Advanced Graph Neural Networks

Derniers papiers

• A Community-Enhanced Graph Representation Model for Link Prediction

  Lei Wang, Darong Lai · 25 décembre 2025

  Although Graph Neural Networks (GNNs) have become the dominant approach for graph representation learning, their performance on link prediction tasks does not always surpass that of traditional heuristic methods such as Common Neighbors and Jaccard Coefficient. This is mainly because existing GNNs t…

• WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks

  Tingzhi Li, Xuefeng Liu, Jing Lei, Xingang Zhang · 25 décembre 2025

  Graph Neural Networks (GNNs) are increasingly deployed in real-world applications, making ownership verification critical to protect their intellectual property against model theft. Fingerprinting and black-box watermarking are two main methods. However, the former relies on determining model simila…

• Semantic Refinement with LLMs for Graph Representations

  Safal Thapaliya, Zehong Wang, Jiazheng Li, Ziming Li, Yanfang Ye, Chuxu Zhang · 25 décembre 2025

  Graph-structured data exhibit substantial heterogeneity in where their predictive signals originate: in some domains, node-level semantics dominate, while in others, structural patterns play a central role. This structure-semantics heterogeneity implies that no graph learning model with a fixed indu…

• Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning

  Zuo Wang, Ye Yuan · 24 décembre 2025

  In this paper, we investigate how the widely existing contextual and structural divergence may influence the representation learning in rich-text graphs. To this end, we propose Jensen-Shannon Divergence Message-Passing (JSDMP), a new learning paradigm for rich-text graph representation learning. Be…

• Sign-Aware Multistate Jaccard Kernels and Geometry for Real and Complex-Valued Signals

  Vineet Yadav · 24 décembre 2025

  We introduce a sign-aware, multistate Jaccard/Tanimoto framework that extends overlap-based distances from nonnegative vectors and measures to arbitrary real- and complex-valued signals while retaining bounded metric and positive-semidefinite kernel structure. Formally, the construction is a set- an…

• Fraud Detection Through Large-Scale Graph Clustering with Heterogeneous Link Transformation

  Chi Liu · 23 décembre 2025

  Collaborative fraud, where multiple fraudulent accounts coordinate to exploit online payment systems, poses significant challenges due to the formation of complex network structures. Traditional detection methods that rely solely on high-confidence identity links suffer from limited coverage, while …

• Explainable Graph Spectral Clustering For GloVe-like Text Embeddings

  Mieczys{\l}aw A. K{\l}opotek, S{\l}awomir T. Wierzcho\'n, Bart{\l}omiej Starosta, Piotr Borkowski, Dariusz Czerski, Eryk Laskowski · 23 décembre 2025

  In a previous paper, we proposed an introduction to the explainability of Graph Spectral Clustering results for textual documents, given that document similarity is computed as cosine similarity in term vector space. In this paper, we generalize this idea by considering other embeddings of documen…

• Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization

  Lichen Yang, Qiang Wang, Zhonghao Yang, Daojing He, Yu Li · 23 décembre 2025

  Graph Neural Networks (GNNs) have demonstrated remarkable efficacy in handling graph-structured data; however, they exhibit failures after deployment, which can cause severe consequences. Hence, conducting thorough testing before deployment becomes imperative to ensure the reliability of GNNs. Howev…

• Graph Transformers: A Survey

  Ahsan Shehzad, Feng Xia, Shagufta Abid, Ciyuan Peng, Shuo Yu, Dongyu Zhang, Karin Verspoor · 23 décembre 2025

  Graph transformers are a recent advancement in machine learning, offering a new class of neural network models for graph-structured data. The synergy between transformers and graph learning demonstrates strong performance and versatility across various graph-related tasks. This survey provides an in…

• FairExpand: Individual Fairness on Graphs with Partial Similarity Information

  Rebecca Salganik, Yibin Wang, Guillaume Salha-Galvan, Jian Kang · 23 décembre 2025

  Individual fairness, which requires that similar individuals should be treated similarly by algorithmic systems, has become a central principle in fair machine learning. Individual fairness has garnered traction in graph representation learning due to its practical importance in high-stakes Web area…

• DyGSSM: Multi-view Dynamic Graph Embeddings with State Space Model Gradient Update

  Bizhan Alipour Pijan, Serdar Bozdag · 23 décembre 2025

  Most of the dynamic graph representation learning methods involve dividing a dynamic graph into discrete snapshots to capture the evolving behavior of nodes over time. Existing methods primarily capture only local or global structures of each node within a snapshot using message-passing and random w…

• A Logical View of GNN-Style Computation and the Role of Activation Functions

  Pablo Barcel\'o, Floris Geerts, Matthias Lanzinger, Klara Pakhomenko, Jan Van den Bussche · 23 décembre 2025

  We study the numerical and Boolean expressiveness of MPLang, a declarative language that captures the computation of graph neural networks (GNNs) through linear message passing and activation functions. We begin with A-MPLang, the fragment without activation functions, and give a characterization of…

• Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs

  David Graber, Victor Armegioiu, Rebecca Buller, Siddhartha Mishra · 23 décembre 2025

