Advanced Graph Neural Networks

Derniers papiers

• Gaussian Process Limit Reveals Structural Benefits of Graph Transformers

  Nil Ayday, Lingchu Yang, Debarghya Ghoshdastidar · 19 mars 2026

  Graph transformers are the state-of-the-art for learning from graph-structured data and are empirically known to avoid several pitfalls of message-passing architectures. However, there is limited theoretical analysis on why these models perform well in practice. In this work, we prove that attention…

• A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models

  Leonardo Defilippis, Florent Krzakala, Bruno Loureiro, Antoine Maillard · 19 mars 2026

  Understanding when learning is statistically possible yet computationally hard is a central challenge in high-dimensional statistics. In this work, we investigate this question in the context of single- and multi-index models, classes of functions widely studied as benchmarks to probe the ability of…

• Exact Generalisation Error Exposes Benchmarks Skew Graph Neural Networks Success (or Failure)

  Nil Ayday, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar · 19 mars 2026

  Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why performance varies drastically between similar models, remai…

• Learning Time-Varying Graphs from Incomplete Graph Signals

  Chuansen Peng, Xiaojing Shen · 19 mars 2026

  This paper tackles the challenging problem of jointly inferring time-varying network topologies and imputing missing data from partially observed graph signals. We propose a unified non-convex optimization framework to simultaneously recover a sequence of graph Laplacian matrices while reconstructin…

• RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems

  Hui Wang, Tianzhu Hu, Mingming Li, Xi Zhou, Chun Gan, Jiao Dai, Jizhong Han, Songlin Hu, Tao Guo · 18 mars 2026

  Recommender systems are inherently dynamic feedback loops where prolonged local interactions accumulate into macroscopic structural degradation such as information cocoons. Existing representation learning paradigms are universally constrained by the assumption of a single flat space, forcing topolo…

• Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach

  Mengyao Zhou, Zhiheng Zhou, Xiao Han, Xingqin Qi, Guanghui Wang, Guiying Yan · 18 mars 2026

  Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes. Inspired by the theory of R…

• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance

  Jiachi Zhao, Zehong Wang, Yamei Liao, Chuxu Zhang, Yanfang Ye · 18 mars 2026

  Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material discovery. Recent approaches leverage diffusion models for step-by-step generation, yet unconditional diffusion offers litt…

• Functorial Neural Architectures from Higher Inductive Types

  Karen Sargsyan · 18 mars 2026

  Neural networks systematically fail at compositional generalization -- producing correct outputs for novel combinations of known parts. We show that this failure is architectural: compositional generalization is equivalent to functoriality of the decoder, and this perspective yields both guarantees …

• Neural-Symbolic Logic Query Answering in Non-Euclidean Space

  Lihui Liu · 18 mars 2026

  Answering complex first-order logic (FOL) queries on knowledge graphs is essential for reasoning. Symbolic methods offer interpretability but struggle with incomplete graphs, while neural approaches generalize better but lack transparency. Neural-symbolic models aim to integrate both strengths but o…

• Beyond Linearity in Attention Projections: The Case for Nonlinear Queries

  Marko Karbevski · 17 mars 2026

  Recent algebraic analysis shows that in decoder-only and encoder-only transformers, the Query projection $W_Q$ may be set to identity without noticeable performance deterioration. This is possible because attention depends on $X$ only through the products $XW_Q, XW_K, XW_V$, allowing basis transform…

• Modality-free Graph In-context Alignment

  Wei Zhuo, Siqiang Luo · 17 mars 2026

  In-context learning (ICL) converts static encoders into task-conditioned reasoners, enabling adaptation to new data from just a few examples without updating pretrained parameters. This capability is essential for graph foundation models (GFMs) to approach LLM-level generality. Yet current GFMs stru…

• A Systematic Evaluation Protocol of Graph-Derived Signals for Tabular Machine Learning

  Mario Heidrich, Jeffrey Heidemann, R\"udiger Buchkremer, Gonzalo Wandosell Fern\'andez de Bobadilla · 17 mars 2026

  While graph-derived signals are widely used in tabular learning, existing studies typically rely on limited experimental setups and average performance comparisons, leaving the statistical reliability and robustness of observed gains largely unexplored. Consequently, it remains unclear which signals…

• Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database

  Madhulatha Mandarapu, Sandeep Kunkunuru · 17 mars 2026

  Biomedical knowledge is fragmented across siloed databases -- Reactome for pathways, STRING for protein interactions, Gene Ontology for functional annotations, ClinicalTrials.gov for study registries, and dozens more. Researchers routinely download flat files from each source and write bespoke scrip…

• Auditing Cascading Risks in Multi-Agent Systems via Semantic-Geometric Co-evolution

  Zixun Luo, Yuhang Fan, Hengyu Lin, Yufei Li, Youzhi Zhang · 17 mars 2026

  Large Language model (LLM)-based Multi-Agent Systems (MAS) are prone to cascading risks, where early-stage interactions remain semantically fluent and policy-compliant, yet the underlying interaction dynamics begin to distort in ways that amplify latent instability or misalignment. Traditional audit…

