Advanced Graph Neural Networks

Derniers papiers

• MetaKE: Meta-learning Aligned Knowledge Editing via Bi-level Optimization

  Shuxin Liu, Ou Wu · 16 mars 2026

  Knowledge editing (KE) aims to precisely rectify specific knowledge in Large Language Models (LLMs) without disrupting general capabilities. State-of-the-art methods suffer from an open-loop control mismatch. We identify a critical "Semantic-Execution Disconnect": the semantic target is derived inde…

• Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs

  Xing Zi, Xinying Zhou, Jinghao Xiao, Catarina Moreira, Mukesh Prasad · 16 mars 2026

  While Large Language Models (LLMs) achieve expert-level performance on standard medical benchmarks through single-hop factual recall, they severely struggle with the complex, multi-hop diagnostic reasoning required in real-world clinical settings. A primary obstacle is "shortcut learning", where mod…

• Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?

  Nicolas Keriven · 16 mars 2026

  Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a non-informative representation, if the weights of the GNN are sufficiently bounded. This assumption is crucial: if, on the contrary, the weig…

• Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction

  Chenghan Wu, Zongmin Yu, Boai Sun, Liu Yang · 16 mars 2026

  In-context operator learning enables neural networks to infer solution operators from contextual examples without weight updates. While prior work has demonstrated the effectiveness of this paradigm in leveraging vast datasets, a systematic comparison against single-operator learning using identical…

• CCMamba: Topologically-Informed Selective State-Space Networks on Combinatorial Complexes for Higher-Order Graph Learning

  Jiawen Chen, Qi Shao, Mingtong Zhou, Duxin Chen, Wenwu Yu · 16 mars 2026

  Topological deep learning has emerged as a powerful paradigm for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. While combinatorial complexes (CCs) offer a unified topological foundation for the higher-order graph learnin…

• Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning

  Huidong Wu, Haojia Xiang, Jingtong Gao, Xiangyu Zhao, Dengsheng Wu, Jianping Li · 16 mars 2026

  Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity o…

• Lyapunov Stable Graph Neural Flow

  Haoyu Chu, Xiaotong Chen, Wei Zhou, Wenjun Cui, Kai Zhao, Shikui Wei, Qiyu Kang · 16 mars 2026

  Graph Neural Networks (GNNs) are highly vulnerable to adversarial perturbations in both topology and features, making the learning of robust representations a critical challenge. In this work, we bridge GNNs with control theory to introduce a novel defense framework grounded in integer- and fraction…

• Sampling and Uniqueness Sets in Graphon Signal Processing

  Alejandro Parada-Mayorga, Alejandro Ribeiro · 16 mars 2026

  In this work, we study the properties of sampling sets on families of large graphs by leveraging the theory of graphons and graph limits. To this end, we extend to graphon signals the notion of removable and uniqueness sets, which was developed originally for the analysis of signals on graphs. We st…

• No More DeLuLu: Physics-Inspired Kernel Networks for Geometrically-Grounded Neural Computation

  Taha Bouhsine · 16 mars 2026

  We introduce the yat-product, a kernel operator combining quadratic alignment with inverse-square proximity. We prove it is a Mercer kernel, analytic, Lipschitz on bounded domains, and self-regularizing, admitting a unique RKHS embedding. Neural Matter Networks (NMNs) use yat-product as the sole non…

• Invariant Graph Transformer for Out-of-Distribution Generalization

  Tianyin Liao, Ziwei Zhang, Yufei Sun, Chunyu Hu, Jianxin Li · 16 mars 2026

  Graph Transformers (GTs) have demonstrated great effectiveness across various graph analytical tasks. However, the existing GTs focus on training and testing graph data originated from the same distribution, but fail to generalize under distribution shifts. Graph invariant learning, aiming to captur…

• TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction

  Qianggang Ding, Haochen Shi, Luis Castej\'on Lozano, Miguel Conner, Juan Abia, Luis Gallego-Ledesma, Joshua Fellowes, Gerard Conangla Planes, Adam Elwood, Bang Liu · 16 mars 2026

  We present a Temporal Rule-Anchored Chain-of-Evidence (TRACE) on knowledge graphs for interpretable stock movement prediction that unifies symbolic relational priors, dynamic graph exploration, and LLM-guided decision making in a single end-to-end pipeline. The approach performs rule-guided multi-ho…

• On the Geometric Coherence of Global Aggregation in Federated Graph Neural Networks

  Chethana Prasad Kabgere, Shylaja SS · 16 mars 2026

  Federated Learning (FL) enables distributed training across multiple clients without centralized data sharing, while Graph Neural Networks (GNNs) model relational data through message passing. In federated GNN settings, client graphs often exhibit heterogeneous structural and propagation characteris…

• Uncovering Locally Low-dimensional Structure in Networks by Locally Optimal Spectral Embedding

  Hannah Sansford, Nick Whiteley, Patrick Rubin-Delanchy · 13 mars 2026

  Standard Adjacency Spectral Embedding (ASE) relies on a global low-rank assumption often incompatible with the sparse, transitive structure of real-world networks, causing local geometric features to be 'smeared'. To address this, we introduce Local Adjacency Spectral Embedding (LASE), which uncover…

