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

• URL: http://arxiv.org/abs/2608.00044v1
• Date: Fri, 24 Jul 2026 09:26:52 GMT
• Title: Retrieval-Based Cross-Domain Generalization in Optical Networks via Global Features
• Abstract summary: We propose a retrieval-based framework for crossdomain quality-of-transmission (QoT) estimation.<n>The proposed approach supports both zero-shot and few-shot adaptation without requiring model retraining.
• Score: 1.0709603403936399
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Cross-Domain Generalization in Optical Networks via Joint Contrastive and Classification Learning [1.0709603403936399]
  robustness of machine learning techniques remains an open challenge in optical networks.<n>Models trained on data from a specific topology or operational configuration often exhibit degraded performance when deployed in unseen networks.<n>We propose a representation learning technique aimed at capturing task-relevant relationships that remain stable across domains.
  arXiv  Detail & Related papers  (2026-07-22T19:02:45Z)
• Cross-Domain Transfer of Hyperspectral Foundation Models [2.0196229393131726]
  Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications.<n>We propose cross-domain transfer as an alternative, reusing HSI foundation models - originally trained in remote sensing - for proximal sensing applications.
  arXiv  Detail & Related papers  (2026-04-29T09:43:52Z)
• Cross-Domain Vessel Segmentation via Latent Similarity Mining and Iterative Co-Optimization [25.50657242704898]
  We propose a novel domain transfer framework that leverages latent vascular similarity across domains.<n>We develop an iterative refinement strategy where segmentation network and generative model undergo mutual optimization.<n> Experiments demonstrate that our framework achieves state-of-the-art performance in cross-domain retinal vessel segmentation.
  arXiv  Detail & Related papers  (2026-04-02T02:55:30Z)
• Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization [52.52838658375592]
  We propose a new paradigm, domain-connecting contrastive learning (DCCL) to enhance conceptual connectivity across domains.<n>On the data side, more aggressive data augmentation and cross-domain positive samples are introduced to improve intra-class connectivity.<n>The results verify that DCCL outperforms state-of-the-art baselines even without domain supervision.
  arXiv  Detail & Related papers  (2025-10-19T04:13:29Z)
• InvFussion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems [76.39776789410088]
  This work introduces a framework that combines the strong performance of supervised approaches and the flexibility of zero-shot methods.<n>A novel architectural design seamlessly integrates the degradation operator directly into the denoiser.<n> Experimental results on the FFHQ and ImageNet datasets demonstrate state-of-the-art posterior-sampling performance.
  arXiv  Detail & Related papers  (2025-04-02T12:40:57Z)
• Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters [69.24377241408851]
  Overfitting to the source domain is a common issue in gradient-based training of deep neural networks. We propose to base the selection on gradient-signal-to-noise ratio (GSNR) of network's parameters.
  arXiv  Detail & Related papers  (2023-10-11T10:21:34Z)
• Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation [7.953644697658355]
  Unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks. We introduce a novel approach to domain adaptation, leveraging the synergy of internal and external information within entropy-based adversarial networks. We devised a probability-sharing network that integrates diverse information for more effective segmentation.
  arXiv  Detail & Related papers  (2023-10-11T02:50:16Z)
• Variational Transfer Learning using Cross-Domain Latent Modulation [1.9662978733004601]
  We introduce a novel cross-domain latent modulation mechanism to a variational autoencoder framework so as to achieve effective transfer learning. Deep representations of the source and target domains are first extracted by a unified inference model and aligned by employing gradient reversal. The learned deep representations are then cross-modulated to the latent encoding of the alternative domain, where consistency constraints are also applied.
  arXiv  Detail & Related papers  (2022-05-31T03:47:08Z)
• Towards Principled Disentanglement for Domain Generalization [90.9891372499545]
  A fundamental challenge for machine learning models is generalizing to out-of-distribution (OOD) data. We first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG) Based on the transformation, we propose a primal-dual algorithm for joint representation disentanglement and domain generalization.
  arXiv  Detail & Related papers  (2021-11-27T07:36:32Z)
• Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection [50.29565896287595]
  We apply transfer learning to exploit common datasets for sarcasm detection. We propose a generalized latent optimization strategy that allows different losses to accommodate each other. In particular, we achieve 10.02% absolute performance gain over the previous state of the art on the iSarcasm dataset.
  arXiv  Detail & Related papers  (2021-04-19T13:07:52Z)
• Self-Challenging Improves Cross-Domain Generalization [81.99554996975372]
  Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. We introduce a simple training, Self-Challenging Representation (RSC), that significantly improves the generalization of CNN to the out-of-domain data. RSC iteratively challenges the dominant features activated on the training data, and forces the network to activate remaining features that correlates with labels.
  arXiv  Detail & Related papers  (2020-07-05T21:42:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.