05015v1

Raising awareness among young people on the relevance of behaviour change for achieving energy savings is widely considered as a key approach towards long-term and cost-effective energy efficiency policies. The GAIA Project aims to deliver a comprehensive solution for both increasing awareness on energy efficiency and achieving energy savings in school buildings. In this framework, we present a novel rule engine that, leveraging a resource-based graph model encoding relevant application domain knowledge, accesses IoT data for producing energy savings recommendations.