arXiv Machine Learning August 28, 2026 By Antonia van Betteray, Jonathan Klees, Miriam Sch\"afers, Matthias Rottmann

Algebraic Multigrid Acceleration for Efficient Label Spreading

Read the original on arXiv Machine Learning →

The paper introduces AMELS, an Algebraic Multigrid Acceleration framework for label spreading that speeds up the construction of neighborhood graphs and replaces the standard random walk iteration with an algebraic multigrid solver. By leveraging the multilevel nature of multigrid, AMELS can propagate label information across graphs of any size in a single cycle, achieving substantial runtime reductions and improved robustness to hyperparameter choices. The method enables efficient and accurate label spreading on large‑scale image datasets even when only a few labeled samples are available.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 3

RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections

arXiv:2605. 26854v2 Announce Type: replace Abstract: The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis.

By Yali Fink, Ido Ben-Yair, Lars Ruthotto, Eran Treister

efficiency

arXiv Machine Learning

Aug 27

JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning

JEPAMatch introduces a new semi‑supervised learning framework that replaces traditional output‑thresholding with explicit geometric shaping of latent representations. By combining the FlexMatch loss with a latent‑space regularization inspired by LeJEPA, the method encourages isotropic Gaussian structure in the embedding space, mitigating class imbalance and noisy pseudo‑labels. Experiments on CIFAR‑100, STL‑10, and Tiny‑ImageNet show consistent performance gains and faster convergence compared to existing FixMatch‑based baselines.

By Ali Aghababaei-Harandi, Aude Sportisse, Massih-Reza Amini

rag diffusion computer-vision benchmarks

arXiv Machine Learning

Jun 5

Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling

arXiv:2606. 05927v1 Announce Type: new Abstract: The complex imbalanced label distribution poses a crucial challenge to multi-label classification, as most classifiers are biased towards the majority class and high-frequent labels.

By Bin Liu, Jun Wu, Haoyu Peng, Ao Zhou, Jin Wang, QiaoSong Chen, Grigorios Tsoumakas

benchmarks

arXiv Machine Learning

Jun 26

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

arXiv:2606. 26973v1 Announce Type: cross Abstract: Open-set semi-supervised learning aims to leverage unlabeled data that may contain out-of-distribution outliers while maintaining performance on in-distribution classes.

By Jiahe Chen, Qian Shao, Qiyuan Chen, Jiaying He, Jintai Chen, Jian Wu, Hongxia Xu

benchmarks

arXiv AI

Jun 11

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

arXiv:2510. 04567v3 Announce Type: replace-cross Abstract: Graph Neural Networks (GNNs) are powerful tools for processing relational data but often struggle to generalize to unseen graphs, giving rise to the development of Graph Foundational Models (GFMs).

By Weishuo Ma, Yanbo Wang, Xiyuan Wang, Lei Zou, Muhan Zhang

llms

arXiv Machine Learning

Jun 11

Accurate and Resource-Efficient Federated Continual Learning

arXiv:2606. 11480v1 Announce Type: new Abstract: Federated continual learning (FCL) must learn from distributed task streams under limited resources, such as communication, computation, memory, and label availability.

By Jebacyril Arockiaraj, Dhruv Parikh, Jayashree Adivarahan, Rajgopal Kannan, Viktor Prasanna

One email a morning, machine-written

Related stories

RAPNet: Accelerating Algebraic Multigrid with Learned Sparse Corrections

JEPAMatch: Geometric Representation Shaping for Semi-Supervised Learning

Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning

Accurate and Resource-Efficient Federated Continual Learning