Recommending Changes on QoE Factors with Conditional Variational AutoEncoder

Increasing complexity in management of immense number of network elements and their dynamically changing environment necessitates machine learning based recommendation models to guide human experts in setting appropriate network configurations to sustain end-user Quality of Experience (QoE). In this paper, we present and demonstrate a generative Conditional Variational AutoEncoder (CVAE)-based technique to reconstruct realistic underlying QoE factors together with improvement suggestions in a video streaming use case. Based on our experiment setting consisting of a set of what-if scenarios, our approach pinpointed the potential required changes on the QoE factors to improve the estimated video Mean Opinion Scores (MOS).

[1]  S. Lipovetsky,et al.  Analysis of regression in game theory approach , 2001 .

[2]  Phuoc Tran-Gia,et al.  Predicting QoE in cellular networks using machine learning and in-smartphone measurements , 2017, 2017 Ninth International Conference on Quality of Multimedia Experience (QoMEX).

[3]  Kevin Liu,et al.  Conditional Variational Autoencoder for Neural Machine Translation , 2018, ArXiv.

[4]  Pasquale Lops,et al.  Content-based Recommender Systems: State of the Art and Trends , 2011, Recommender Systems Handbook.

[5]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[6]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[7]  Joshua Zhexue Huang,et al.  Generative neural network based spectrum sharing using linear sum assignment problems , 2019, China Communications.

[8]  O. J. Dunn.  Multiple Comparisons Using Rank Sums , 1964 .

[9]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[10]  James She,et al.  Collaborative Variational Autoencoder for Recommender Systems , 2017, KDD.

[11]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[12]  John Riedl,et al.  GroupLens: an open architecture for collaborative filtering of netnews , 1994, CSCW '94.

[13]  Iadh Ounis,et al.  A Hybrid Conditional Variational Autoencoder Model for Personalised Top-n Recommendation , 2020, ICTIR.

[14]  Zhengfang Duanmu,et al.  A Quality-of-Experience Database for Adaptive Video Streaming , 2018, IEEE Transactions on Broadcasting.

[15]  Sebastian Möller,et al.  QoE beyond the MOS: an in-depth look at QoE via better metrics and their relation to MOS , 2016, Quality and User Experience.

[16]  Junhao Wen,et al.  Recommender Systems Based on Generative Adversarial Networks: A Problem-Driven Perspective , 2020, Inf. Sci..