Zero-touch network management is essential for beyond 5G and 6G systems, requiring full automation through a closed loop of data collection, predictive capabilities, and decision-making for network control. Recent approaches have combined prediction and decision-making using a single deep-learning model trained on past data with custom loss functions for optimization. We introduce a metric meta-learning model that minimizes human intervention during model design, enhances the explainability and transferability of models, and outperforms custom losses in various experiments and practical scenarios.

About Alan Collet

Alan Collet is currently a Ph.D. student in the Network Data Science research group at IMDEA Networks Institute, Madrid, Spain. He received his B.S. and M.S. degrees in Telecommunications Engineering from the University of Bordeaux, France. He also received a second M.S. degree in computer science from the Illinois Institute of Technology of Chicago, USA. He is mainly working on neural network optimization for real-world networking problems.

Este evento se impartirá en inglés