← Back to all news
Hugging Face Trending Papers

Quantum Evolution Kernel for Node-Attributed Graphs

Read the original on Hugging Face Trending Papers →

The paper introduces a new method for embedding node‑attributed graphs onto neutral‑atom quantum computers, extending PASQAL’s quantum evolution kernel by adding a node‑level feature encoding using three‑level quantum states. A prototype demonstrates how this embedding can extract correlation‑based information for classification, specifically applied to digit recognition. Experiments, simulated with Pasqal’s Pulser library, show that the proposed approach outperforms traditional Jensen‑Shannon distance‑based methods by using the Wasserstein distance, achieving higher mean accuracy on the digit recognition task.

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 Hugging Face Trending Papers.

Related stories

arXiv Machine Learning
Oct 28

A quantum k-nearest neighbors implementation using magnitude-aware comparisons

The paper introduces a practical quantum encoding technique that allows Euclidean distance calculation between vectors with different L2 norms by appending a single component to each vector. This method is applied to the quantum k‑nearest neighbors (QKNN) problem, offering a simpler and more qubit‑efficient implementation than existing approaches. The authors provide an implementation and benchmark it against a recent Euclidean‑distance QKNN method, showing improved performance in simulations with realistic noise due to the reduced qubit count and more coherent circuits.

By Christopher Rector, Jiangwen Sun
benchmarks
More like this →
Hugging Face Trending Papers
Sep 10

Learning structural balance of graphs from quantum spectral features

The paper introduces a quantum method for extracting spectral features from the density of states (DOS) of a problem-dependent Hamiltonian, applied to signed graphs represented as Ising models. It demonstrates that standardized moments of the Ising DOS count signed closed walks, are switching‑invariant, and size‑free, enabling accurate learning of the frustration index with a mean error of 0.4 on 140,000 labeled graphs. The authors propose DOS‑QPE, a phase estimation technique that requires far fewer shots than traditional methods, and highlight potential applications in social network analysis, spin‑glass studies, correlation clustering, and protein‑interaction networks.

benchmarks
More like this →
arXiv Machine Learning
Jul 23

Edge-Local and Qubit-Efficient Quantum Graph Learning for the NISQ Era

arXiv:2602. 16018v2 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) are a powerful framework for learning representations from graph-structured data, but their direct implementation on near-term quantum hardware remains challenging due to circuit depth, multi-qubit interactions, and qubit scalability constraints.

By Armin Ahmadkhaniha, Jake Doliskani
More like this →