導讀:深入學習任何一門學科,都離不開對前沿知識的瞭解。對於推薦系統學習者來說,一年一度的RecSys大會就是了解學術界與工業界研究熱點的最佳平臺。鑑於此,在這篇文章中,我們把過往的RecSys論文整理成一個清單,列出了大家學習推薦系統必看的10篇RecSys論文。
下邊這5篇是根據ACM數字圖書館中的閱讀量整理出來的。在已發表的925篇論文中,這五篇論文是閱讀量最高的。這五篇論文約佔所有RecSys會議論文引用的12%!
· Performance of recommender algorithms on top-n recommendation tasks — 2010, by Paolo Cremonesi, Yehuda Koren, Roberto Turrin
· Trust-aware recommender systems — 2007, by Paolo Massa, Paolo Avesani
· A matrix factorization technique with trust propagation for recommendation in social networks — 2010, by Mohsen Jamali, Martin Ester
· Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering — 2010, by Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, Nuria Oliver
· Hidden factors and hidden topics: understanding rating dimensions with review text — 2013, by Julian McAuley, Jure Leskovec
自從2009年以來,每一年的ACM RecSys大會還會爲當年作出較大貢獻的論文進行頒獎,接下來的5篇論文在近5年內被評爲了“最佳論文”。
· Modeling the Assimilation-Contrast Effects in Online Product Rating Systems: Debiasing and Recommendations — 2017, by X. Zhang, J. Zhao, J.C.S. Lui
· Local Item-Item Models for Top-N Recommendation — 2016, by E. Christakopoulou and G. Karypis;
· Context-Aware Event Recommendation in Event-based Social Networks— 2015, by A. Macedo, L. Marinho and R. Santos
· Beyond Clicks: Dwell Time for Personalization — 2014, by X. Yi, L. Hong, E. Zhong, N. Nan Liu and S. Rajan
· A Fast Parallel SGD for Matrix Factorization in Shared Memory Systems— 2013, by Y. Zhuang, W. Chin, Y. Juan and C. Lin (Best Paper)