arXiv AI July 24, 2026 By Amirhossein Nouranizadeh, Sarang Rajendra Patil, Alan John Varghese, Varsha Narayanan, Amit Chakraborty, Mengjia Xu

Multilevel Graph Wavelet Compressed Sensing with Scale-Aware Neural Recovery

Read the original on arXiv AI →

arXiv:2607. 20857v1 Announce Type: cross Abstract: Scientific machine learning methods such as neural operators and physics-informed neural networks have advanced engineering applications and inverse problems, but their training typically requires large volumes of simulated data.

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 AI.

benchmarks

arXiv Machine Learning

Aug 31

Beyond Pairwise Graphs in Science: Hypergraph Adaptive Wavelet Operators for Parametric PDEs

arXiv:2608.27883v1 Announce Type: new Abstract: Physical systems are often modeled by solution operators that map input fields, parameters, geometries, or past states to steady or future physical sta...

By Rajat Sarkar, Venkataramana Runkana, Souvik Chakraborty

llms benchmarks

arXiv Machine Learning

Jul 28

Does Graph Compression Preserve Signal Propagation?

arXiv:2607. 23338v1 Announce Type: new Abstract: Graph compression reduces the computational cost of graph learning, but its effect on signal propagation remains largely underexplored.

By Kawshik Banerjee, Khaled Mohammed Saifuddin

arXiv Machine Learning

Aug 20

GraphK: Variable-Size Graph Generation with Efficient Edge Construction

GraphK introduces an encoder‑sampler‑decoder framework that generates variable‑size graphs efficiently. It learns permutation‑invariant latent representations and samples new node embeddings via maximum likelihood, enabling both upscaling and downscaling of graph size. Edge construction uses KDTree‑based top‑k neighbor search in latent space, reducing computational cost while capturing graph properties.

By Resul Tugay, Eren Olu\u{g}, Elif Ak, Sule Gunduz Oguducu

rag diffusion

arXiv Machine Learning

Jul 15

Graph Regularized PCA

arXiv:2601. 10199v2 Announce Type: replace Abstract: Multivariate data often exhibit complex dependencies that violate the assumption of isotropic residual noise.

By Antonio Briola, Marwin Schmidt, Fabio Caccioli, Carlos Ros Perez, James Singleton, Christian Michler, Tomaso Aste

efficiency

arXiv AI

Jul 28

Plain Transformers are Surprisingly Powerful Link Predictors

arXiv:2602. 01553v3 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies.

By Quang Truong, Yu Song, Donald Loveland, Mingxuan Ju, Tong Zhao, Neil Shah, Jiliang Tang

llms rag benchmarks

arXiv AI

Sep 15

LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction

arXiv:2609.14977v1 Announce Type: cross Abstract: Finite element stress fields often exhibit strong local non-smoothness, where stress concentrations near holes, notches, and loading regions induce s...

By Chen Zeng, Qiao Wang

One email a morning, machine-written

Related stories

Beyond Pairwise Graphs in Science: Hypergraph Adaptive Wavelet Operators for Parametric PDEs

Does Graph Compression Preserve Signal Propagation?

GraphK: Variable-Size Graph Generation with Efficient Edge Construction

Graph Regularized PCA

Plain Transformers are Surprisingly Powerful Link Predictors

LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction