Advanced Graph Neural Networks

Derniers papiers

• The physics of AI weather models

  George Craig, Tobias Selz, Matthias Beylich, Kirsten I. Tempest · 25 mai 2026

  Could it be that AI weather models are solving physical equations, although they may not be the equations used by conventional NWP models? We compute correlations of forecast skill and Centered Kernel Alignment, providing evidence that different AI weather models represent the atmosphere in similar …

• Weisfeiler-Leman Is Incomplete on Simple Spectrum Graphs, so Canonicalize Them

  Snir Hordan, Nadav Dym, Tim Seppelt · 25 mai 2026

  Graphs with a simple spectrum admit cubic-time isomorphism testing, yet we prove that for every natural number $k$, the $k$-Weisfeiler-Leman ($k$-WL) test cannot distinguish all non-isomorphic graphs with a simple spectrum. As the WL hierarchy upper-bounds the distinguishing power of widely-used Gra…

• PLACE: Prompt Learning for Attributed Community Search in Large Graphs

  Shuheng Fang, Kangfei Zhao, Rener Zhang, Yu Rong, Jeffrey Xu Yu · 25 mai 2026

  In this paper, we propose PLACE (Prompt Learning for Attributed Community Search), an innovative graph prompt learning framework for ACS. Enlightened by prompt-tuning in Natural Language Processing (NLP), where learnable prompt tokens are inserted to contextualize NLP queries, PLACE integrates struc…

• Sparse In-Network Learning via Shortest-Path Backpropagation and Finite-Rate Gating

  Mohammad Reza Deylam Salehi · 25 mai 2026

  In-network learning (INL) trains distributed neural modules by exchanging latent activations and backpropagated errors over a communication graph. This letter proposes Dijkstra-pruned INL (D-INL), which removes non-tree links by retaining a capacity-aware shortest-path tree rooted at the fusion node…

• Topological Signal Processing: An Application-Oriented Tutorial

  Flavia Petruso, Maria Giulia Preti, Dimitri Van De Ville · 25 mai 2026

  Many modern datasets are large and carry complex structural relationships. Graph-based methods have traditionally been used to represent networked data, modeling individual elements as nodes and pairwise interactions as edges. Furthermore, Graph Signal Processing (GSP) has been developed to analyze …

• Convex Compositional Reasoning Models

  Meir Roketlishvili, Semyon Semenov, Maksim Bobrin, Viktor Kovalchuk, Albert Baichorov, Abduragim Shtanchaev, Fakhri Karray, Dmitry V. Dylov, Martin Tak\'a\v{c}, Arip Asadulaev · 25 mai 2026

  Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show that a key bottleneck in compositional reasoning is not composition itself, but the non-convex geometry of the learned e…

• Expressive Power of Deep Homomorphism Networks over Relational Databases

  Moritz Sch\"onherr, Balder ten Cate, Maurice Funk, Benny Kimelfeld, Carsten Lutz, Arie Soeteman · 25 mai 2026

  The expressive limitations of message-passing Graph Neural Networks (GNNs) have motivated a wide range of more powerful graph learning architectures. We advocate Deep Homomorphism Networks (DHNs) as a model particularly well-suited for learning over relational databases, due to their close connectio…

• What Linear Probes Miss: Multi-View Probing for Weight-Space Learning

  Eunwoo Heo, Kyeongkook Seo, Jaejun Yoo · 25 mai 2026

  The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentation or metadata. While weight-space learning offers a pathway to identify and analyze these models directly from their parameters, processing full-sca…

• SeedER: Seed-and-Expand Retrieval from Knowledge Graphs

  Hamed Shirzad, Frederik Wenkel, Dominique Beaini, Danica J. Sutherland, Emmanuel Noutahi · 25 mai 2026

  Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense embedding methods struggle with multi-hop compositional queries. Existing agent-based graph exploration approaches, whi…

• SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

  Shuofei Qiao, Yunxiang Wei, Jiazheng Fan, Bin Wu, Busheng Zhang, Mengru Wang, Yuqi Zhu, Ningyu Zhang, Keyan Ding, Qiang Zhang, Huajun Chen · 25 mai 2026

  The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on super…

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

  Weishuo Ma, Yanbo Wang, Xiyuan Wang, Lei Zou, Muhan Zhang · 25 mai 2026

  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). However, current GFMs are challenged by the extreme heterogeneity of graph data, where each graph can …

• Relevant Walk Search for Explaining Graph Neural Networks

  Ping Xiong, Thomas Schnake, Michael Gastegger, Gr\'egoire Montavon, Klaus-Robert M\"uller, Shinichi Nakajima · 25 mai 2026

