Advanced Graph Neural Networks

Derniers papiers

• Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation

  Jiangwen Dong, Bo Li, Wanyu Lin · 7 mai 2026

  LLM-empowered multi-agent systems offer new potential to accelerate scientific discovery by generating novel research ideas. However, existing methods typically coordinate agents through temporary texts, such as drafts or chat logs; it is difficult to pinpoint the weaknesses in the generated ideas a…

• Unsat Core Prediction through Polarity-Aware Representation Learning over Clause-Literal Hypergraphs

  Zhenchao Sun, Shuai Ma, Ping Lu, Chongyang Tao · 7 mai 2026

  Graph neural networks have been widely used in Boolean satisfiability (SAT) tasks to learn structural information from SAT formulas. The goal of these studies is to solve SAT instances or to enhance SAT solvers, including tasks such as unsat-core prediction. However, most existing approaches model a…

• Hypergraph Generation via Structured Stochastic Diffusion

  Christopher Nemeth · 7 mai 2026

  Hypergraphs model higher-order interactions, but realistic hypergraph generation remains difficult because incidence, hyperedge-size heterogeneity, and overlap structure are not faithfully captured by pairwise reductions. We propose \HEDGE, a generative model defined directly on relaxed incidence ma…

• Order-based Rehearsal Learning

  Yu-Xuan Tao, Tian-Zuo Wang, Zhi-Hua Zhou · 7 mai 2026

  When a machine learning (ML) model forecasts an undesired event, one often seeks a decision to avoid it, known as the avoiding undesired future (AUF) problem. Many rehearsal learning methods have been proposed for AUF, but they rely on an underlying graph structure; learning such a graph from observ…

• HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily

  Xinyi Li, Ming Li, Lu Bai, Lixin Cui, Feilong Cao, Ke Lv, Yunliang Jiang, Pietro Li\`o · 7 mai 2026

  Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate messages along metapaths or meta-relations primarily based on featur…

• Unifying Dynamical Systems and Graph Theory to Mechanistically Understand Computation in Neural Networks

  Jatin Sharma, Dan F. M Goodman, Danyal Akarca · 7 mai 2026

  Understanding how biological and artificial neural networks implement computation from connectivity is a central problem in neuroscience and machine learning. In neural systems, structural and functional connectivity are known to diverge, motivating approaches that move beyond direct connections alo…

• Conceptors for Semantic Steering

  Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao, Miranda Muqing Miao, Sunny Rai, Lyle Ungar, Sharath Chandra Guntuku, Neville Ryant, Jo\~ao Sedoc · 7 mai 2026

  Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than selecting a single steering direction, we use conceptors: soft projection matrices estimated from …

• Entropic Riemannian Neural Optimal Transport

  Alessandro Micheli, Silvia Sapora, Anthea Monod, Samir Bhatt · 7 mai 2026

  Many machine learning problems involve data supported on curved spaces such as spheres, rotation groups, hyperbolic spaces, and general Riemannian manifolds, where Euclidean geometry can distort distances, averages, and the resulting optimal transport (OT) problem. Existing manifold OT methods have …

• Quantile-Free Uncertainty Quantification in Graph Neural Networks

  Soyoung park, Hwanjun Song, Sungsu Lim · 7 mai 2026

  Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge. In graph settings, message passing often relies on strong assumptions such as exchangeability, which are rarely satisfied in practice. Moreover, achieving reliable U…

• Bridging Input Feature Spaces Towards Graph Foundation Models

  Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua, Bruno Ribeiro, Carola-Bibiane Sch\"onlieb · 7 mai 2026

  Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and dimensionality. This misalignment prevents graph models from generalizing across datasets, limiting their use as foundatio…

• Beyond Rigid Geometries: The Spline-Pullback Metric for Universal Diffeomorphic SPD Representation Learning

  Tushar Das, Subrata Dutta, Sarmistha Neogy, Koushlendra Kumar Singh · 7 mai 2026

  The integration of Symmetric Positive Definite (SPD) matrices into deep learning has historically relied on fixed algebraic Riemannian metrics. Analogous to hand-crafted features in classical machine learning, these static formulations impose rigid geometries limiting network expressivity and adapta…

• Stable Multimodal Graph Unlearning via Feature-Dimension Aware Quantile Selection

  Jingjing Zhou, Yongshuai Yang, Qing Qing, Ziqi Xu, Xikun Zhang, Renqiang Luo, Ivan Lee, Feng Xia · 6 mai 2026

  Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that existing unlearning strategies tend to apply uniform parameter selection and editing across all graph neural network (GNN) layers, which is especially h…

• SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering

  Jiujiu Chen, Yazheng Liu, Sihong Xie, Hui Xiong · 6 mai 2026

  Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they often suffer from a risk compensation effect, where incorrect steps are offset by later correct ones, assigning high rewar…

