arXiv:2510.27474v1 Announce Type: new 
Abstract: Graphs are central to modeling complex systems in domains such as social networks, molecular chemistry, and neuroscience. While Graph Neural Networks, particularly Graph Convolutional Networks, have become standard tools for graph learning, they remain constrained by reliance on fixed structures and susceptibility to over-smoothing. We propose the Spectral Preservation Network, a new framework for graph representation learning that generates reduced graphs serving as faithful proxies of the original, enabling downstream tasks such as community detection, influence propagation, and information diffusion at a reduced computational cost. The Spectral Preservation Network introduces two key components: the Joint Graph Evolution layer and the Spectral Concordance loss. The former jointly transforms both the graph topology and the node feature matrix, allowing the structure and attributes to evolve adaptively across layers and overcoming the rigidity of static neighborhood aggregation. The latter regularizes these transformations by enforcing consistency in both the spectral properties of the graph and the feature vectors of the nodes. We evaluate the effectiveness of Spectral Preservation Network on node-level sparsification by analyzing well-established metrics and benchmarking against state-of-the-art methods. The experimental results demonstrate the superior performance and clear advantages of our approach.

تم تقديم إطار جديد يسمى شبكة الحفاظ الطيفي لتحسين تعلم تمثيل الرسوم البيانية. تعالج هذه الابتكار القيود المفروضة على الشبكات العصبية الرسومية التقليدية، التي غالبًا ما تواجه صعوبة مع الهياكل الثابتة ومشكلات الإفراط في التنعيم. من خلال تحسين كيفية نمذجة الرسوم البيانية، يمكن أن يكون لهذا التطور تأثير كبير في مجالات مثل الشبكات الاجتماعية والكيمياء الجزيئية، مما يسهل تحليل الأنظمة المعقدة.

Se ha presentado un nuevo marco llamado Spectral Preservation Network para mejorar el aprendizaje de la representación de grafos. Esta innovación aborda las limitaciones de las Redes Neuronales de Grafos tradicionales, que a menudo luchan con estructuras fijas y problemas de sobre-suavizado. Al mejorar la forma en que se modelan los grafos, este desarrollo podría tener un impacto significativo en campos como las redes sociales y la química molecular, facilitando el análisis de sistemas complejos.

Un nouveau cadre appelé le Spectral Preservation Network a été introduit pour améliorer l'apprentissage de la représentation des graphes. Cette innovation répond aux limites des réseaux de neurones graphiques traditionnels, qui ont souvent du mal avec des structures fixes et des problèmes de sur-lissage. En améliorant la modélisation des graphes, ce développement pourrait avoir un impact significatif dans des domaines tels que les réseaux sociaux et la chimie moléculaire, facilitant ainsi l'analyse de systèmes complexes.

A new framework called the Spectral Preservation Network has been introduced to enhance graph representation learning. This innovation addresses the limitations of traditional Graph Neural Networks, which often struggle with fixed structures and over-smoothing issues. By improving how graphs are modeled, this development could significantly impact fields like social networks and molecular chemistry, making it easier to analyze complex systems.

Spectral Neural Graph Sparsification

arXiv:2601.08621v1 Announce Type: new 
Abstract: Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains such as e-commerce, social networks, and scientific citations, remains underexplored. Unlike plain text corpora, graphs encode rich topological signals that connect related entities and can serve as valuable priors for retrieval, enabling more targeted search and improved reasoning efficiency. Yet, effectively leveraging such structure poses unique challenges, including the difficulty of generating graph-expressive queries and ensuring reliable retrieval that balances structural and semantic relevance. To address this gap, we introduce GraphSearch, the first framework that extends search-augmented reasoning to graph learning, enabling zero-shot graph learning without task-specific fine-tuning. GraphSearch combines a Graph-aware Query Planner, which disentangles search space (e.g., 1-hop, multi-hop, or global neighbors) from semantic queries, with a Graph-aware Retriever, which constructs candidate sets based on topology and ranks them using a hybrid scoring function. We further instantiate two traversal modes: GraphSearch-R, which recursively expands neighborhoods hop by hop, and GraphSearch-F, which flexibly retrieves across local and global neighborhoods without hop constraints. Extensive experiments across diverse benchmarks show that GraphSearch achieves competitive or even superior performance compared to supervised graph learning methods, setting state-of-the-art results in zero-shot node classification and link prediction. These findings position GraphSearch as a flexible and generalizable paradigm for agentic reasoning over graphs.

