aiqbench analysis
This research tackles the critical issue of long-tailed distributions in semi-supervised learning by introducing Gaussian Bridge Consistency (GBC) to smooth semantic trajectories between uncertain predictions and reliable class prototypes. The proposed method effectively mitigates confirmation bias caused by noisy pseudo-labels while maintaining scalability on standard benchmarks like ImageNet-LT.
Geometric Regularization for Long-Tailed Semi-Supervised Learning via Gaussian Feature Bridges
arXiv:2608.20710v1 Announce Type: new Abstract: Real-world semi-supervised learning (SSL) often encounters significant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In this work, we introduce a novel framework, Gaussian Bridge Consistency (GBC), to address these challenges by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors. Our method maintains a dynamic Prototype Atlas that stores a diverse and evolving set of labeled and pseudo-labeled exemplars per class. For each unlabeled instance, GBC forms a class-conditional Gaussian Feature Bridge in the latent space, enabling the student model to traverse a smooth trajectory from uncertain predictions to reliable class prototypes. A bridge consistency loss is applied along this path to enforce alignment with a geometrically interpolated target distribution. Furthermore, we propose BridgeMix, a confidence-aware feature mixing strategy that interpolates both sample and anchor pairs to amplify cross-sample generalization. Extensive experiments on CIFAR10-LT and ImageNet-LT (USB benchmarks) validate the robustness and effectiveness of GBC under realistic long-tailed SSL settings, consistently improving long tail-class performance without sacrificing scalability.
Abstract:Real-world semi-supervised learning (SSL) often encounters significant challenges with long-tailed label distributions and noisy pseudo-labels, which hinder generalization and amplify confirmation bias. In this work, we introduce a novel framework, Gaussian Bridge Consistency (GBC), to address these challenges by constructing semantic interpolation paths between unlabeled samples and high-quality class anchors. Our method maintains a dynamic Prototype Atlas that stores a diverse and evolving set of labeled and pseudo-labeled exemplars per class. For each unlabeled instance, GBC forms a class-conditional Gaussian Feature Bridge in the latent space, enabling the student model to traverse a smooth trajectory from uncertain predictions to reliable class prototypes. A bridge consistency loss is applied along this path to enforce alignment with a geometrically interpolated target distribution. Furthermore, we propose BridgeMix, a confidence-aware feature mixing strategy that interpolates both sample and anchor pairs to amplify cross-sample generalization. Extensive experiments on CIFAR10-LT and ImageNet-LT (USB benchmarks) validate the robustness and effectiveness of GBC under realistic long-tailed SSL settings, consistently improving long tail-class performance without sacrificing scalability.
Accepted at the European Conference on Computer Vision (ECCV) 2026. Conference page: this https URL
Machine Learning (cs.LG)
arXiv:2608.20710 [cs.LG]
(or arXiv:2608.20710v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.20710 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 277 words
Related coverage
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026
JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning
arXiv · Aug 27, 2026
[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier
Latent Space · Sep 1, 2026
Learning Dynamics of Logits Debiasing for Long-Tailed Semi-Supervised Learning
arXiv · Sep 1, 2026