Advanced Graph Neural Networks

Derniers papiers

• Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models

  Fengzhi Li, Liang Zhang, Yuan Zuo, Ruiqing Zhao, YanSong Liu, Yunfei Ma, Fanyu Meng, Junlan Feng · 4 mars 2026

  Graph-based tasks in the zero-shot setting remain a significant challenge due to data scarcity and the inability of traditional Graph Neural Networks (GNNs) to generalize to unseen domains or label spaces. While recent advancements have transitioned toward leveraging Large Language Models (LLMs) as …

• VL-KGE: Vision-Language Models Meet Knowledge Graph Embeddings

  Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic, Nachoem Wijnberg, Marcel Worring · 4 mars 2026

  Real-world multimodal knowledge graphs (MKGs) are inherently heterogeneous, modeling entities that are associated with diverse modalities. Traditional knowledge graph embedding (KGE) methods excel at learning continuous representations of entities and relations, yet they are typically designed for u…

• Can Computational Reducibility Lead to Transferable Models for Graph Combinatorial Optimization?

  Semih Cant\"urk, Thomas Sabourin, Frederik Wenkel, Michael Perlmutter, Guy Wolf · 4 mars 2026

  A key challenge in deriving unified neural solvers for combinatorial optimization (CO) is efficient generalization of models between a given set of tasks to new tasks not used during the initial training process. To address it, we first establish a new model, which uses a GCON module as a form of ex…

• Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs

  Muyukani Kizito, Elizabeth Nyambere · 4 mars 2026

  We present Odin, the first production-deployed graph intelligence engine for autonomous discovery of meaningful patterns in knowledge graphs without prior specification. Unlike retrieval-based systems that answer predefined queries, Odin guides exploration through the COMPASS (Composite Oriented Mul…

• Torus embeddings

  Dan Stowell · 4 mars 2026

  Many data representations are vectors of continuous values. In particular, deep learning embeddings are data-driven representations, typically either unconstrained in Euclidean space, or constrained to a hypersphere. These may also be translated into integer representations (quantised) for efficient…

• On the Expressive Power of Transformers for Maxout Networks and Continuous Piecewise Linear Functions

  Linyan Gu, Lihua Yang, Feng Zhou · 4 mars 2026

  Transformer networks have achieved remarkable empirical success across a wide range of applications, yet their theoretical expressive power remains insufficiently understood. In this paper, we study the expressive capabilities of Transformer architectures. We first establish an explicit approximatio…

• Conformal Graph Prediction with Z-Gromov Wasserstein Distances

  Gabriel Melo, Thibaut de Saivre, Anna Calissano, Florence d'Alch\'e-Buc · 4 mars 2026

  Supervised graph prediction addresses regression problems where the outputs are structured graphs. Although several approaches exist for graph--valued prediction, principled uncertainty quantification remains limited. We propose a conformal prediction framework for graph-valued outputs, providing di…

• MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks

  Zhi Hong, Qian Zhang, Jiahang Sun, Zhiwei Shang, Mingze Kong, Xiangyi Wang, Yao Shu, Zhongxiang Dai · 4 mars 2026

  Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment scenarios preclude MAS workflow modifications and its perfor…

• Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection

  Jiaqi Lv, Qingfeng Du, Yu Zhang, Yongqi Han, Sheng Li · 4 mars 2026

  Graph fraud detection (GFD) is crucial for identifying fraudulent behavior within graphs, benefiting various domains such as financial networks and social media. Existing methods based on graph neural networks (GNNs) have succeeded considerably due to their effective expressive capacity for graph-st…

• Incremental Graph Construction Enables Robust Spectral Clustering of Texts

  Marko Pranji\'c, Boshko Koloski, Nada Lavra\v{c}, Senja Pollak, Marko Robnik-\v{S}ikonja · 4 mars 2026

  Neighborhood graphs are a critical but often fragile step in spectral clustering of text embeddings. On realistic text datasets, standard $k$-NN graphs can contain many disconnected components at practical sparsity levels (small $k$), making spectral clustering degenerate and sensitive to hyperparam…

• CARD: Towards Conditional Design of Multi-agent Topological Structures

  Tongtong Wu, Yanming Li, Ziye Tang, Chen Jiang, Linhao Luo, Guilin Qi, Shirui Pan, Gholamreza Haffari · 3 mars 2026

  Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned, …

• Invariant-Stratified Propagation for Expressive Graph Neural Networks

  Asela Hevapathige, Ahad N. Zehmakan, Asiri Wijesinghe, Saman Halgamuge · 3 mars 2026

  Graph Neural Networks (GNNs) face fundamental limitations in expressivity and capturing structural heterogeneity. Standard message-passing architectures are constrained by the 1-dimensional Weisfeiler-Leman (1-WL) test, unable to distinguish graphs beyond degree sequences, and aggregate information …

• Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting

  Yi Li, Han Liu, Mingfeng Fan, Guo Chen, Chaojie Li, Biplab Sikdar · 3 mars 2026

  Federated learning (FL) on graphs shows promise for distributed time-series forecasting. Yet, existing methods rely on static topologies and struggle with client heterogeneity. We propose Fed-GAME, a framework that models personalized aggregation as message passing over a learnable dynamic implicit …

• Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning

  Xinxun Zhang, Pengfei Jiao, Mengzhou Gao, Tianpeng Li, Xuan Guo · 3 mars 2026

  Although dynamic graph neural networks (DyGNNs) have demonstrated promising capabilities, most existing methods ignore out-of-distribution (OOD) shifts that commonly exist in dynamic graphs. Dynamic graph OOD generalization is non-trivial due to the following challenges: 1) Identifying invariant and…

• GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detection

  Xiong Zhang, Hong Peng, Zhenli He, Cheng Xie, Xin Jin, Hua Jiang · 3 mars 2026

  Anomalies often occur in real-world information networks/graphs, such as malevolent users, malicious comments, banned users, and fake news in social graphs. The latest graph anomaly detection methods use a novel mechanism called truncated affinity maximization (TAM) to detect anomaly nodes without u…

• FSW-GNN: A Bi-Lipschitz WL-Equivalent Graph Neural Network

  Yonatan Sverdlov, Yair Davidson, Nadav Dym, Tal Amir · 3 mars 2026

  Famously, the ability of Message Passing Neural Networks (MPNN) to distinguish between graphs is limited to graphs separable by the Weisfeiler-Lemann (WL) graph isomorphism test, and the strongest MPNNs, in terms of separation power, are WL-equivalent. However, it was demonstrated that the quality o…

• Property-Driven Evaluation of GNN Expressiveness at Scale: Datasets, Framework, and Study

  Sicong Che, Jiayi Yang, Sarfraz Khurshid, Wenxi Wang · 3 mars 2026

  Advancing trustworthy AI requires principled software engineering approaches to model evaluation. Graph Neural Networks (GNNs) have achieved remarkable success in processing graph-structured data, however, their expressiveness in capturing fundamental graph properties remains an open challenge. We a…

• BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loop

  Chao Chen, Xujia Li, Dongsheng Hong, Shanshan Lin, Xiangwen Liao, Chuanyi Liu, Lei Chen · 3 mars 2026

  The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate graph data. In this context, Few-Shot Graph Learning (FSGL) app…

• Practical Deep Heteroskedastic Regression

  Mikkel Jordahn, Jonas Vestergaard Jensen, James Harrison, Michael Riis Andersen, Mikkel N. Schmidt · 3 mars 2026

  Uncertainty quantification (UQ) in deep learning regression is of wide interest, as it supports critical applications including sequential decision making and risk-sensitive tasks. In heteroskedastic regression, where the uncertainty of the target depends on the input, a common approach is to train …

• t-SNE Exaggerates Clusters, Provably

  Noah Bergam, Szymon Snoeck, Nakul Verma · 3 mars 2026

  Central to the widespread use of t-distributed stochastic neighbor embedding (t-SNE) is the conviction that it produces visualizations whose structure roughly matches that of the input. To the contrary, we prove that (1) the strength of the input clustering, and (2) the extremity of outlier points, …

• Rapid training of Hamiltonian graph networks using random features

  Atamert Rahma, Chinmay Datar, Ana Cukarska, Felix Dietrich · 3 mars 2026

  Learning dynamical systems that respect physical symmetries and constraints remains a fundamental challenge in data-driven modeling. Integrating physical laws with graph neural networks facilitates principled modeling of complex N-body dynamics and yields accurate and permutation-invariant models. H…

• Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchanger

  Li Sun, Ming Zhang, Wenxin Jin, Zhongtian Sun, Zhenhao Huang, Hao Peng, Sen Su, Philip Yu · 3 mars 2026

  Hypergraphs are the natural description of higher-order interactions among objects, widely applied in social network analysis, cross-modal retrieval, etc. Hypergraph Neural Networks (HGNNs) have become the dominant solution for learning on hypergraphs. Traditional HGNNs are extended from message pas…

• GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning

  Yuchen Ying, Weiqi Jiang, Tongya Zheng, Yu Wang, Shunyu Liu, Kaixuan Chen, Mingli Song · 3 mars 2026

  Knowledge graphs provide structured and reliable information for many real-world applications, motivating increasing interest in combining large language models (LLMs) with graph-based retrieval to improve factual grounding. Recent Graph-based Retrieval-Augmented Generation (GraphRAG) methods theref…

• Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs

  Emanuele Mule, Stefano Fiorini, Antonio Purificato, Federico Siciliano, Stefano Coniglio, Fabrizio Silvestri · 3 mars 2026

  Hypergraphs provide a natural way to represent higher-order interactions among multiple entities. While undirected hypergraphs have been extensively studied, the case of directed hypergraphs, which can model oriented group interactions, remains largely under-explored despite its relevance for many a…

• CIRCUS: Circuit Consensus under Uncertainty via Stability Ensembles

  Swapnil Parekh · 3 mars 2026

  Mechanistic circuit discovery is notoriously sensitive to arbitrary analyst choices, especially pruning thresholds and feature dictionaries, often yielding brittle "one-shot" explanations with no principled notion of uncertainty. We reframe circuit discovery as an uncertainty-quantification problem …