Advanced Graph Neural Networks

Derniers papiers

• Deep Neural Sheaf Diffusion

  Remi Bourgerie, Sarunas Girdzijauskas, Viktoria Fodor · 20 mai 2026

  Deep Graph Neural Networks (GNNs) are essential for capturing complex dependencies in graph-structured data. However, scaling GNNs to depth remains challenging, as stacking layers leads to representation collapse and diminishing sensitivity due to repeated aggregation. While Neural Sheaf Diffusion (…

• Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence

  Mridul Gupta, Samyak Jain, Vansh Ramani, Hariprasad Kodamana, Sayan Ranu · 20 mai 2026

  Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular biology. Graph condensation -- the task of generating a smaller…

• Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees

  Zhuoping Zhou, Davoud Ataee Tarzanagh, Sima Didari, Wenjun Hu, Baruch Gutow, Oxana Verkholyak, Masoud Faraki, Heng Hao, Hankyu Moon, Seungjai Min · 20 mai 2026

  Graph-based Retrieval-Augmented Generation (RAG) systems leverage interconnected knowledge structures to capture complex relationships that flat retrieval struggles with, enabling multi-hop reasoning. Yet most existing graph-based methods suffer from (i) heuristic designs lacking theoretical guarant…

• From Llama to Cria: Scaling Down Neural Networks via Neuron-Level Spectral Structural Importance Evaluation

  Yongyu Wang · 20 mai 2026

  This paper proposes a neuron pruning framework based on neuron-level spectral structural importance evaluation. Given a trained neural network, we record the hidden states of each hidden layer during inference and model neurons as graph nodes, with hidden states treated as graph signals. Using ideas…

• CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection

  Junjun Pan, Yixin Liu, Yu Zheng, Lianhua Chi, Alan Wee-Chung Liew, Shirui Pan · 20 mai 2026

  Text-attributed graph fraud detection (TAGFD) plays a critical role in preventing fraudulent activities on online social and e-commerce platforms. However, to evade detection, fraudsters continuously evolve their camouflaging strategies by deliberately mimicking textual responses of benign users, th…

• Inferring Sensitive Attributes from Knowledge Graph Embeddings: Attack and Defense Strategies

  Yasmine Hayder (PETSCRAFT) · 20 mai 2026

  Knowledge Graphs (KGs) are a powerful representation of linked data, offering flexibility, semantic richness, and support for knowledge enrichment and reasoning. They help data owners organize and exploit heterogeneous data to provide insightful services (e.g., recommendations), yet real-world KGs a…

• BLINKG: A Benchmark for LLM-Integrated Knowledge Graph Generation

  Carla Castedo, Enrique Iglesias, Manuel Lama, Alberto Bugarin-Diz, Maria-Esther Vidal, David Chaves-Fraga · 20 mai 2026

  Generating Knowledge Graphs (KGs) remains one of the most time-consuming and labor-intensive tasks for knowledge engineers, as they need to identify semantic equivalences between input data sources and ontology terms. While declarative solutions (e.g., RML, SPARQL-Anything) have helped to generalize…

• STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation

  Shuai Li, Chen Huang, Duanyu Feng, Wenqiang Lei, See-Kiong Ng · 20 mai 2026

  To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG) leverages lightweight retrievers to efficiently extract information from a given Knowledge Graph (KG). However, existing methods often overlook the i…

• Emergence of Frontier Superposition: M\"obius attractor and Cascade Supervision

  Hongyu Gu, Jingwen Fu · 20 mai 2026

  Superposition allows Transformers to reason in depth, carrying an entire reasoning frontier in parallel through a bounded-depth forward pass instead of unrolling serial chain-of-thought tokens. While Zhu et al. (2025) hand-crafted an equal-weight breadth-first frontier in a single residual stream fo…

• Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

  Sujan Chakraborty, Saptarshi Bej · 20 mai 2026

  We introduce Contrastive FUSE, a fast and unified framework for scalable node representation learning in graphs with partially available pairwise node labels and no available node features. Unlike existing methods, we directly optimize a spectral contrastive objective that integrates community-aware…

• Exploiting Non-Negativity in DAG Structure Learning

  Samuel Rey, Madeline navarro, Gonzalo Mateos · 20 mai 2026

  This work addresses the problem of learning directed acyclic graphs (DAGs) from nodal observations generated by a linear structural equation model. DAG learning is a central task in signal processing, machine learning, and causal inference, but it remains challenging because acyclicity is a global c…

• Graph Neural Networks for Community Detection in Graph Signal Analysis

  Roberto Cavoretto, Alessandra De Rossi, Enrico Montini · 20 mai 2026

  Community detection is a central problem in graph analysis, with applications ranging from network science to graph signal processing. In recent years, Graph Neural Networks (GNNs) have emerged as effective tools for learning low-dimensional representations of graph-structured data and have shown st…

• Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization

  Thien Le, Melanie Weber · 20 mai 2026

  Distillation transfers knowledge from a large model trained on broad data to a smaller, more efficient model suitable for deployment. In structured prediction settings, prior knowledge about the task can guide the choice of a target architecture that is algorithmically aligned with the underlying pr…

• Directed Acyclic Graph Convolutional Networks

  Samuel Rey, Hamed Ajorlou, Gonzalo Mateos · 20 mai 2026

  Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolu…

• Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors

  Aldric Labarthe (CB, UNIGE) · 20 mai 2026

  Bayesian latent space models offer a principled approach to network representation, but rely on correct specification of both geometry and link function. Real-world networks often violate these assumptions, exhibiting geometric mismatch and structural anomalies that break standard metric properties.…

• Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling

  Longgang He, Longzhu He, Daojing He, Chaozhuo Li · 20 mai 2026

  LLM-based multi-agent systems (MAS) have demonstrated strong reasoning and decision-making capabilities that consistently surpass those of single LLM agents. However, their performance often suffers from naive aggregation mechanisms that assume uniformly cooperative interactions. Upon close inspecti…

• Projecting Latent RL Actions: Towards Generalizable and Scalable Graph Combinatorial Optimization

  Franco Terranova (UL, LORIA, Inria), Guillermo Bernardez (UC Santa Barbara), Albert Cabellos-Aparicio (UPC), Nina Miolane (UC Santa Barbara), Abdelkader Lahmadi (LORIA, UL, Inria) · 20 mai 2026

  Graph combinatorial optimization (GCO) has attracted growing interest, as many NP-hard problems naturally admit graph formulations, yet their combinatorial explosion renders exact methods computationally intractable. Recent advances in Reinforcement Learning (RL) combined with Graph Neural Networks …

• Conflict-Free Replicated Data Types for Neural Network Model Merging: A Two-Layer Architecture Enabling CRDT-Compliant Model Merging Across 26 Strategies

  Ryan Gillespie · 20 mai 2026

  All 26 neural network merge strategies we tested including weight averaging, SLERP, TIES, DARE, Fisher merging, and evolutionary approaches -- fail the algebraic properties (commutativity, associativity, idempotency) required for conflict-free distributed operation. We prove that this failure is str…

• DOTRAG: Retrieval-Time Reasoning Along Paths

  Larnell Moore, Naihao Deng, Rada Mihalcea, Farnaz Jahanbakhsh · 20 mai 2026

  Graph Retrieval-Augmented Generation (GraphRAG) is dominated by a retrieve-then-reason paradigm, where context is retrieved using heuristics and then reasoned over. Such methods struggle to adapt to the query-specific logic required for complex multi-hop tasks, often accumulating irrelevant context …

• Agentic GraphRAG: Navigating Unstructured Financial Data with Collaborative AI

  Arthur Capozzi, Dirk Helbing · 20 mai 2026

  We present a collaborative agentic GraphRAG framework for expert analysis of commercial registry data. Public registries are often formally accessible, yet difficult to use in practice because they combine structured records with large volumes of unstructured legal text. This limits conventional key…

• Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data

  Zhenyu Lu, Mahyar Abbasian, Amir M. Rahmani · 20 mai 2026

  Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are long-term, multimodal, and highly personalized. A key challenge is context selection: providing insufficient context limits reasoning, while including all available data leads to inefficiency and degr…

• ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability

  Hongjiang Chen, Xin Zheng, Pengfei Jiao, Huan Liu, Zhidong Zhao, Huaming Wu, Feng Xia, Shirui Pan · 20 mai 2026

  Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpre…

• TERGAD: Structure-Aware Text-Enhanced Representations for Graph Anomaly Detection

  Wen Shi, Zhe Wang, Huafei Huang, Qing Qing, Ziqi Xu, Qixin Zhang, Xikun Zhang, Renqiang Luo, Feng Xia · 20 mai 2026

  Graph Anomaly Detection (GAD) aims to identify atypical graph entities, such as nodes, edges, or substructures, that deviate significantly from the majority. While existing text-rich approaches typically integrate structural context into the data representation pipeline using raw textual features, t…

• InfoFlow: A Framework for Multi-Layer Transformer Analysis

  Penghao Yu, Haotian Jiang, Zeyu Bao, Qianxiao Li · 19 mai 2026

  While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer Transformers possess fundamentally different approximation capa…

• Function graph transformers universally approximate operators between function spaces

  Takashi Furuya, David Mis, Ivan Dokmani\'c, Maarten V. de Hoop, Matti Lassas · 19 mai 2026

  We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a recently introduced measure-theoretic view of transformers. A function $h$ is represented by its graph measure $\gamma_h$,…