Retrieval-Based Cross-Domain Generalization in Optical Networks via Global Features

2026/07/24 by Ali Al Housseini, Carlos Natalino, Paolo Monti +1
Engineering · Computer Science · #eess.SP #cs.CV #cs.IR #cs.LG #cs.NI

paper · pdf

5 Pages, 2 Figures. Accepted and presented at the 26th International Conference on Transparent Optical Networks (ICTON 2026), Prague, Czech Republic, 12-16 July 2026

arxiv created 2026/07/24 · arxiv updated 2026/08/04

Abstract

We propose a retrieval-based framework for crossdomain quality-of-transmission (QoT) estimation that leverages transferable feature representations while avoiding reliance on source-domain-specific decision boundaries. The proposed approach supports both zero-shot and few-shot adaptation without requiring model retraining. Experimental results on cross-domain QoT datasets demonstrate improved generalization performance compared with conventional machine learning baselines and recent contrastive learning approaches, highlighting the potential of retrieval-based inference for robust optical network automation.

Citations

• Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning
• Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning