analiza aiqbench
This research tackles the critical challenge of domain shift in optical networks by introducing a joint contrastive and classification learning framework. The method simultaneously optimizes representation stability for unseen topologies while maintaining task-specific accuracy, enabling rapid adaptation with minimal fine-tuning data. By proving robustness across heterogeneous network domains using lightpath quality estimation as a test case, the work advances machine learning techniques essential for scalable optical infrastructure management.
Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning
arXiv:2607.20666v1 Announce Type: cross 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.
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.
6 pages, 2 figures. Accepted and presented at the 30th International Conference on Optical Network Design and Modelling (ONDM 2026), Munich, Germany, 12-15 May 2026
Networking and Internet Architecture (cs.NI); Machine Learning (cs.LG)
arXiv:2607.20666 [cs.NI]
(or arXiv:2607.20666v1 [cs.NI] for this version)
https://doi.org/10.48550/arXiv.2607.20666 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 177 cuvinte
Subiecte conexe
Introducing Clef: our open-source decision models, and new RL fine-tuning platform
Cloudflare Blog · 1 oct. 2026
Atrial Fibrillation Detection with Arbitrary Leads via a Codebook-Based Reconstruction-Classification Framework
arXiv · 20 aug. 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026