تم تقديم إطار عمل جديد يسمى GraphSearch، الذي يوسع التفكير المعزز بالبحث إلى تعلم الرسوم البيانية، مما يمكّن التعلم من الرسوم البيانية بدون ضبط محدد للمهمة. هذا التقدم يعالج التحديات المتعلقة بالتعامل مع البيانات الهيكلية في الرسوم البيانية، والتي تزداد شيوعًا في مجالات متنوعة مثل التجارة الإلكترونية والشبكات الاجتماعية.

Se ha introducido un nuevo marco llamado GraphSearch, que extiende el razonamiento aumentado por búsqueda al aprendizaje de grafos, permitiendo el aprendizaje de grafos sin ajuste específico a la tarea. Este avance aborda los desafíos de operar con datos estructurados en grafos, que son cada vez más prevalentes en diversos dominios como el comercio electrónico y las redes sociales.

Un nouveau cadre nommé GraphSearch a été introduit, étendant le raisonnement augmenté par la recherche à l'apprentissage des graphes, permettant un apprentissage de graphes sans coupure spécifique à la tâche. Cette avancée répond aux défis liés à l'exploitation des données structurées en graphes, de plus en plus présentes dans divers domaines tels que le commerce électronique et les réseaux sociaux.

A new framework named GraphSearch has been introduced, extending search-augmented reasoning to graph learning, enabling zero-shot graph learning without the need for task-specific fine-tuning. This advancement addresses the challenges of operating on graph-structured data, which is increasingly prevalent in various domains such as e-commerce and social networks.

GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning

arXiv:2503.22252v2 Announce Type: replace-cross 
Abstract: Graph neural networks, recently introduced into the field of fluid flow surrogate modeling, have been successfully applied to model the temporal evolution of various fluid flow systems. Existing applications, however, are mostly restricted to cases where the domain is time-invariant. The present work extends the application of graph neural network-based modeling to fluid flow around structures rotating with respect to a certain axis. Specifically, we propose to apply a graph neural network-based surrogate model with part of the mesh/graph co-rotating with the structure and part of the mesh/graph static. A single layer of interface cells are constructed at the interface between the two parts and are allowed to distort and adapt, which helps in circumventing the difficulty of interpolating information encoded by the neural network at every graph neural network layer. Dedicated reconstruction and re-projection schemes are designed to counter the error caused by the distortion and connectivity change of the interface cells. The effectiveness of our proposed framework is examined on two test cases: (i) fluid flow around a 2D oscillating airfoil, and (ii) fluid flow past a 3D rotating cube. Our results show that the model achieves stable rollout predictions over hundreds or even a thousand time steps. We further demonstrate that one could enforce accurate, error-bounded prediction results by incorporating the measurements from sparse pressure sensors. In addition to the accurate flow field predictions, the lift and drag force predictions closely match with the computational fluid dynamics calculations, highlighting the potential of the framework for modeling fluid flow around rotating structures, and paving the path towards a graph neural network-based surrogate model for more complex scenarios like flow around marine propellers.

تقدم دراسة جديدة شبكة عصبية هيبرغرافية قابلة للتكيف مع الشبكات، مصممة لنمذجة تدفق السوائل غير المستقر حول الهياكل المتذبذبة والدورانية، مما يوسع تطبيق الشبكات العصبية الرسومية في ديناميات السوائل. يسمح هذا النهج المبتكر لجزء من الشبكة بالدوران مع الهيكل بينما يحتفظ بجزء ثابت، مما يسهل تحسين استيفاء المعلومات عبر طبقات الشبكة.

Un nuevo estudio presenta una red neuronal hipergráfica adaptativa a mallas, diseñada para modelar el flujo de fluidos no estacionario alrededor de estructuras oscilantes y rotativas, ampliando la aplicación de redes neuronales gráficas en la dinámica de fluidos. Este enfoque innovador permite que parte de la malla co-rotee con la estructura mientras mantiene una porción estática, facilitando una mejor interpolación de información a través de las capas de la red.

Une nouvelle étude présente un réseau de neurones hypergraphe adaptatif à maillage, conçu pour modéliser l'écoulement de fluide instable autour de structures oscillantes et tournantes, étendant l'application des réseaux de neurones graphiques en dynamique des fluides. Cette approche innovante permet à une partie du maillage de co-rotationner avec la structure tout en maintenant une portion statique, facilitant ainsi une meilleure interpolation des informations à travers les couches du réseau.

A new study introduces a mesh-adaptive hypergraph neural network designed to model unsteady fluid flow around oscillating and rotating structures, extending the application of graph neural networks in fluid dynamics. This innovative approach allows part of the mesh to co-rotate with the structure while maintaining a static portion, facilitating better information interpolation across the network layers.

Spectral Neural Graph Sparsification

Was this article worth reading? Share it

LucidQuery AI

Airparser

Graphite Note

The Visualizer

Sourcely

Octofy

Ready to build your own newsroom?