Advanced Graph Neural Networks

Derniers papiers

• Synthetic Tabular Generators Fail to Preserve Behavioral Fraud Patterns: A Benchmark on Temporal, Velocity, and Multi-Account Signals

  Bhavana Sajja · 16 avril 2026

  We introduce behavioral fidelity -- a third evaluation dimension for synthetic tabular data that measures whether generated data preserves the temporal, sequential, and structural behavioral patterns that distinguish real-world entity activity. Existing frameworks evaluate statistical fidelity (marg…

• Leveraging LLM-GNN Integration for Open-World Question Answering over Knowledge Graphs

  Hussein Abdallah, Ibrahim Abdelaziz, Panos Kalnis, Essam Mansour · 16 avril 2026

  Open-world Question Answering (OW-QA) over knowledge graphs (KGs) aims to answer questions over incomplete or evolving KGs. Traditional KGQA assumes a closed world where answers must exist in the KG, limiting real-world applicability. In contrast, open-world QA requires inferring missing knowledge b…

• Evaluating Relational Reasoning in LLMs with REL

  Lukas Fesser, Yasha Ektefaie, Ada Fang, Sham M. Kakade, Marinka Zitnik · 15 avril 2026

  Relational reasoning is the ability to infer relations that jointly bind multiple entities, attributes, or variables. This ability is central to scientific reasoning, but existing evaluations of relational reasoning in large language models often focus on structured inputs such as tables, graphs, or…

• PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

  Anupam Nayak, Baris Askin, Muhammed Ustaomeroglu, Carlee Joe-Wong, Gauri Joshi · 15 avril 2026

  Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentralized private data distributed across organizations. Federated training is a natural solution, but scaling RLVR in this reg…

• Privacy-Preserving Transfer Learning for Community Detection using Locally Distributed Multiple Networks

  Xiao Guo, Xuming He, Xiangyu Chang, Shujie Ma · 15 avril 2026

  Modern applications increasingly involve highly sensitive network data, where raw edges cannot be shared due to privacy constraints. We propose \texttt{TransNet}, a new spectral clustering-based transfer learning framework that improves community detection on a \emph{target network} by leveraging he…

• CascadeDebate: Multi-Agent Deliberation for Cost-Aware LLM Cascades

  Raeyoung Chang, Dongwook Kwon, Jisoo Lee, Nikhil Verma · 15 avril 2026

  Cascaded LLM systems coordinate models of varying sizes with human experts to balance accuracy, cost, and abstention under uncertainty. However, single-model tiers at each stage often struggle with ambiguous queries, triggering premature escalations to costlier models or experts due to under-confide…

• KumoRFM-2: Scaling Foundation Models for Relational Learning

  Valter Hudovernik, Federico L\'opez, Vid Kocijan, Akihiro Nitta, Jan Eric Lenssen, Jure Leskovec, Matthias Fey · 15 avril 2026

  We introduce KumoRFM-2, the next iteration of a pre-trained foundation model for relational data. KumoRFM-2 supports in-context learning as well as fine-tuning and is applicable to a wide range of predictive tasks. In contrast to tabular foundation models, KumoRFM-2 natively operates on relational d…

• Policy-Invisible Violations in LLM-Based Agents

  Jie Wu, Ming Gong · 15 avril 2026

  LLM-based agents can execute actions that are syntactically valid, user-sanctioned, and semantically appropriate, yet still violate organizational policy because the facts needed for correct policy judgment are hidden at decision time. We call this failure mode policy-invisible violations: cases in …

• Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning

  Xiaoxue Han, Libo Zhang, Zining Zhu, Yue Ning · 15 avril 2026

  We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predictions are made based on the activation of these concepts. Unlike existing inter…

• RoleMAG: Learning Neighbor Roles in Multimodal Graphs

  Yilong Zuo, Xunkai Li, Zhihan Zhang, Ronghua Li, Guoren Wang · 15 avril 2026

  Multimodal attributed graphs (MAGs) combine multimodal node attributes with structured relations. However, existing methods usually perform shared message passing on a single graph and implicitly assume that the same neighbors are equally useful for all modalities. In practice, neighbors that benefi…

• Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs

  Alkid Baci, Luke Friedrichs, Caglar Demir, N'Dah Jean Kouagou, Axel-Cyrille Ngonga Ngomo · 15 avril 2026

  Knowledge graph embedding (KGE) models perform well on link prediction but struggle with unseen entities, relations, and especially literals, limiting their use in dynamic, heterogeneous graphs. In contrast, pretrained large language models (LLMs) generalize effectively through prompting. We reformu…

• Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting

  Shuai Wang, Xixi Wang, Yinan Yu · 15 avril 2026

  Large Language Models (LLMs) have shown remarkable capabilities across various tasks but remain prone to hallucinations in knowledge-intensive scenarios. Knowledge Base Question Answering (KBQA) mitigates this by grounding generation in Knowledge Graphs (KGs). However, most multi-hop KBQA methods re…

• Learning to accelerate distributed ADMM using graph neural networks

  Henri Doerks, Paul H\"ausner, Daniel Hern\'andez Escobar, Jens Sj\"olund · 15 avril 2026