• SCGNN: Semantic Consistency enhanced Graph Neural Network Guided by Granular-ball Computing

  Genhao Tian, Taihua Xu, Shuyin Xia, Qinghua Zhang, Jie Yang, Jianjun Chen · 6 mai 2026

  Capturing semantic consistency among nodes is crucial for effective graph representation learning. Existing approaches typically rely on $k$-nearest neighbors ($k$NN) or other node-level full search algorithms (FSA) to mine semantic relationships via exhaustive pairwise similarity computation, which…

• Hallucination Detection in LLMs with Topological Divergence on Attention Graphs

  Alexandra Bazarova, Aleksandr Yugay, Andrey Shulga, Alina Ermilova, Andrei Volodichev, Konstantin Polev, Julia Belikova, Rauf Parchiev, Dmitry Simakov, Maxim Savchenko, Andrey Savchenko, Serguei Barannikov, Alexey Zaytsev · 6 mai 2026

  Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, which leverages a topological divergence metric to quantify the structural properties of graphs i…

• Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding

  Zhongjian Zhang, Yue Yu, Mengmei Zhang, Junping Du, Xiao Wang, Chuan Shi · 6 mai 2026

  The remarkable success of large language models (LLMs) has motivated researchers to adapt them as universal predictors for various graph tasks. As a widely recognized paradigm, Graph-Tokenizing LLMs (GTokenLLMs) compress complex graph data into graph tokens and treat them as prefix tokens for queryi…

• Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items

  Junting Wang, Chenghuan Guo, Jiao Yang, Yanhui Guo, Hari Sundaram, Yan Gao · 6 mai 2026

  We study the problem of inferring substitutable and complementary items, which underpins applications such as alternative and follow-up purchase suggestions. Existing approaches typically learn from behavior-derived item-item associations using GNNs or leverage item content alone. However, these met…

• GRIFDIR: Graph Resolution-Invariant FEM Diffusion Models in Function Spaces over Irregular Domains

  James Rowbottom, Elizabeth L. Baker, Nick Huang, Ben Adcock, Carola-Bibiane Sch\"onlieb, Alexander Denker · 6 mai 2026

  Score-based diffusion models in infinite-dimensional function spaces provide a mathematically principled framework for modelling function-valued data, offering key advantages such as resolution invariance and the ability to handle irregular discretisations. However, practical implementations have st…

• SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

  Tianshi Zheng, Rui Wang, Xiyun Li, Yangqiu Song, Tianqing Fang · 6 mai 2026

  Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking ta…

• Adaptive Negative Scheduling for Graph Contrastive Learning

  Adnan Ali, Jinlong Li, Syed Muhammad Israr, Ali Kashif Bashir · 6 mai 2026

  Graph contrastive learning (GCL) has become a central paradigm for self-supervised representation learning in computational intelligence, with applications spanning recommendation, anomaly detection, and personalization. A key limitation of existing methods is their reliance on static negative sampl…

• Position: How can Graphs Help Large Language Models?

  Xiyuan Wang, Yi Hu, Yanbo Wang, Chuan Shi, Muhan Zhang · 6 mai 2026

  With the rapid advancement of large language models (LLMs), classic graph learning tasks have greatly benefited from LLMs, including improved encoding of textual features, more efficient construction of graphs from text, and enhanced reasoning over knowledge graphs. In this paper, we ask a complemen…

• Most ReLU Networks Admit Identifiable Parameters

  Moritz Grillo, Guido Mont\'ufar · 6 mai 2026

  We study the realization map of deep ReLU networks, focusing on when a function determines its parameters up to scaling and permutation. To analyze hidden redundancies beyond these standard symmetries, we introduce a framework based on weighted polyhedral complexes. Our main result shows that for ev…

• Networked Information Aggregation for Binary Classification

  MohammadHossein Bateni, Zahra Hadizadeh, MohammadTaghi Hajiaghayi, Mahdi JafariRaviz, Shayan Taherijam · 5 mai 2026

  We study networked binary classification on a directed acyclic graph (DAG) where each agent observes only a subset of the feature columns of a shared dataset. Agents act sequentially along the DAG: each receives prediction columns from its parents (if any), augments its local features with these col…

• GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data

  Gleb Bazhenov, Oleg Platonov, Liudmila Prokhorenkova · 5 mai 2026

  Although data that can be naturally represented as graphs is widespread in real-world applications across diverse industries, popular graph ML benchmarks for node property prediction only cover a surprisingly narrow set of data domains, and graph neural networks (GNNs) are often evaluated on just a …

• Fine-Grained Graph Generation through Latent Mixture Scheduling

  Nidhi Vakil, Hadi Amiri · 5 mai 2026

  Structure aware graph generation aims to generate graphs that satisfy given topological properties. It has applications in domains such as drug discovery, social network modeling, and knowledge graph construction. Unlike existing methods that only provide coarse control over graph properties, we int…