LibRec 精选：连通知识图谱与推荐系统

LibRec 精选

推荐系统进展 第11期（更新至2018.8.5），更新10篇论文。

等一个人，还是等一个故事。-- 海子

1

社交更新

1

RecSys 2018 accepted papers: 
https://recsys.acm.org/recsys18/accepted-contributions/

2

【Andreu Vall's Slides】Song context and song order in music playlist generation: 
https://t.co/FCk0obDpKN

3

【Neo4j blog】The future of recommendation engines: graph-aided search:
https://neo4j.com/blog/recommendation-engines-graph-aided-search/

4

【Slides】Deep Learning-based recommendations for Germany's biggest vehicle marketplace:
https://www.slideshare.net/FlorianWilhelm2/deep-learningbased-recommendations-for-germanys-biggest-online-vehicle-marketplace-90541406

2

论文更新

KB4Rec: A Dataset for Linking Knowledge Bases with Recommender Systems

Wayne Xin Zhao, Gaole He, Hongjian Dou et al.

https://arxiv.org/abs/1807.11141v2

To develop a knowledge-aware recommender system, a key data problem is how we can obtain rich and structured knowledge information for recommender system (RS) items. Existing datasets or methods either use side information from original recommender systems (containing very few kinds of useful information) or utilize private knowledge base (KB). In this paper, we present the first public linked KB dataset for recommender systems, named KB4Rec v1.0, which has linked three widely used RS datasets with the popular KB Freebase.

Automatic Clone Recommendation for Refactoring Based on the Present and the Past

Ruru Yue, Zhe Gao, Na Meng et al.

https://arxiv.org/abs/1807.11184v1

To help developers refactor code and improve software quality, various tools were built to recommend clone-removal refactorings based on the past and the present information, such as the cohesion degree of individual clones or the co-evolution relations of clone peers. This paper introduces CREC, a learning-based approach that recommends clones by extracting features from the current status and past history of software projects. We designed the largest feature set thus far for clone recommendation, and performed an evaluation on six large projects.

Mixture Matrix Completion

Daniel L. Pimentel-Alarcón

https://arxiv.org/abs/1808.00616v1

Completing a data matrix X has become an ubiquitous problem in modern data science, with applications in recommender systems, computer vision, and networks inference, to name a few. This paper generalizes these models to what we call mixture matrix completion (MMC): the case where each entry of X corresponds to one of several low-rank matrices. MMC is a more accurate model for recommender systems, and brings more flexibility to other completion and clustering problems.

Rank and Rate: Multi-task Learning for Recommender Systems

Guy Hadash, Oren Sar Shalom, Rita Osadchy

https://arxiv.org/abs/1807.11698v1

The two main tasks in the Recommender Systems domain are the ranking and rating prediction tasks. Several previous approaches proposed learning user and item representations to optimize both tasks simultaneously in a multi-task framework. In this work we propose a novel multi-task framework that exploits the fact that a user does a two-phase decision process - first decides to interact with an item (ranking task) and only afterward to rate it (rating prediction task).

RecoGym: A Reinforcement Learning Environment for the problem of Product Recommendation in Online Advertising

David Rohde, Stephen Bonner, Travis Dunlop et al.

https://arxiv.org/abs/1808.00720v1

Recommender Systems are becoming ubiquitous in many settings and take many forms, from product recommendation in e-commerce stores, to query suggestions in search engines, to friend recommendation in social networks. Current research directions which are largely based upon supervised learning from historical data appear to be showing diminishing returns with a lot of practitioners report a discrepancy between improvements in offline metrics for supervised learning and the online performance of the newly proposed models. To this end we introduce RecoGym, an RL environment for recommendation, which is defined by a model of user traffic patterns on e-commerce and the users response to recommendations on the publisher websites.

News Session-Based Recommendations using Deep Neural Networks

Gabriel de Souza P. Moreira, Felipe Ferreira, Adilson Marques da Cunha

https://arxiv.org/abs/1808.00076v1

Some promising results have been recently achieved by the usage of Deep Learning techniques on Recommender Systems, specially for item's feature extraction and for session-based recommendations with Recurrent Neural Networks. In this paper, its presented a Deep Learning architecture for Session-Based recommendations of News articles. This architecture is composed of two modules, the first responsible to learn news articles representations, based on their text and metadata, and the second module aimed to provide session-based recommendations using Recurrent Neural Networks.

The Importance of Context When Recommending TV Content: Dataset and Algorithms

Miklas S. Kristoffersen, Sven E. Shepstone, Zheng-Hua Tan

https://arxiv.org/abs/1808.00337v1

Users' decision processes are complex and highly influenced by contextual settings, but data supporting the development and evaluation of context-aware recommender systems are scarce. In this paper we present a dataset of self-reported TV consumption enriched with contextual information of viewing situations. The results suggest that including contextual features in the prediction cause notable improvements, and both temporal and social context show significant contributions.

Revealing the Unobserved by Linking Collaborative Behavior and Side Knowledge

Evgeny Frolov, Ivan Oseledets

https://arxiv.org/abs/1807.10634v1

We propose a tensor-based model that fuses a more granular representation of user preferences with the ability to take additional side information into account. The model relies on the concept of ordinal nature of utility, which better corresponds to actual user perception. We demonstrate the effectiveness of the proposed model on several standard benchmark datasets.

Task Recommendation in Crowdsourcing Based on Learning Preferences and Reliabilities

Qiyu Kang, Wee Peng Tay

https://arxiv.org/abs/1807.10444v1

An important problem in crowdsourcing is the task recommendation problem, in which tasks that best match a particular worker's preferences and reliabilities are recommended to that worker. A task recommendation scheme that assigns tasks more likely to be accepted by a worker who is more likely to complete it reliably results in better performance for the task requester. We develop three task recommendation strategies to determine the number of gold tasks for different task categories, and show that they are order optimal.

Recurrent Neural Networks for Long and Short-Term Sequential Recommendation

Kiewan Villatel, Elena Smirnova, Jérémie Mary et al.

https://arxiv.org/abs/1807.09142v1

A large body of previous research studied long-term recommendation through dimensionality reduction techniques applied to the historical user-item interactions. A recently introduced session-based recommendation setting highlighted the importance of modeling short-term user preferences. In this task, Recurrent Neural Networks (RNN) have shown to be successful at capturing the nuances of user's interactions within a short time window.