  Distributed optimization is fundamental to large-scale machine learning and control applications. Among existing methods, the alternating direction method of multipliers (ADMM) has gained popularity due to its strong convergence guarantees and suitability for decentralized computation. However, ADMM…

• KG-Reasoner: A Reinforced Model for End-to-End Multi-Hop Knowledge Graph Reasoning

  Shuai Wang, Yinan Yu · 15 avril 2026

  Large Language Models (LLMs) exhibit strong abilities in natural language understanding and generation, yet they struggle with knowledge-intensive reasoning. Structured Knowledge Graphs (KGs) provide an effective form of external knowledge representation and have been widely used to enhance performa…

• Building evidence-based knowledge bases from full-text literature for disease-specific biomedical reasoning

  Chang Zong, Sicheng Lv, Si-tu Xue, Huilin Zheng, Jian Wan, Lei Zhang · 15 avril 2026

  Biomedical knowledge resources often either preserve evidence as unstructured text or compress it into flat triples that omit study design, provenance, and quantitative support. Here we present EvidenceNet, a disease-specific dataset of record-level evidence collections and corresponding graph repre…

• AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

  Haoyu Huang, Hong Ting Tsang, Jiaxin Bai, Xi Peng, Gong Zhang, Yangqiu Song · 14 avril 2026

  Retrieval-augmented generation (RAG) has shown some success in augmenting large language models (LLMs) with external knowledge. However, as a non-parametric knowledge integration paradigm for LLMs, RAG methods heavily rely on external retrieval modules and the retrieved textual context prior. Especi…

• Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks

  Xinping Yi · 14 avril 2026

  Graph neural networks have demonstrated excellent applicability to a wide range of domains, including social networks, biological systems, recommendation systems, and wireless communications. Yet a principled theoretical understanding of their generalization behavior remains limited, particularly fo…

• CID-TKG: Collaborative Historical Invariance and Evolutionary Dynamics Learning for Temporal Knowledge Graph Reasoning

  Shuai-Long Lei, Xiaobin Zhu, Jiarui Liang, Guoxi Sun, Zhiyu Fang, Xu-Cheng Yin · 14 avril 2026

  Temporal knowledge graph (TKG) reasoning aims to infer future facts at unseen timestamps from temporally evolving entities and relations. Despite recent progress, existing approaches still suffer from inherent limitations due to their inductive biases, as they predominantly rely on time-invariant or…

• Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing

  Zhiheng Zhou, Mengyao Zhou, Xixun Lin, Xingqin Qi, Guiying Yan · 14 avril 2026

  Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNNs often suffer from shallow propagation, oversmoothing, and limited adaptability to complex hypergraph structures. In th…

• A Temporally Augmented Graph Attention Network for Affordance Classification

  Ami Chopra, Supriya Bordoloi, Shyamanta M. Hazarika · 14 avril 2026

  Graph attention networks (GATs) provide one of the best frameworks for learning node representations in relational data; but, existing variants such as Graph Attention Network (GAT) mainly operate on static graphs and rely on implicit temporal aggregation when applied to sequential data. In this pap…

• CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models

  Linggang Kong, Lei Wu, Yunlong Zhang, Xiaofeng Zhong, Zhen Wang, Yongjie Wang, Yao Pan · 14 avril 2026

  Despite the groundbreaking advancements made by large language models (LLMs), hallucination remains a critical bottleneck for their deployment in high-stakes domains. Existing classification-based methods mainly rely on static and passive signals from internal states, which often captures the noise …

• DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation

  Yang Yan, Qiuyan Wang, Tianjin Huang, Qiudong Yu, Kexin Zhang · 14 avril 2026

  Graph Neural Network pretraining is pivotal for leveraging unlabeled graph data. However, generalizing across heterogeneous domains remains a major challenge due to severe distribution shifts. Existing methods primarily focus on intra-domain patterns, failing to disentangle task-relevant invariant k…

• CircuitSynth: Reliable Synthetic Data Generation

  Zehua Cheng, Wei Dai, Jiahao Sun, Thomas Lukasiewicz · 14 avril 2026

  The generation of high-fidelity synthetic data is a cornerstone of modern machine learning, yet Large Language Models (LLMs) frequently suffer from hallucinations, logical inconsistencies, and mode collapse when tasked with structured generation. Existing approaches, such as prompting or retrieval-a…

• Exploring Structural Complexity in Normative RAG with Graph-based approaches: A case study on the ETSI Standards

  Aiman Al Masoud, Marco Arazzi, Simone Germani, Antonino Nocera · 14 avril 2026

  Industrial standards and normative documents exhibit intricate hierarchical structures, domain-specific lexicons, and extensive cross-referential dependencies, which making it challenging to process them directly by Large Language Models (LLMs). While Retrieval-Augmented Generation (RAG) provides …

• GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators

  Mattia Rigotti, Nicholas Thumiger, Thomas Frick · 14 avril 2026

  Adapting transformer positional encodings to graphs and meshes faces a fundamental tension: exact spectral methods require cubic-complexity eigendecomposition and inadvertently break gauge invariance through numerical solver artifacts, while existing efficient approximations sacrifice gauge symmetry…