• HOG-Diff: Higher-Order Guided Diffusion for Graph Generation

  Yiming Huang, Tolga Birdal · 13 mars 2026

  Graph generation is a critical yet challenging task, as empirical analyses require a deep understanding of complex, non-Euclidean structures. Diffusion models have recently made significant advances in graph generation, but these models are typically adapted from image generation frameworks and over…

• Graph Tokenization for Bridging Graphs and Transformers

  Zeyuan Guo, Enmao Diao, Cheng Yang, Chuan Shi · 13 mars 2026

  The success of large pretrained Transformers is closely tied to tokenizers, which convert raw input into discrete symbols. Extending these models to graph-structured data remains a significant challenge. In this work, we introduce a graph tokenization framework that generates sequential representati…

• KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation

  Qizhi Chen, Chao Qi, Yihong Huang, Muquan Li, Rongzheng Wang, Dongyang Zhang, Ke Qin, Shuang Liang · 13 mars 2026

  Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LLM) generations.However,this reliance on external data introduces new attack surfaces.Attackers can inject poisoned texts…

• Reversible Lifelong Model Editing via Semantic Routing-Based LoRA

  Haihua Luo, Xuming Ran, Tommi K\"arkk\"ainen, Zhonghua Chen, Jiangrong Shen, Qi Xu, Fengyu Cong · 13 mars 2026

  The dynamic evolution of real-world necessitates model editing within Large Language Models. While existing methods explore modular isolation or parameter-efficient strategies, they still suffer from semantic drift or knowledge forgetting due to continual updating. To address these challenges, we pr…

• Effective Resistance Rewiring: A Simple Topological Correction for Over-Squashing

  Bertran Miquel-Oliver, Manel Gil-Sorribes, Victor Guallar, Alexis Molina · 13 mars 2026

  Graph Neural Networks struggle to capture long-range dependencies due to over-squashing, where information from exponentially growing neighborhoods must pass through a small number of structural bottlenecks. While recent rewiring methods attempt to alleviate this limitation, many rely on local crite…

• Graph-GRPO: Training Graph Flow Models with Reinforcement Learning

  Baoheng Zhu, Deyu Bo, Delvin Ce Zhang, Xiao Wang · 12 mars 2026

  Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, \aka, graph flow model (GFM), has emerged due to its superior performance and flexible sampling. However, effectively aligning GFMs with complex human pref…

• Evaluating Progress in Graph Foundation Models: A Comprehensive Benchmark and New Insights

  Xingtong Yu, Shenghua Ye, Ruijuan Liang, Chang Zhou, Hong Cheng, Xinming Zhang, Yuan Fang · 12 mars 2026

  Graph foundation models (GFM) aim to acquire transferable knowledge by pre-training on diverse graphs, which can be adapted to various downstream tasks. However, domain shift in graphs is inherently two-dimensional: graphs differ not only in what they describe (topic domains) but also in how they ar…

• A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification

  Yichi Zhu, Kan Ling, Xu Liu, Hengrun Zhang, Huiqun Yu, Guisheng Fan · 12 mars 2026

  Medication errors pose a significant threat to patient safety, making pharmacist verification (PV) a critical, yet heavily burdened, final safeguard. The direct application of Large Language Models (LLMs) to this zero-tolerance domain is untenable due to their inherent factual unreliability, lack of…

• Causal Concept Graphs in LLM Latent Space for Stepwise Reasoning

  Md Muntaqim Meherab, Noor Islam S. Mohammad, Faiza Feroz · 12 mars 2026

  Sparse autoencoders can localize where concepts live in language models, but not how they interact during multi-step reasoning. We propose Causal Concept Graphs (CCG): a directed acyclic graph over sparse, interpretable latent features, where edges capture learned causal dependencies between concept…

• GaLoRA: Parameter-Efficient Graph-Aware LLMs for Node Classification

  Mayur Choudhary, Saptarshi Sengupta, Katerina Potika · 12 mars 2026

  The rapid rise of large language models (LLMs) and their ability to capture semantic relationships has led to their adoption in a wide range of applications. Text-attributed graphs (TAGs) are a notable example where LLMs can be combined with Graph Neural Networks to improve the performance of node c…

• a-TMFG: Scalable Triangulated Maximally Filtered Graphs via Approximate Nearest Neighbors

  Lionel Yelibi · 11 mars 2026

  The traditional Triangular Maximally Filtered Graph (TMFG) construction requires pre-computation and storage of a dense correlation matrix; this limits its applicability to small and medium-sized datasets. Here we identify key memory and runtime complexity challenges when using TMFG at scale. We the…

• $P^2$GNN: Two Prototype Sets to boost GNN Performance

  Arihant Jain, Gundeep Arora, Anoop Saladi, Chaosheng Dong · 11 mars 2026

  Message Passing Graph Neural Networks (MP-GNNs) have garnered attention for addressing various industry challenges, such as user recommendation and fraud detection. However, they face two major hurdles: (1) heavy reliance on local context, often lacking information about the global context or graph-…