LibRec 精选：近期15篇推荐系统论文
LibRec 精选
一场来之不易的遇见，不知憔悴了前世多少的繁芜。愿这世上终有一人，是你奋不顾身的理由。
编者导读：本次论文更新15篇，包括多篇的序列推荐模型、基于会话的综述文章；基于树/图神经网络的推荐模型；基于增强学习的推荐模型等新工作，都值得大家重点关注。社交媒体上有趣的内容不太多，但可观察到欧洲有很多的推荐系统线下讨论会，而且很多地方已经举办了很多次了。相对地，国内在推荐系统方面的线下讨论还不活跃。
附：近期实在是太忙了，内容更新得稍慢了一些，望大家见谅。
【论文集】WSDM 2019的论文集：http://www.wsdm-conference.org/2019/acm-proceedings.php，包括不少推荐系统方面的论文。
1. Model-Based Reinforcement Learning for Whole-Chain Recommendations
Xiangyu Zhao, Long Xia, Jiliang Tang, Dawei Yin, Yihong Zhao
https://arxiv.org/abs/1902.03987v1
Therefore, in this paper, we study the recommendation problem with multiple (consecutive) scenarios, i.e., whole-chain recommendations. We propose a multi-agent reinforcement learning based approach (DeepChain), which can capture the sequential correlation among different scenarios and jointly optimize multiple recommendation strategies. In this paper, we introduce model-based reinforcement learning techniques to reduce the training data requirement and execute more accurate strategy updates.
2. Interest-Related Item Similarity Model Based on Multimodal Data for Top-N Recommendation
Mohsen Guizani, Jie Guo, XiaoJiang Du, Junmei Lv, Bin Song
https://arxiv.org/abs/1902.05566v1
In this paper, we propose an end-to-end Multimodal Interest-Related Item Similarity model (Multimodal IRIS) to provide recommendations based on multimodal data source. Specifically, the Multimodal IRIS model consists of three modules, i.e., multimodal feature learning module, the Interest-Related Network (IRN) module and item similarity recommendation module. At last, the multimodal data feature learning, IRN and item similarity recommendation modules are unified into an integrated system to achieve performance enhancements and to accommodate the addition or absence of different modal data.
3. A Survey on Session-based Recommender Systems
Yan Wang, Shoujin Wang, Longbing Cao
https://arxiv.org/abs/1902.04864v1
Session-based recommender systems (SBRS) are an emerging topic in the recommendation domain and have attracted much attention from both academia and industry in recent years. Most of existing works only work on modelling the general item-level dependency for recommendation tasks. In this paper, we provide a systematic and comprehensive review on SBRS and create a hierarchical and in-depth understanding of a variety of challenges in SBRS.
4. Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems
Lixin Zou, Long Xia, Zhuoye Ding, Jiaxing Song, Weidong Liu, Dawei Yin
https://arxiv.org/abs/1902.05570v1
In such an interactive manner, a good recommender system should pay more attention to user stickiness, which is far beyond classical instant metrics, and typically measured by {\bf long-term user engagement}. Directly optimizing the long-term user engagement is a non-trivial problem, as the learning target is usually not available for conventional supervised learning methods. To address these issues, in this work, we introduce a reinforcement learning framework --- FeedRec to optimize the long-term user engagement.
5. Collaborative Similarity Embedding for Recommender Systems
Yi-Hsuan Yang, Ming-Feng Tsai, Chuan-Ju Wang, Chih-Ming Chen
https://arxiv.org/abs/1902.06188v1
We present collaborative similarity embedding (CSE), a unified framework that exploits comprehensive collaborative relations available in a user-item bipartite graph for representation learning and recommendation. In the proposed framework, we differentiate two types of proximity relations: direct proximity and k-th order neighborhood proximity. Moreover, for improving scalability and flexibility, we propose a sampling technique that is specifically designed to capture the two types of proximity relations.
6. NAIRS: A Neural Attentive Interpretable Recommendation System
Qiang Qu, Jialie Shen, Min Yang, Baocheng Li, Shuai Yu, Yongbo Wang
https://arxiv.org/abs/1902.07494v1
In this paper, we develop a neural attentive interpretable recommendation system, named NAIRS. Based on the user profiles obtained by the self-attention network, NAIRS offers personalized high-quality recommendation. This demo application with the implementation of NAIRS enables users to interact with a recommendation system, and it persistently collects training data to improve the system.
7. Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
Han Li, Xiang Li, Jie He, Ziru Xu, Pengye Zhang, Kun Gai, Han Zhu, Daqing Chang, Jian Xu
https://arxiv.org/abs/1902.07565v1
Tree-based Deep Model (TDM) for recommendation \cite{zhu2018learning} greatly improves recommendation accuracy using tree index. In tree-based recommendation methods, the quality of both the tree index and the trained user preference prediction model determines the recommendation accuracy for the most part. In our proposed joint optimization framework, the learning of index and user preference prediction model are carried out under a unified performance measure.
