Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning

2026-07-22

AI Summary

This work addresses the significant degradation in generalization performance of machine learning models when deployed across heterogeneous domains in optical networks, where varying topologies and operational configurations hinder adaptability. To tackle this challenge, the authors propose a representation learning framework that jointly integrates contrastive and classification learning, enabling the co-optimization of task-specific objectives and domain-invariant features within a unified latent space. This approach effectively captures relationships that are both task-relevant and invariant across domains. Notably, it is the first to combine contrastive and classification learning explicitly for cross-domain generalization in optical networks and supports few-shot fine-tuning. Evaluated on optical channel quality estimation, the method achieves superior cross-domain performance, substantially outperforming existing baselines with only a small number of labeled samples from the target domain.

Abstract

The robustness of machine learning techniques across heterogeneous network domains remains an open challenge in optical networks. Models trained on data from a specific topology or operational configuration often exhibit degraded performance when deployed in unseen networks. In this work, we address this challenge by proposing a representation learning technique aimed at capturing task-relevant relationships that remain stable across domains. The proposed technique is based on a novel joint contrastive and classification learning approach in which representation learning and task optimization are performed simultaneously, allowing both objectives to shape the latent space. Experimental results on a representative use case, namely, lightpath quality of transmission estimation, demonstrate the effectiveness of our approach compared to baseline approaches, and highlight its capacity for rapid adaptation, providing excellent performance even with limited fine-tuning.

Problem

• cross-domain generalization
• optical networks
• domain shift
• machine learning robustness
• heterogeneous networks

Innovation

• cross-domain generalization
• contrastive learning
• classification learning
• representation learning
• optical networks