2nd GNNet Workshop

Graph Neural Networking Workshop
Co-located with ACM CoNEXT 2023
December 8, 2023


09:00 – 09:10 Welcome Pere Barlet-Ros and Pedro Casas
09:10 – 10:00 Keynote I: Medical Digital Twin with Graph Representation Learning.
Pietro Liò, University of Cambridge, UK
10:00 – 10:40 Session I: GNN for traffic compression
  • Atom: Neural Traffic Compression with Spatio-Temporal Graph Neural Networks

Paul Almasan (Telefónica Research); Krzysztof Rusek (AGH University of Science and Technology); Shihan Xiao, Xiang Shi, Xiangle Cheng (Network Technology Lab., Huawei Technologies Co., Ltd.); Albert Cabellos, Pere Barlet-Ros (Barcelona Neural Networking Center, Universitat Politècnica de Catalunya)

  • Topological Network Traffic Compression

Guillermo Bernárdez (Universitat Politecnica de Catalunya); Lev Telyatnikov (Sapienza Università di Roma); Eduard Alarcon (Universitat Politecnica de Catalunya); Albert Cabellos-Aparicio, Pere Barlet-Ros (Barcelona Neural Networking Center, Universitat Politècnica de Catalunya, Spain); Pietro Liò (University of Cambridge)

10:40 – 11:00 Coffee break
11:00 – 11:40 Session II: GNN for network modeling
  • Predicting Latency Quantiles using Network Calculus-assisted GNNs

Max Helm, Georg Carle (Technical University of Munich)

  • Active Few-shot Learning For RouteNet-Fermi

Xiaoyi FU, Menghan SHAO (HKUST); Songze Li (SEU); Liuqing YANG (HKUST)

11:40 – 12:30 Keynote II: Foundational + specialized models for network operations
Dario Rossi,
Huawei Paris Research Center, France
12:30 – 14:00 Lunch
14:00 – 15:30 GNNet challenge Award Ceremony
  • Introduction and awards announcement (Albert Cabellos and Carlos Güemes)
  • Winning Solution: m0b1us team

Authors: Cláudio Matheus Modesto, Andrey Silva, Silvia Lins, Rebecca Aben-Athar

  • Second team: BUPT_CMCC

Authors: Zicheng Wang, Yuanjie Duan, Danyang Chen, Lingqi Guo

  • Third team: LKN

Authors: Kaan Aykurt, Johannes Zerwas, Serkut Ayvasik, Maximilian Stephan

15:30 – 16:00 Coffee break
16:00 – 17:00 Session III: GNN for network security
  • Detecting Contextual Network Anomalies with Graph Neural Networks

Hamid Latif Martínez (Universitat Politècnica de Catalunya); José Suárez-Varela (Telefónica Research); Albert Cabellos-Aparicio, Pere Barlet-Ros (Universitat Politècnica de Catalunya)

  • Exploring Temporal GNN Embeddings for Darknet Traffic Analysis

Luca Gioacchini, Andrea Cavallo, Marco Mellia, Luca Vassio (Politecnico di Torino)

  • Optimizing Honeypot Placement Strategies with Graph Neural Networks for Enhanced Resilience via Cyber Deception

Mohamed Osman, Tamer Nadeem (Virginia Commonwealth University); Ahmed Hemida, Charles Kamhoua (DEVCOM Army Research Laboratory)

17:00 – 17:1 0 Closing