8. Graph Neural Networks for Social Recommendation
Dawei Yin, Eric Zhao, Jiliang Tang, Yuan He, Qing Li, Yao Ma, Wenqi Fan
https://arxiv.org/abs/1902.07243v1
In recent years, Graph Neural Networks (GNNs), which can naturally integrate node information and topological structure, have been demonstrated to be powerful in learning on graph data. These advantages of GNNs provide great potential to advance social recommendation since data in social recommender systems can be represented as user-user social graph and user-item graph; and learning latent factors of users and items is the key. For example, the user-item graph encodes both interactions and their associated opinions; social relations have heterogeneous strengths; users involve in two graphs (e.g., the user-user social graph and the user-item graph).
9. User-based collaborative filtering approach for content recommendation in OpenCourseWare platforms
Nikola Tomasevic, Dejan Paunovic, Sanja Vranes
https://arxiv.org/abs/1902.10376v1
A content recommender system or a recommendation system represents a subclass of information filtering systems which seeks to predict the user preferences, i.e. through the content-based filtering, or user-based collaborative filtering (CF). The proposed approach also envisages a hybrid recommendation system as a combination of user-based and content-based approaches in order to provide a holistic and efficient solution for content recommendation.
10. Session-based Social Recommendation via Dynamic Graph Attention Networks
Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang, Jian Tang
https://arxiv.org/abs/1902.09362v1
In that context, recommending relevant information to users becomes critical for viability. However, recommendation in online communities is a challenging problem: 1) users' interests are dynamic, and 2) users are influenced by their friends. We model dynamic user behaviors with a recurrent neural network, and context-dependent social influence with a graph-attention neural network, which dynamically infers the influencers based on users' current interests.
11. B-Script: Transcript-based B-roll Video Editing with Recommendations
Bernd Huber, Hijung Valentina Shin, Bryan Russell, Oliver Wang, Gautham J. Mysore
https://arxiv.org/abs/1902.11216v1
In video production, inserting B-roll is a widely used technique to enrich the story and make a video more engaging. We present B-Script, a system that supports B-roll video editing via interactive transcripts. Users found it easier and were faster to insert B-roll using the transcript-based interface, and they created more engaging videos when recommendations were provided.
12. Multi-Scale Quasi-RNN for Next Item Recommendation
Chaoyue He, Yong Liu, Qingyu Guo, Chunyan Miao
https://arxiv.org/abs/1902.09849v1
This paper proposes a new neural architecture, multi-scale Quasi-RNN for next item Recommendation (QR-Rec) task. Our model provides the best of both worlds by exploiting multi-scale convolutional features as the compositional gating functions of a recurrent cell. The key idea aims to capture the recurrent relations between different kinds of local features, which has never been studied previously in the context of recommendation.
13. Representation Learning for Recommender Systems with Application to the Scientific Literature
Robin Brochier
https://arxiv.org/abs/1902.11058v1
The scientific literature is a large information network linking various actors (laboratories, companies, institutions, etc.). In this article, I present my first thesis works in partnership with an industrial company, Digital Scientific Research Technology. Finally, the interplay between textual and graph data in text-attributed heterogeneous networks remains an open research direction.
14. Degenerate Feedback Loops in Recommender Systems
Ray Jiang, Silvia Chiappa, Tor Lattimore, Andras Agyorgy, Pushmeet Kohli
https://arxiv.org/abs/1902.10730v1
Machine learning is used extensively in recommender systems deployed in products. The decisions made by these systems can influence user beliefs and preferences which in turn affect the feedback the learning system receives - thus creating a feedback loop. In this paper, we provide a novel theoretical analysis that examines both the role of user dynamics and the behavior of recommender systems, disentangling the echo chamber from the filter bubble effect.
15. MIRA: A Computational Neuro-Based Cognitive Architecture Applied to Movie Recommender Systems
Mariana B. Santos, Amanda M. Lima, Lucas A. Silva, Felipe S. Vargas, Guilherme A. Wachs-Lopes, Paulo S. Rodrigues
https://arxiv.org/abs/1902.09291v1
Nevertheless, for decades the scientific community has proposed computational models that try to simulate their parts, specific applications, or their behavior in different situations. The most complete model in this line is undoubtedly the LIDA model, proposed by Stan Franklin with the aim of serving as a generic computational architecture for several applications. The present project is inspired by the LIDA model to apply it to the process of movie recommendation, the model called MIRA (Movie Intelligent Recommender Agent) presented percentages of precision similar to a traditional model when submitted to the same assay conditions.
相关内容
微信扫码咨询专知VIP会员