• TAS-GNN: A Status-Aware Signed Graph Neural Network for Anomaly Detection in Bitcoin Trust Systems

  Chang Xue, Fang Liu, Jiaye Wang, Jinming Xing, Chen Yang · 17 mars 2026

  Decentralized financial platforms rely heavily on Web of Trust reputation systems to mitigate counterparty risk in the absence of centralized identity verification. However, these pseudonymous networks are inherently vulnerable to adversarial behaviors, such as Sybil attacks and camouflaged fraud, w…

• HyReaL: Clustering Attributed Graph via Hyper-Complex Space Representation Learning

  Junyang Chen, Yang Lu, Mengke Li, Cuie Yang, Yiqun Zhang, Yiu-ming Cheung · 17 mars 2026

  Clustering complex data in the form of attributed graphs has attracted increasing attention, where powerful graph representation is a critical prerequisite. However, the well-known Over-Smoothing (OS) effect makes Graph Convolutional Networks tend to homogenize the representation of graph nodes, whi…

• LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs

  Ying Zhang, Hang Yu, Haipeng Zhang, Peng Di · 17 mars 2026

  Text-rich graphs, which integrate complex structural dependencies with abundant textual information, are ubiquitous yet remain challenging for existing learning paradigms. Conventional methods and even LLM-hybrids compress rich text into static embeddings or summaries before structural reasoning, cr…

• Bridging Local and Global Knowledge: Cascaded Mixture-of-Experts Learning for Near-Shortest Path Routing

  Yung-Fu Chen, Anish Arora · 17 mars 2026

  While deep learning models that leverage local features have demonstrated significant potential for near-optimal routing in dense Euclidean graphs, they struggle to generalize well in sparse networks where topological irregularities require broader structural awareness. To address this limitation, w…

• Suppressing Domain-Specific Hallucination in Construction LLMs: A Knowledge Graph Foundation for GraphRAG and QLoRA on River and Sediment Control Technical Standards

  Takato Yasuno · 17 mars 2026

  This paper addresses the challenge of answering technical questions derived from Japan's River and Sediment Control Technical Standards -- a multi-volume regulatory document covering survey, planning, design, and maintenance of river levees, dams, and sabo structures -- using open-source large langu…

• Node Role-Guided LLMs for Dynamic Graph Clustering

  Dongyuan Li, Ying Zhang, Yaozu Wu, Renhe Jiang · 17 mars 2026

  Dynamic graph clustering aims to detect and track time-varying clusters in dynamic graphs, revealing how complex real-world systems evolve over time. However, existing methods are predominantly black-box models. They lack interpretability in their clustering decisions and fail to provide semantic ex…

• Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution

  Hua Liu, Yanbin Wei, Fei Xing, Tyler Derr, Haoyu Han, Yu Zhang · 17 mars 2026

  Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal evolution. They tend to overlook fine-grained variations in temporal interaction…

• GraphVLM: Benchmarking Vision Language Models for Multimodal Graph Learning

  Jiajin Liu, Dongzhe Fan, Chuanhao Ji, Daochen Zha, Qiaoyu Tan · 17 mars 2026

  Vision-Language Models (VLMs) have demonstrated remarkable capabilities in aligning and understanding multimodal signals, yet their potential to reason over structured data, where multimodal entities are connected through explicit relational graphs, remains largely underexplored. Unlocking this capa…

• JobMatchAI An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search and Explainable AI

  Mayank Vyaas, Abhijit Chakrabroty, Vivek Gupta · 17 mars 2026

  Recruiters and job seekers rely on search systems to navigate labor markets, making candidate matching engines critical for hiring outcomes. Most systems act as keyword filters, failing to handle skill synonyms and nonlinear careers, resulting in missed candidates and opaque match scores. We introdu…

• OMNIA: Closing the Loop by Leveraging LLMs for Knowledge Graph Completion

  Fr\'ed\'eric Ieng, Soror Sahri, Mourad Ouzzani, Massinissa Hammaz, Salima Benbernou, Hanieh Khorashadizadeh, Sven Groppe, Farah Benamara · 17 mars 2026

  Knowledge Graphs (KGs) are widely used to represent structured knowledge, yet their automatic construction, especially with Large Language Models (LLMs), often results in incomplete or noisy outputs. Knowledge Graph Completion (KGC) aims to infer and add missing triples, but most existing methods ei…

• Lost in Aggregation: On a Fundamental Expressivity Limit of Message-Passing Graph Neural Networks

  Eran Rosenbluth · 17 mars 2026

  We define a generic class of functions that captures most conceivable aggregations for Message-Passing Graph Neural Networks (MP-GNNs), and prove that any MP-GNN model with such aggregations induces only a polynomial number of equivalence classes on all graphs - while the number of non-isomorphic gr…