EGAD: Evolving Graph Representation Learning with Self-Attention and Knowledge Distillation for Live Video Streaming Events

Stefanos Antaris, Dimitrios Rafailidis, Sarunas Girdzijauskas

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

In this study, we present a dynamic graph representation learning model on weighted graphs to accurately predict the network capacity of connections between viewers in a live video streaming event. We propose EGAD, a neural network architecture to capture the graph evolution by introducing a self-attention mechanism on the weights between consecutive graph convolutional networks. In addition, we account for the fact that neural architectures require a huge amount of parameters to train, thus increasing the online inference latency and negatively influencing the user experience in a live video streaming event. To address the problem of the high online inference of a vast number of parameters, we propose a knowledge distillation strategy. In particular, we design a distillation loss function, aiming to first pretrain a teacher model on offline data, and then transfer the knowledge from the teacher to a smaller student model with less parameters. We evaluate our proposed model on the link prediction task on three real-world datasets, generated by live video streaming events. The events lasted 80 minutes and each viewer exploited the distribution solution provided by the company Hive Streaming AB. The experiments demonstrate the effectiveness of the proposed model in terms of link prediction accuracy and number of required parameters, when evaluated against state-of-the-art approaches. In addition, we study the distillation performance of the proposed model in terms of compression ratio for different distillation strategies, where we show that the proposed model can achieve a compression ratio up to 15:100, preserving high link prediction accuracy. For reproduction purposes, our evaluation datasets and implementation are publicly available at https://stefanosantaris.github.io/EGAD.
Original languageEnglish
Title of host publication2020 IEEE International Conference on Big Data (Big Data)
PublisherIEEE Xplore
Pages1455-1464
Number of pages10
ISBN (Print)978-1-7281-6252-2
DOIs
Publication statusPublished - 13 Dec 2020
Event2020 IEEE International Conference on Big Data (Big Data) - Atlanta, GA, USA
Duration: 10 Dec 202013 Dec 2020

Conference

Conference2020 IEEE International Conference on Big Data (Big Data)
Period10/12/2013/12/20

Keywords

  • Training
  • Adaptation models
  • Streaming media
  • Predictive models
  • Data models
  • User experience
  • Task analysis

Cite this