LibRec 精选：推荐系统的论文与源码

LibRec 精选

LibRec智能推荐 第 19 期（至2018.11.29），更新 6 篇精彩讨论内容。

白首如新，倾盖如故。 

1

RecSys 2019 @ Copenhagen, Denmark, Sep. 16-20, 2019，链接：https://recsys.acm.org/recsys19/ 

2

搜索与推荐系统的论文与源码，链接：http://fmoraes.nl/se-recsys-paperswithcode/ 

3

PhD positions available @ University of Glasgow【信息检索与推荐系统】，链接：https://www.gla.ac.uk/schools/computing/postgraduateresearch/postgraduateresearchstudy/phd-projects/

4

Mixed-initiative recommender systems【PPT】，链接：https://www.slideshare.net/kverbert/mixedinitiative-recommender-systems/ 

1. Recommending Users: Whom to Follow on Federated Social Networks

Jan Trienes, Andrés Torres Cano, Djoerd Hiemstra

https://arxiv.org/abs/1811.09292v1

Popular social networks such as Facebook and Twitter generate follow recommendations by listing profiles a user may be interested to connect with. Federated social networks aim to resolve issues associated with the popular social networks - such as large-scale user-surveillance and the miss-use of user data to manipulate elections - by decentralizing authority and promoting privacy. Due to their recent emergence, recommender systems do not exist for federated social networks, yet.

2. Attentive Neural Architecture Incorporating Song Features For Music Recommendation

Noveen Sachdeva, Kartik Gupta, Vikram Pudi

https://arxiv.org/abs/1811.08203v1

Often the aim of these systems is to increase the time, the user spends on the platform and hence having a high commercial value. Prediction of the next song the user might like requires some kind of modeling of the user interests at the given point of time. In this direction, we propose a novel attentive neural architecture which in addition to the sequence of items selected by the user, uses the features of these items to better learn the user short-term preferences and recommend the next song to the user.

3. Bias Disparity in Recommendation Systems

Virginia Tsintzou, Evaggelia Pitoura, Panayiotis Tsaparas

https://arxiv.org/abs/1811.01461v1

More importantly, there are cases where recommenders may amplify such biases, leading to the phenomenon of bias disparity. In this short paper, we present a preliminary experimental study on synthetic data, where we investigate different conditions under which a recommender exhibits bias disparity, and the long-term effect of recommendations on data bias. We also consider a simple re-ranking algorithm for reducing bias disparity, and present some observations for data disparity on real data.

4. GEMRank: Global Entity Embedding For Collaborative Filtering

Arash Khoeini, Bita Shams, Saman Haratizadeh

https://arxiv.org/abs/1811.01686v1

Unlike many other domains, this approach has not achieved a desired performance in collaborative filtering problems, probably due to unavailability of appropriate textual data. It uses the concept of profile co-occurrence for defining relations among entities and applies a factorization method for embedding the users and items. The results show that GEMRank significantly outperforms the baseline algorithms in a variety of data sets with different degrees of density.

5. Deep Item-based Collaborative Filtering for Top-N Recommendation

Feng Xue, Xiangnan He, Xiang Wang, Jiandong Xu, Kai Liu, Richang Hong

https://arxiv.org/abs/1811.04392v1

Item-based Collaborative Filtering(short for ICF) has been widely adopted in recommender systems in industry, owing to its strength in user interest modeling and ease in online personalization. By constructing a user's profile with the items that the user has consumed, ICF recommends items that are similar to the user's profile. We treat this solution as a deep variant of ICF, thus term it as DeepICF.

6. Fast Non-Bayesian Poisson Factorization for Implicit-Feedback Recommendations

David Cortes

https://arxiv.org/abs/1811.01908v1

This work explores non-negative matrix factorization based on regularized Poisson models for recommender systems with implicit-feedback data. The properties of Poisson likelihood allow a shortcut for very fast computation and optimization over elements with zero-value when the latent-factor matrices are non-negative, making it a more suitable approach than squared loss for very sparse inputs such as implicit-feedback data. A simple and embarrassingly parallel optimization approach based on proximal gradients is presented, which in large datasets converges 2-3 orders of magnitude faster than its Bayesian counterpart (Hierarchical Poisson Factorization) fit through variational inference techniques, and 1 order of magnitude faster than implicit-ALS fit with the Conjugate Gradient method.