(c) depositphotos.com

9th International Conference on Machine Learning for Networking (MLN'2026)


Paris, France, December 1-3, 2026

Keynote: Yassine Hadjadj-Aoul, Professor at University of Rennes, France


Title: Towards Autonomous 6G Networks: From Predictive Orchestration to SLA-Aware Intelligence


Abstract

Future 6G networks are expected to operate autonomously across increasingly complex, heterogeneous and multi-domain environments. While artificial intelligence offers new opportunities to achieve zero-touch network management, existing orchestration approaches remain largely reactive. Two major challenges persist: anticipating network dynamics across administrative domains and adapting embedded intelligence to meet diverse service requirements. In this talk, we explore these challenges through two complementary research contributions. First, we introduce a distributed, predictive network orchestration framework in which agents anticipate future network states and coordinate resource management across multiple domains. By combining Latent Ordinary Differential Equations (Latent ODEs) with attention mechanisms, the framework enables secure, context-aware network state prediction to support proactive resource scaling decisions. Second, we investigate how intelligence can be embedded directly into Virtual Network Function Forwarding Graphs (VNF-FGs), transforming conventional service chains into AI-native, SLA-aware service chains. Leveraging a meta-learning approach (MetaRNN), the proposed solution enables the rapid generation and deployment of AI profiles tailored to service-specific requirements in terms of accuracy, energy consumption and latency. Together, these contributions outline a vision for end-to-end AI-native network management, where orchestration mechanisms not only anticipate evolving network conditions but also adapt the intelligence deployed within the network itself. This perspective represents a step towards proactive, adaptive and autonomous 6G networks.


Biography

Yassine Hadjadj-Aoul is a Full Professor at the University of Rennes, France, where he heads the ESIR’s school computer science department since 2022. He is affiliated with the INRIA Ermine team-project and the IRISA Laboratory, which he joined in 2009 when he was hired as an Associate Professor at the University of Rennes. After completing his Ph.D. from the University of Versailles, he further developed his research experience as a postdoctoral researcher at the University of Lille 1 and as a Marie Curie Fellow under the EU FP6 EIF program at University College Dublin (UCD), Ireland. A Senior Member of the IEEE and recipient of multiple best paper awards, he has supervised numerous Ph.D. students and postdoctoral researchers and has played a key role in several high-impact projects in the area of Next Generation Networks. He actively contributes to scientific committees and editorial boards, and co-leads both the “AI for Infrastructure” initiative within the French GDR and the SmartNet research action between INRIA and Nokia Bell Labs, which focuses on AI-driven intelligent network management. His primary research interests include Congestion Control, Network Slicing, and more generally on QoS/QoE provisioning across the Edge–Cloud continuum.