└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Must-read papers on GNN for communication networks 2 | Please, feel free to contribute to this list by making a pull request. 3 | 4 | ## Content 5 | 6 | 7 | 8 | 9 | 10 | 11 |
1-. Surveys and related articles
2-. Wired networks
3-. Wireless networks
4-. Job scheduling in data centers
5-. Explainability
12 | 13 | ## Surveys and related articles 14 | 15 | - **Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities.**
16 | IEEE Network, 2021. [[DOI](https://doi.org/10.1109/MNET.123.2100773)] [[ArXiv](https://arxiv.org/abs/2112.14792)]
17 | *J. Suárez-Varela, P. Almasan, M. Ferriol-Galmés, K. Rusek, F. Geyer, X. Cheng, X. Shi, S. Xiao, F. Scarselli, A. Cabellos-Aparicio, P. Barlet-Ros.* 18 | 19 | - **Graph-based Deep Learning for Communication Networks: A Survey.**
20 | Elsevier Computer Communications, 2021. [[DOI](https://doi.org/10.1016/j.comcom.2021.12.015)]
21 | *Jiang W.* 22 | 23 | - **Learning Combinatorial Optimization on Graphs: A Survey With Applications to Networking.**
24 | IEEE ACCESS, 2020. [[paper](https://arxiv.org/pdf/2005.11081.pdf)]
25 | N. Vesselinova, R. Steinert, D. Perez-Ramirez, M. Boman. 26 | 27 | - **IGNNITION: A framework for fast prototyping of Graph Neural Networks.**
28 | GNNSys workshop, 2021. [[paper](https://gnnsys.github.io/papers/GNNSys21_paper_4.pdf)]
29 | *D. Pujol-Perich, J. Suárez-Varela, M. Ferriol-Galmés, S. Xiao, B. Wu, A. Cabellos-Aparicio, P. Barlet-Ros.* 30 | 31 | ## Wired networks 32 | 33 | - **RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDN.**
34 | IEEE JSAC, 2020. [[paper](https://arxiv.org/pdf/1910.01508.pdf)]
35 | *K. Rusek, J. Suárez-Varela, P. Almasan, P. Barlet-Ros, A. Cabellos-Aparicio.* 36 | 37 | - **Learning and generating distributed routing protocols using graph-based deep learning.**
38 | ACM SIGCOMM BigDAMA workshop, 2018. [[paper](https://www.net.in.tum.de/fileadmin/bibtex/publications/papers/geyer2018bigdama.pdf)] [[code](https://github.com/BNN-UPC/ignnition/tree/main/examples/Graph_query_networks)]
39 | *F. Geyer, G. Carle.* 40 | 41 | - **Is machine learning ready for traffic engineering optimization?**
42 | IEEE International Conference on Network Protocols (ICNP), 2021. [[paper](https://arxiv.org/pdf/2109.01445.pdf)]
43 | *G. Bernrdez, J. Suárez-Varela, A. López, B. Wu, S. Xiao, X. Cheng, P. Barlet-Ros, and A. Cabellos-Aparicio.* 44 | 45 | - **DeepTMA: Predicting Effective Contention Models for Network Calculus using Graph Neural Networks.**
46 | IEEE INFOCOM, 2019. [[paper](https://www.net.in.tum.de/fileadmin/bibtex/publications/papers/geyer2019infocom.pdf)]
47 | *F. Geyer, S. Bondorf.* 48 | 49 | - **Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN.**
50 | ACM SOSR, 2019. [[paper](https://arxiv.org/pdf/1901.08113.pdf)] [[code](https://github.com/BNN-UPC/ignnition/tree/main/examples/Routenet)]
51 | *K. Rusek, J. Suárez-Varela, A. Mestres, P. Barlet-Ros, A. Cabellos-Aparicio.* 52 | 53 | - **Towards more realistic network models based on Graph Neural Networks.**
54 | ACM CoNEXT student workshop, 2019. [[paper](https://upcommons.upc.edu/bitstream/handle/2117/190294/paper_CoNEXT_postprint.pdf)] [[code](https://github.com/BNN-UPC/ignnition/tree/main/examples/Q-size)]
55 | *A. Badia-Sampera, J. Suárez-Varela, P. Almasan, K. Rusek, P. Barlet-Ros, A. Cabellos-Aparicio.* 56 | 57 | - **Deep Reinforcement Learning meets Graph Neural Networks: Exploring a routing optimization use case.**
58 | ArXiv preprint arXiv:1910.07421, 2019 [[paper](https://arxiv.org/pdf/1910.07421.pdf)]
59 | *P. Almasan, J. Suárez-Varela, A. Badia-Sampera, K. Rusek, P. Barlet-Ros, A. Cabellos-Aparicio.* 60 | 61 | - **A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding.**
62 | IEEE Transactions on Network and Service Management, 2019. [[paper](https://hal.inria.fr/hal-02427641/document)]