  Graph Neural Networks (GNNs) have become important machine learning tools for graph analysis, and its explainability is crucial for safety, fairness, and robustness. Layer-wise relevance propagation for GNNs (GNN-LRP) evaluates the relevance of \emph{walks} to reveal important information flows in t…

• S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning

  Dai Shi, Luke Thompson, Linhan Luo, Lequan Lin, Andi Han, Junbin Gao, Jos\'e Miguel Hern\'andez Lobato · 25 mai 2026

  Message-passing neural networks (MPNNs) often suffer from an information bottleneck when capturing long-range dependencies, leading to the oversquashing (OSQ) phenomenon. Alongside spatial connectivity enrichment (e.g., rewiring), recent studies have shown that spectral filtering can yield strong lo…

• Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints

  Hoyun Choi, Junghyo Jo, Deok-Sun Lee · 25 mai 2026

  How network structure determines function is a fundamental question, and it can be investigated by graph ensembles with precisely controlled structural properties. Canonical approaches, formulated as exponential random graph models (ERGMs), enforce constraints only in expectation, allowing individua…

• Self-supervised Adversarial Purification for Graph Neural Networks

  Woohyun Lee, Hogun Park · 25 mai 2026

  Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicting objectives within a single classifier. To overcome this limitation, we propos…

• Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems

  Ling Wang, Xin Liu, Songnan Liu, Jianan Wang, Cheng Cheng, Yihan Zhu, Enyu Li, Yu Xiao, Jiangyong Xie, Duogong Yan, Jiangyi Chen · 22 mai 2026

  Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphRAG, NL2SQL) lack the semantic grounding and auditable execution required for these complex environments. We introduce HE…

• Gaussian Sheaf Neural Networks

  Andr\'e Ribeiro, Ana Luiza Ten\'orio, Tiago da Silva, Diego Mesquita · 21 mai 2026

  Graph Neural Networks (GNNs) have become the de facto standard for learning on relational data. While traditional GNNs' message passing is well suited for vector-valued node features, there are cases in which node features are better represented by probability distributions than real vectors. Concre…

• Spectral structural distortion reveals redundant neurons in neural networks

  Yongyu Wang · 21 mai 2026

  Overparameterized neural networks often contain many removable neurons, yet what makes a neuron redundant remains poorly understood. Existing pruning criteria commonly rely on local quantities such as weight magnitude, activation strength, or gradient sensitivity, but these measures provide limited …

• From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach

  Nura Aljaafari, Danilo S. Carvalho, Andre Freitas · 21 mai 2026

  Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how they relate, or when two findings provide evidence for the sa…

• Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

  Yi Huang, Qingyun Sun, Jia Li, Xingcheng Fu, Jianxin Li · 21 mai 2026

  Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational Deep Learning (RDL) addresses this problem by modeling RDBs as graphs and applying graph neural networks (GNNs) for end-to-end learning. However, th…

• Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification

  Brown Zaz, Mar Gonz\`alez I Catal\`a, Ferran Hernandez Caralt, Moshe Eliasof, Pietro Li\`o · 21 mai 2026

  In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on architectural innovation. In this paper, we revisit an orthogonal axis: the training objective. We start from a simple ob…

• Instance Discrimination for Link Prediction

  Valentin Cuzin-Rambaud (SyCoSMA, DM2L, LIRIS, UCBL), Mathieu Lefort (LIRIS, SyCoSMA, IRISA, MALT, UR), R\'emy Cazabet (DM2L, LIRIS, UCBL, IXXI) · 21 mai 2026

  Recently, instance discrimination models have emerged as a major solution for self-supervised learning. Having already demonstrated its effectiveness in the image domain, instance discrimination learning is now proving equally convincing in the graph domain, in particular for node classification. Ho…

• Prism: Structural Symmetry Scanning via Duality-Constrained Laplacian Projection

  Jiatong Xie · 21 mai 2026

  We introduce \textbf{Prism}, a framework for structural symmetry diagnosis in complex networks. Given a graph Laplacian $L$ and a duality operator $P$ (a symmetric involution), Prism computes the \emph{duality defect} $\delta(L,P) = \|LP - PL\|_F / \|L\|_F$ -- a scalar measuring how far the network …

• GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval

  Peter Fernandes, Ria Kanjilal · 21 mai 2026

  Graph-based Retrieval Augmented Generation (GraphRAG) extends retrieval-augmented generation to support structured reasoning over complex corpora, but its reliability under resource-constrained, privacy-sensitive deployments remains unclear. In healthcare, where Electronic Health Record (EHR) data i…

• Graph Navier Stokes Networks

  Zexing Zhao, Guangsi Shi, Yu Gong, Tianyu Wang, Shirui Pan, Hongye Cheng, Yuxiao Li · 21 mai 2026

  Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the oversmoothing problem, where node features become indisting…