Advanced Graph Neural Networks

Derniers papiers

• Learning the Graphical Nature of Symmetries

  Rashid Barket, Enrico Grimaldi, Yacoub Hendi, Edward Hirst, Adam Onus, Harmeet Singh · 15 juillet 2026

  Finite groups are rigid algebraic objects, whose Cayley graphs expose a rich network geometry through which group-theoretic structure can be measured, compared, and learned. In this paper, a dataset of $131{,}406$ Cayley graphs is constructed, covering all groups of order at most $767$ except order …

• Scalable Optimal Transport Algorithm for Network Alignment

  Elaheh Hassani, Durga Mandarapu, Qi Yu, Hanghang Tong, Ariful Azad · 15 juillet 2026

  Network alignment identifies node correspondences across different networks and is a fundamental primitive in many data science applications, including social network analysis, fraud detection, and knowledge graph integration. However, state-of-the-art network alignment methods often achieve high ac…

• Institutional Equity Holdings Prediction Using Node Affinities of Dynamic Graphs

  Emad Izadifar, Zahed Rahmati · 15 juillet 2026

  Institutional equity holdings disclosed in SEC Form 13F filings provide a rich temporal record of portfolio decisions by large investment managers. However, forecasting future allocations and modeling future demand remains challenging due to disclosure lags, reporting noise, and strong persistence i…

• PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

  Jing Liu, Kun Yang, Yan Wang, Dingkang Yang, Xiaoshuai Hao, Wei Zhang, Yang Liu, Wei Zhou · 15 juillet 2026

  Agentic AI systems are reshaping communications and networking by deploying autonomous intelligent agents capable of collaborative learning while maintaining data privacy at network edges. Within distributed network environments, Multimodal Large Language Models (MLLMs) serve as cognitive engines fo…

• UNIT: Unleash Large Language Models Potential for Graph Continual Learning

  Tairan Huang, Yili Wang, Beibei Hu, Yiting Shi, Qiutong Li, Changlong He, Jianliang Gao · 14 juillet 2026

  In real-world multimodal web scenarios, graph-structured data often arrives in a streaming manner, making graph continual learning a crucial paradigm for continuously modeling such evolving structures. However, existing graph continual learning methods still face two fundamental challenges. 1) seman…

• Distance-Preserving Embeddings in Inhomogeneous Random Graphs

  My Le, Luana Ruiz, Souvik Dhara · 14 juillet 2026

  Graph machine learning provides powerful tools for understanding complex networks and learning meaningful node representations. A central challenge, however, is designing embeddings with minimal distortion of both local and global functionals, such as shortest path lengths. Prior distortion guarante…

• Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment

  Chunyu Hu, Tianyin Liao, Ge Lan, Xingxuan Zhang, Jianxin Li, Peng Cui, Ziwei Zhang · 14 juillet 2026

  Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains. Recent advancements in GFMs have been largely dominated by two paradigms: Graph Neural Network and Large Language Model (LLM) based methods. However, these meth…

• CA-DGCL: Dynamic Graph Continual Learning via Condensation and Attachment

  Tingxu Yan Ye Yuan · 14 juillet 2026

  Dynamic graph continual learning (DGCL) is an effective manner for handling catastrophic forgetting in dynamic graphs. However, existing DGCL methods underutilize temporal information across graph snapshots. To address this critical issue, we propose a novel framework for Dynamic Graph Continual Lea…

• RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM

  Mikhail Komarov, Ivan Bondarenko, Stanislav Shtuka, Oleg Sedukhin, Roman Shuvalov, Yana Dementyeva, Matvey Solovyov, Nikolay O. Nikitin · 14 juillet 2026

  Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separ…

• The Equilibrium Is the Initialization: Lazy Identity Collapse in Physics-Structured Deep Equilibrium Reasoning

  Joyjeet Singh · 14 juillet 2026

  Deep equilibrium models promise input-adaptive implicit computation: harder problems should demand more solver iterations, and the solved equilibrium should encode the result of genuine iterative inference. We report a cautionary study of a port-Hamiltonian DEQ with a learned initialization on two r…

• When does distribution shift break graph neural networks calibration?

  Abderaouf Bahi · 14 juillet 2026

  Graph neural networks (GNNs) are increasingly deployed in real-world applications where distribution shift is un-avoidable. However, how such shifts affect model calibration, defined as the agreement between predictive confidence and actual accuracy, remains poorly understood, and existing graph cal…

• RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation

  Renzhi Wu, Zikun Cui, Junjie Yang, Tai Guo, Hong Li, Xian Chen, Li Yu, Ke Pan, Sri Reddy, Mahesh Srinivasan, Nipun Mathur, Haomin Yu, Hong Yan · 14 juillet 2026

  Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet existing work addresses each in isolation. We present RankGraph-2, a framework deployed at Meta that co-designs all three l…

• Quantum-Inspired Contextual Learning for Sparse-Ring Fraud Detection in Dynamic Transaction Graphs

