arXiv Machine Learning June 5, 2026 By Minh Triet Pham, Ian Gallagher

The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

Read the original on arXiv Machine Learning →

arXiv:2605. 22346v2 Announce Type: replace-cross Abstract: Two of the most widely used methods for analysing graph data, Adjacency Spectral Embedding and Laplacian Spectral Embedding, often produce different results when applied to the same graph.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 12

Spectral Embeddings of Degree-$\alpha$ Laplacians in Random Dot Product Graphs

arXiv:2608. 10845v1 Announce Type: cross Abstract: Spectral clustering methods for network data are commonly based on a few matrix representations, such as the adjacency matrix and the symmetric Laplacian.

By John Park, Ning Hao

rag

Hugging Face Trending Papers

Jun 11

Understanding Truncated Positional Encodings for Graph Neural Networks

Positional encodings (PEs) enhance the power of graph neural networks (GNNs), both theoretically and empirically. Two of the most popular families of PEs - spectral (e.

arXiv Machine Learning

Jul 9

Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization

arXiv:2607. 07513v1 Announce Type: new Abstract: Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretical explanation.

By Adam M. Oberman

safety

arXiv Machine Learning

Aug 11

Sparse corruption in low-rank matrix inference: the PCA benchmark

arXiv:2511. 11927v2 Announce Type: replace-cross Abstract: Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations.

By Urte Adomaityte, Gabriele Sicuro, Pierpaolo Vivo

benchmarks safety

arXiv Machine Learning

Jun 2

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

arXiv:2410. 09737v2 Announce Type: replace Abstract: A popular way to improve the expressive power of graph neural networks (GNNs) is to use Laplacian eigenvectors as additional node features, since they can serve both as structural identifiers and global coordinates of nodes.

By Junru Zhou, Cai Zhou, Xiyuan Wang, Pan Li, Muhan Zhang

benchmarks

arXiv Machine Learning

Jun 11

Weighted Random Dot Product Graphs

arXiv:2505. 03649v4 Announce Type: replace-cross Abstract: Modeling of intricate relational patterns has become a cornerstone of contemporary statistical research and related data science fields.

By Bernardo Marenco, Paola Bermolen, Marcelo Fiori, Federico Larroca, Gonzalo Mateos

rag

Related stories

Spectral Embeddings of Degree-$\alpha$ Laplacians in Random Dot Product Graphs

Understanding Truncated Positional Encodings for Graph Neural Networks

Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization

Sparse corruption in low-rank matrix inference: the PCA benchmark

Towards Stable, Globally Expressive Graph Representations with Laplacian Eigenvectors

Weighted Random Dot Product Graphs