Koffka Khan

Department of Computing and Information Technology, The University of the West Indies, St Augustine, Trinidad and Tobago, W.I.

This paper presents a framework with a taxonomy for multi-task learning in the context of Dynamic Adaptive Streaming over HTTP (DASH). DASH is a widely used technology for video streaming, and multi-task learning has emerged as a promising approach to enhance the performance and user experience of DASH systems by jointly optimizing multiple related tasks. The framework provides a structured approach to design, train, and evaluate multi-task learning models in DASH, while the taxonomy categorizes the key components and approaches within the framework. The taxonomy includes task types, multitask learning approaches, input features, and training strategies. Task types encompass video quality adaptation, buffer management, bandwidth estimation, content pre-fetching, and resource allocation, representing the specific tasks involved in DASH. Multi-task learning approaches encompass methodologies such as shared representation learning, task-specific layers, multi-head architectures, knowledge distillation, and reinforcement learning, offering flexibility in model design and optimization. Input features cover video characteristics, network conditions, device capabilities, and user preferences, providing the necessary information for informed decision-making across tasks. Training strategies include joint training, alternate training, hierarchical training, task weighting, and task balancing, determining how the multi-task learning model is trained and optimized. By following the presented framework and taxonomy, researchers and practitioners can systematically approach the design, training, and evaluation of multi-task learning models in DASH. The framework enables the development of efficient and adaptive video streaming systems by leveraging the interdependencies among tasks. The taxonomy helps organize the components and approaches within the framework, aiding in a better understanding of the various aspects of multi-task learning in the DASH context. Overall, this framework and taxonomy provide a valuable resource for advancing the field of multitask learning in the dynamic and complex domain of video streaming over HTTP.

multi-task, learning, DASH, framework, video, quality, optimization, streaming

1) Antaris, S., Rafailidis, D., & Girdzijauskas, S. (2020, December). EGAD: Evolving graph representation learning with selfattention and knowledge distillation for live video streaming events. In 2020 IEEE International Conference on Big Data (Big Data) (pp. 1455-1464). IEEE.

2) Barbalau, A., Ionescu, R. T., Georgescu, M. I., Dueholm, J., Ramachandra, B., Nasrollahi, K., ... & Shah, M. (2023). Ssmtl++: Revisiting self-supervised multi-task learning for video anomaly detection. Computer Vision and Image Understanding, 229, 103656.

3) Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8), 1798-1828.

4) Bruneau-Queyreix, J., Lacaud, M., & Négru, D. (2017, October). A Hybrid P2P/Multi-Server Quality-Adaptive LiveStreaming Solution Enhancing End-User's QoE. In Proceedings of the 25th ACM international conference on Multimedia (pp. 1261- 1262).

5) Chang, Z., Zhou, X., Wang, Z., Li, H., & Zhang, X. (2019, April). Edge-assisted adaptive video streaming with deep learning in mobile edge networks. In 2019 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 1-6). IEEE.

6) Chen, X., Proietti, R., Liu, C. Y., & Yoo, S. B. (2021). A multi-task-learning-based transfer deep reinforcement learning design for autonomic optical networks. IEEE Journal on Selected Areas in Communications, 39(9), 2878-2889.

7) Doshi, K., & Yilmaz, Y. (2022). Multi-task learning for video surveillance with limited data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 3889-3899).

8) Elgendy, I. A., Zhang, W. Z., He, H., Gupta, B. B., & Abd El-Latif, A. A. (2021). Joint computation offloading and task caching for multi-user and multi-task MEC systems: reinforcement learning-based algorithms. Wireless Networks, 27(3), 2023-2038.

9) Hussein, A., & Hajj, H. (2022). Domain adaptation with representation learning and nonlinear relation for time series. ACM Transactions on Internet of Things, 3(2), 1-26.

10) Jiang, Z., Zhang, X., Huang, W., Chen, H., Xu, Y., Hwang, J. N., ... & Sun, J. (2019). A hierarchical buffer management approach to rate adaptation for 360-degree video streaming. IEEE Transactions on Vehicular Technology, 69(2), 21572170.

11) Khan, K., & Goodridge, W. (2018). Bandwidth Estimation Techniques for Relative'Fair'Sharing in DASH. International Journal of Advanced Networking and Applications, 9(6), 3607-3615.

12) Khan, K., & Goodridge, W. (2018). Future DASH applications: A survey. International Journal of Advanced Networking and Applications, 10(2), 3758-3764.

13) Khan, K., & Goodridge, W. (2018). QoE in DASH. International Journal of Advanced Networking and Applications, 9(4), 3515- 3522.

14) Khan, K., & Goodridge, W. Markov Decision Processes for bitrate harmony in adaptive video streaming. In 2017 Future Technologies Conference (FTC), Vancouver, Canada, unpublished.

15) Koffka, K., & Wayne, G. (2018). A DASH Survey: the ON-OFF Traffic Problem and Contemporary Solutions. Computer Sciences and Telecommunications, (1), 3-20.

16) Kua, J., Armitage, G., & Branch, P. (2017). A survey of rate adaptation techniques for dynamic adaptive streaming over HTTP. IEEE Communications Surveys & Tutorials, 19(3), 1842-1866.

17) Li, J., Tian, Y., Huang, T., & Gao, W. (2010). Probabilistic multi-task learning for visual saliency estimation in video. International journal of computer vision, 90, 150-165.

18) Li, L., Shi, D., Hou, R., Chen, R., Lin, B., & Pan, M. (2020). Energy-efficient proactive caching for adaptive video streaming via data-driven optimization. IEEE Internet of Things Journal, 7(6), 5549-5561.

19) Liu, Z., Tian, J., Cai, Q., Zhao, X., Gao, J., Liu, S., ... & Gai, K. (2023, April). Multi-Task Recommendations with Reinforcement Learning. In Proceedings of the ACM Web Conference 2023 (pp. 1273-1282).

20) Long, L., Huang, F., Yin, Y., & Xu, Y. (2022). Multi-task learning for collaborative filtering. International Journal of Machine Learning and Cybernetics, 1-14.

21) Mao, H., Netravali, R., & Alizadeh, M. (2017, August). Neural adaptive video streaming with pensieve. In Proceedings of the conference of the ACM special interest group on data communication (pp. 197-210).

22) Tang, H., Liu, J., Zhao, M., & Gong, X. (2020, September). Progressive layered extraction (ple): A novel multi-task learning (mtl) model for personalized recommendations. In Proceedings of the 14th ACM Conference on Recommender Systems (pp. 269-278).

23) Uzakgider, T., Cetinkaya, C., & Sayit, M. (2015). Learning-based approach for layered adaptive video streaming over SDN. Computer Networks, 92, 357-368.

24) Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., & Van Gool, L. (2021). Multi-task learning for dense prediction tasks: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(7), 3614-3633.

25) Wallingford, M., Li, H., Achille, A., Ravichandran, A., Fowlkes, C., Bhotika, R., & Soatto, S. (2022). Task adaptive parameter sharing for multi-task learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7561-7570).

26) Zhang, Y., & Yang, Q. (2021). A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12), 5586-5609.

27) Zhang, Y., & Yang, Q. (2021). A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering, 34(12), 5586-5609.

VOLUME 06 ISSUE 06 JUNE 2023

There is an Open Access article, distributed under the term of the Creative Commons Attribution – Non Commercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/), which permits remixing, adapting and building upon the work for non-commercial use, provided the original work is properly cited.