63 | *Q. T. A. Pham, Y. Hadjadj-Aoul, A. Outtagarts.* 64 | 65 | - **DeepMPLS: Fast Analysis of MPLS Configurations Using Deep Learning.**
66 | IFIP Networking, 2019. [[paper](https://www.net.in.tum.de/fileadmin/bibtex/publications/papers/geyer2019networking.pdf)]
67 | *F. Geyer, S. Schmid.* 68 | 69 | - **Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement.**
70 | IEEE Communications Letters, 2020. [[paper](https://ieeexplore.ieee.org/abstract/document/9201405)]
71 | *P Sun, J Lan, J Li, Z Guo, Y Hu.* 72 | 73 | - **GCLR: GNN-Based Cross Layer Optimization for Multipath TCP by Routing.**
74 | IEEE Access, 2020. [[doi](https://doi.org/10.1109/ACCESS.2020.2966045)]
75 | *H. Wang, Y. Wu, G. Min, W. Miao* 76 | 77 | - **Network Planning with Deep Reinforcement Learning.**
78 | ACM SIGCOMM, 2021. [[doi](https://dl.acm.org/doi/10.1145/3452296.3472902)]
79 | *H. Zhu, V. Gupta, S. S. Ahuja, Y. D. Tian, Y. Zhang, and X. Jin* 80 | 81 | 82 | ## Wireless networks 83 | 84 | - **Graph neural networks for scalable radio resource management: Architecture design and theoretical analysis.**
85 | IEEE JSAC, 2020. [[paper](https://arxiv.org/pdf/2007.07632.pdf)]
86 | *Y. Shen, Y. Shi, J. Zhang, K.B. Letaief.* 87 | 88 | - **Optimal wireless resource allocation with random edge graph neural networks.**
89 | IEEE Transactions on Signal Processing, 2020. [[paper](https://arxiv.org/pdf/1909.01865.pdf)]
90 | *M. Eisen, A. Ribeiro.* 91 | 92 | - **Relational Deep Reinforcement Learning for Routing in Wireless Networks.**
93 | arXiv preprint arXiv:2012.15700, 2020. [[paper](https://arxiv.org/pdf/2012.15700.pdf)]
94 | *V. Manfredi,, A. Wolfe, B. Wang, X. Zhang.* 95 | 96 | - **Unsupervised Learning for Asynchronous Resource Allocation in Ad-hoc Wireless Networks.**
97 | arXiv preprint arXiv:2011.02644, 2020. [[paper](https://arxiv.org/pdf/2011.02644.pdf)]
98 | *Z. Wang, M. Eisen, A. Ribeiro.* 99 | 100 | - **Graph Attention Spatial-Temporal Network with Collaborative Global-Local Learning for Citywide Mobile Traffic Prediction**
101 | IEEE Transactions on Mobile Computing, 2020. [[paper](https://ieeexplore.ieee.org/document/9184280)]
102 | *K. He, X. Chen, Q. Wu, S. Yu, Z. Zhou* 103 | 104 | - **Channel Estimation for Full-Duplex RIS-assisted HAPS Backhauling with Graph Attention Networks**
105 | IEEE International Conference on Communications, 2021. [[paper](https://ieeexplore.ieee.org/document/9500697)]
106 | *K. Tekbıyık, G. K. Kurt, C. Huang, A. R. Ekti, H. Yanikomeroglu.* 107 | 108 | 109 | ## Job scheduling in data centers 110 | 111 | - **Learning scheduling algorithms for data processing clusters.**
112 | ACM SIGCOMM, 2019. [[paper](https://arxiv.org/pdf/1810.01963.pdf)]
113 | *H. Mao, M. Schwarzkopf, S. B. Venkatakrishnan, Z. Meng, M. Alizadeh.* 114 | 115 | - **DeepWeave: Accelerating Job Completion Time with Deep Reinforcement Learning-based Coflow**
116 | Scheduling. IJCAI, 2020. [[paper](https://www.ijcai.org/Proceedings/2020/0458.pdf)]
117 | *P. Sun, Z. Guo, J. Wang, J. Li, J. Lan, Y. Hu* 118 | 119 | ## Explainability 120 | 121 | - **Interpreting Deep Learning-Based Networking Systems.**
122 | ACM SIGCOMM, 2020. [[paper](https://arxiv.org/pdf/1910.03835.pdf)]
123 | *Z. Meng, M. Wang, J. Bai, M. Xu, H. Mao, H. Hu.* 124 | 125 | - **NetXplain: Real-time explainability of Graph Neural Networks applied to Computer Networks.**
126 | GNNSys workshop, 2021. [[paper](https://gnnsys.github.io/papers/GNNSys21_paper_7.pdf)]
127 | *D. Pujol-Perich, J. Suárez-Varela, S. Xiao, B. Wu, A. Cabellos-Aparicio, P. Barlet-Ros.* 128 | 129 | ## Other lists 130 | This list is intended to be short and keep only relevant references on different types of communication networks. You may refer to the following link for a more complete list with all the existing works in the field: 131 | 132 | GNN-Communication-Networks: https://github.com/jwwthu/GNN-Communication-Networks 133 | --------------------------------------------------------------------------------