  Behnam Tonekaboni, Hiroshi Yamauchi · 14 juillet 2026

  We present an exploratory benchmark and quantum-inspired modeling prototype for fraud screening in dynamic financial transaction graphs. Coordinated fraud may not be visible from individual transactions alone, but may emerge as a multi-period relational pattern. We focus on sparse-ring fraud, a styl…

• Learning Subgroup Relations Using Siamese Graph Neural Networks

  Tal Weissblat · 14 juillet 2026

  Determining whether one finite group is isomorphic to a subgroup of another is a fundamental problem in computational group theory. In this work, we propose a Siamese Graph Neural Network (Siamese GNN) for subgroup prediction using Cayley graph representations of finite groups. Each input group is r…

• GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention

  Jiaxin Pan, Osama Mohammed, Daniel Hern\'andez, Steffen Staab · 14 juillet 2026

  Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relations. Extending this transferability to temporal knowledge graphs (TKGs) remains challenging: existing temporal models tie…

• Community-Aware Vertex Ordering for Reference-Based Graph Compression: A Cross-Encoder Empirical Study

  Jimmy Dubuisson · 14 juillet 2026

  Reference-based graph compression encodes each vertex's neighbor list as differences from a nearby encoded list. WebGraph's BVGraph fixes a single encoding pipeline and relies on a separately chosen vertex ordering -- typically URL-lexicographic or Layered Label Propagation (LLP). Their interaction …

• Hyper-modal Imputation Diffusion Embedding with Dual-Distillation for Federated Multimodal Knowledge Graph Completion

  Ying Zhang, Yu Zhao, Xuhui Sui, Baohang Zhou, Xiangrui Cai, Li Shen, Xiaojie Yuan, Dacheng Tao · 14 juillet 2026

  With the increasing multimodal knowledge privatization requirements, multimodal knowledge graphs in different institutes are usually decentralized, lacking of effective collaboration system with both stronger reasoning ability and transmission safety guarantees. In this paper, we propose the Federat…

• KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text

  Nipun Misra, Vikranth Udandarao, Aanchal Gupta, Yogender Kumar, Manuj Mukherjee, Raghava Mutharaju · 14 juillet 2026

  Knowledge Graphs (KGs) are increasingly constructed through automated extraction pipelines; however, such systems often introduce spurious or incomplete triples, which degrade downstream performance. Existing evaluation practices rely heavily on task-specific metrics or small-scale manual verificati…

• Structure-Feature Aligned Graph Learning via Alternating Constrained Optimization

  Chengcheng Yan, Qingsong Wang · 14 juillet 2026

  We introduce a constrained two-view framework for node prediction that aligns structure-conditioned GNN embeddings with a structure-free feature prior learned by an anchor model. Conventional Graph Neural Networks (GNNs) couple feature transformation and neighborhood aggregation, which renders them …

• A Novel Graph Fraud Detector via Grouped Attribute Completion and Confidence-Aware Contrastive Learning

  Junpeng Wu, Ye Yuan · 14 juillet 2026

  Graph fraud detection plays a pivotal role in safeguarding the security and integrity of modern digital ecosystems. Graph Neural Networks (GNNs) are commonly adopted for graph fraud detection. However, the practical performance of existing GNN-based detectors is severely hindered by incomplete node …

• Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey

  Chengcheng Sun, Jiayun Tian, Cheng Zhai, Zhixiao Wang, Yajie Song, Xiaobin Rui, Jian Zhang, Philip S. Yu · 14 juillet 2026

  Graph Neural Networks (GNNs) have emerged as a powerful paradigm in Knowledge Graphs (KGs) due to their intrinsic ability to model graph-structured data. However, there remains a lack of a systematic review about GNN-based methodologies across the entire knowledge graph technologies pipeline. To add…

• PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection

  Liming Liu, Chao Hu, Mingfei Lu, Yiwei Ge, Xingle Li, Heyuan Shi · 14 juillet 2026

  Relational fraud detection can exploit both label-free graph context and label-derived neighborhood evidence, but these two information sources obey different validity conditions. In particular, neighborhood risk becomes invalid when a queried node's own label, or any validation or test label, enter…

• Group Invariant Spectral Embedding

  Yeari Vigder, Paulina Hoyos, David Thong, Joakim and\'en, Joe Kileel, Amit Moscovich · 13 juillet 2026

  Spectral embedding methods are widely used for dimensionality reduction and clustering of high-dimensional datasets with intrinsic low-dimensional structures. Although many datasets of practical interest exhibit invariance under symmetries such as rotations, standard spectral embedding methods do no…

• Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification

  Camila Piscioneri Magalh\~aes, Lucas Pascotti Valem · 13 juillet 2026

  While the growing availability of image data has driven significant advances, labeling datasets remains costly and time-consuming. Therefore, semi-supervised approaches such as Graph Convolutional Networks (GCNs), which learn from both labeled and unlabeled data, have emerged as a promising solution…

• Pattern-Aware Graph Neural Networks for Handling Missing Data

  Minett Tran, Taehee Jeong · 13 juillet 2026

  Missing data is ubiquitous in real-world datasets. Traditional methods either discard incomplete samples or apply imputation techniques that ignore potentially informative missingness patterns, implicitly assuming that missingness occurs randomly. However, missingness patterns might provide addition…