  Predictive machine learning models generally excel on in-distribution data, but their performance degrades on out-of-distribution (OOD) inputs. Reliable deployment therefore requires robust OOD detection, yet this is particularly challenging for irregular 3D graphs that combine continuous geometry w…

• Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection

  Souhail Abdelmouaiz Sadat, Mohamed Yacine Touahria Miliani, Khadidja Hab El Hames, Hamida Seba, Mohammed Haddad · 23 décembre 2025

  This survey reviews hyperbolic graph embedding models, and evaluate them on anomaly detection, highlighting their advantages over Euclidean methods in capturing complex structures. Evaluating models like \textit{HGCAE}, \textit{\(\mathcal{P}\)-VAE}, and \textit{HGCN} demonstrates high performance, w…

• Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study

  Janek Dyer, Jagdeep Ahluwalia, Javad Zarrin · 23 décembre 2025

  The ability to discriminate between generative graph models is critical to understanding complex structural patterns in both synthetic graphs and the real-world structures that they emulate. While Graph Neural Networks (GNNs) have seen increasing use to great effect in graph classification tasks, fe…

• ARC: Leveraging Compositional Representations for Cross-Problem Learning on VRPs

  Han-Seul Jeong, Youngjoon Park, Hyungseok Song, Woohyung Lim · 23 décembre 2025

  Vehicle Routing Problems (VRPs) with diverse real-world attributes have driven recent interest in cross-problem learning approaches that efficiently generalize across problem variants. We propose ARC (Attribute Representation via Compositional Learning), a cross-problem learning framework that learn…

• LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networks

  Chuqin Geng, Ziyu Zhao, Zhaoyue Wang, Haolin Ye, Yuhe Jiang, Xujie Si · 23 décembre 2025

  Existing rule-based explanations for Graph Neural Networks (GNNs) provide global interpretability but often optimize and assess fidelity in an intermediate, uninterpretable concept space, overlooking grounding quality for end users in the final subgraph explanations. This gap yields explanations tha…

• AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learning

  Xuling Zhang, Jindong Li, Yifei Zhang, Menglin Yang · 23 décembre 2025

  Continual graph learning (CGL) aims to enable graph neural networks to incrementally learn from a stream of graph structured data without forgetting previously acquired knowledge. Existing methods particularly those based on experience replay typically store and revisit past graph data to mitigate c…

• SEA: Spectral Edge Attack on Graph Neural Networks

  Yongyu Wang · 23 décembre 2025

  Graph neural networks (GNNs) have been widely applied in a variety of domains. However, the very ability of graphs to represent complex data structures is both the key strength of GNNs and a major source of their vulnerability. Recent studies have shown that attacking GNNs by maliciously perturbing …

• Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection

  Jie Yang, Rui Zhang, Ziyang Cheng, Dawei Cheng, Guang Yang, Bo Wang · 23 décembre 2025

  Nowadays, Graph Fraud Detection (GFD) in financial scenarios has become an urgent research topic to protect online payment security. However, as organized crime groups are becoming more professional in real-world scenarios, fraudsters are employing more sophisticated camouflage strategies. Specifica…

• Probabilistic Digital Twins of Users: Latent Representation Learning with Statistically Validated Semantics

  Daniel David · 23 décembre 2025

  Understanding user identity and behavior is central to applications such as personalization, recommendation, and decision support. Most existing approaches rely on deterministic embeddings or black-box predictive models, offering limited uncertainty quantification and little insight into what latent…

• Certified Defense on the Fairness of Graph Neural Networks

  Yushun Dong, Binchi Zhang, Hanghang Tong, Jundong Li · 23 décembre 2025

  Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs, it has been empirically shown that malicious attackers could easily corrupt the fairness level of their predictions by adding p…

• UniRel-R1: RL-tuned LLM Reasoning for Knowledge Graph Relational Question Answering

  Yinxu Tang, Chengsong Huang, Jiaxin Huang, William Yeoh · 22 décembre 2025

  Knowledge Graph Question Answering (KGQA) has traditionally focused on entity-centric queries that return a single answer entity. However, real-world queries are often relational, seeking to understand how entities are associated. In this work, we introduce relation-centric KGQA, a complementary set…

• From Priors to Predictions: Explaining and Visualizing Human Reasoning in a Graph Neural Network Framework

  Quan Do, Caroline Ahn, Leah Bakst, Michael Pascale, Joseph T. McGuire, Chantal E. Stern, Michael E. Hasselmo · 22 décembre 2025

  Humans excel at solving novel reasoning problems from minimal exposure, guided by inductive biases, assumptions about which entities and relationships matter. Yet the computational form of these biases and their neural implementation remain poorly understood. We introduce a framework that combines G…

• Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation

  Luca Miglior, Matteo Tolloso, Alessio Gravina, Davide Bacciu · 22 décembre 2025

  Effectively capturing long-range interactions remains a fundamental yet unresolved challenge in graph neural network (GNN) research, critical for applications across diverse fields of science. To systematically address this, we introduce ECHO (Evaluating Communication over long HOps), a novel benchm…