← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 27 papers for 2026-05-27

Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
GNN Graph Learning

We propose CE-FedGNN, a framework for learning on coupled graphs in a federated setting where raw data cannot be shared. The method achieves communication efficiency and privacy guarantees while preserving cross-client linkage information without exchanging dense embeddings, enabling accurate GNN training across participants.

Dynamic Link Prediction with Temporally Enhanced Signed Graph Neural Networks
GNN Graph Learning

We address dynamic link prediction in temporal signed networks by introducing a modular temporal enhancement for signed GNNs. Our approach captures the evolution of both positive and negative relations while respecting balance-theoretic constraints, improving predictive performance on evolving graphs.

Generalist Graph Anomaly Detection via Prototype-Based Distillation
Graph Learning

We introduce ProMoS, the first unsupervised generalist GAD framework that learns a prototype-based distillation to produce transferable anomaly detectors across graphs. It reduces dependence on scarce annotations and avoids few-shot inference at test time, improving robustness to unseen anomaly patterns.

TED: Related Party Transaction guided Tax Evasion Detection on Heterogeneous Graph
Graph Learning

TED models tax evasion detection as a heterogeneous graph task guided by related party transactions. It exploits rich interactive information in tax scenarios beyond company-level statistics. The framework achieves improved detection accuracy on heterogeneous graphs.

What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction
GNN Graph Learning

This study asks what pharmacology can be inferred from molecular structure in toxicity prediction. Through a systematic case study centered on aspirin, we analyze explainability gaps in GNN-based toxicity models and taxonomy of what the structure cannot encode.

Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations
Knowledge Graph Graph Learning

We propose using a knowledge graph as a missing data layer for LLM-based industrial asset operations. A KG-backed data layer improves reasoning beyond flat documents, demonstrated on scenarios with a 781-node graph built from CouchDB/YAML/CSV data. We compare data-layer choices and show gains.

Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN
GNN Graph Learning

We present BSMS-GNN for efficient mesh-based physical simulation with multi-scale GNNs to address scaling and oversmoothing. It reduces reliance on manual coarse meshes by learning scalable multi-scale structures, enabling accurate simulations on large meshes.

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
GNN Graph Learning

We introduce Graph State-Space Models (GSSMs) that embed state-space computation directly into message-passing neural networks. This preserves permutation equivariance and efficiency while improving modeling of long-range temporal dependencies on graphs.

Learnable Kernel Density Estimation for Graphs and Its Application to Graph-Level Anomaly Detection
Graph Learning

LGKDE learns kernel density estimation for graphs by mapping each graph with a GNN into a distribution and learning the KDE. It combines graph kernels with KDE under learnable representations to improve graph-level anomaly detection.

Morphling: Fast, Fused, and Flexible GNN Training at Scale
GNN Graph Learning

Morphling delivers fast, fused, and scalable GNN training by designing specialized kernels that fuse irregular graph traversals with regular dense matmul. This reduces memory movement and intermediate allocations, enabling efficient training at scale.

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

We study MPLang, a declarative language for GNN-style computation, and characterize the expressive power of A-MPLang (without activations) via walk-summed features. For bounded activations, we show that all eventually constant activations yield the same numerical and Boolean expressive power, unifying prior results.

GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training
LLM × Graph Graph Learning

GraphDancer is a two-stage curriculum post-training framework that teaches LLMs to reason over graphs by interleaving natural language reasoning with graph function execution. It enables LLMs to explore graphs and perform precise graph-aware reasoning.

Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques
Graph Learning

This work introduces SVBCX for silicosis/pneumonia CXR classification and proposes a graph Transformer post-hoc modeling with ensemble techniques to boost performance.

Distributed Control of Network Systems in the Space of Stabilizing Graph Neural Network Policies
GNN Graph Learning

We study distributed control of networked systems by parameterizing GNN policies within a Youla-like framework, ensuring stability by design. The magnitude component uses a stable operator with a GNN on disturbances, while the direction component uses a GNN.

NeuroMambaLLM: Dynamic Graph Learning of fMRI Functional Connectivity in Autistic Brains Using Mamba and Language Model Reasoning
LLM × Graph Graph Learning

NeuroMambaLLM combines dynamic graph learning of fMRI functional connectivity using Mamba with language model reasoning to support autism neuroscience analysis. It models transient FC dynamics and leverages LLMs to interpret results.

PhyGHT: Physics-Guided HyperGraph Transformer for Signal Purification at the HL-LHC
GNN Graph Learning

PhyGHT introduces Physics-Guided HyperGraph Transformer to purify signals at HL-LHC by modeling pileup as a hypergraph with physics priors, improving signal extraction.

GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GNN

GraphIP-Bench provides a unified benchmark to evaluate GNN model extraction attacks and defenses under consistent threat models, enabling fair comparisons of theft resistance and defense effectiveness.

Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs
Knowledge Graph LLM × Graph

Helicase presents uncertainty-guided, autonomous multi-agent LLMs to construct supply chain knowledge graphs from fragmented web sources via multi-hop reasoning, enabling reliable decision support.

Boosting Knowledge Graph Foundation Models via Enhanced Negative Sampling
Knowledge Graph

We propose enhanced negative sampling methods to train KG foundation models, improving zero-shot KG completion on unseen KGs with different relation vocabularies. Empirical results show better generalization.

Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
Knowledge Graph LLM × Graph

Chat-ISV is a KG-enhanced multi-agent Q&A system for steel industry VOC governance. It constructs a Neo4j knowledge graph from literature (27180 nodes, 81779 relations) to provide traceable reasoning and reliable decision support.

The Compressive Knowledge Graph Hypothesis: Which Graph Facts Matter for Scientific Hypothesis Generation?
Knowledge Graph

This study examines how different facts in knowledge graphs influence hypothesis generation for battery materials across multiple LLMs (Mistral-7B, Llama-3.1-70B, Gemini 2.5 Flash). The authors perturb local KGs by varying density, ontology richness, topology, and control structure, and assess outputs with both provided-graph and fixed-reference metrics. They find that KG utility is selective and highly model-dependent: adding graph context changes outputs, but there is no universal mapping from a graph property to improved hypothesis quality.

RAGEAR: Retrieval-Augmented Graph-Enhanced Academic Recommender
Knowledge Graph Graph Learning

RAGEAR is a neurosymbolic recommender for academic courses that combines dense retrieval over full lecture transcripts with a symbolic Knowledge Graph capturing courses, lessons, transcript chunks, credits, study plans, and curricular constraints. The Knowledge Graph enables symbolic filtering and contextualization based on constraints such as credits, disciplines, study plans, and prerequisites, delivering more controllable and explainable recommendations than metadata-only baselines.

OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion
Graph Learning Knowledge Graph

OMD-GraphRAG extends GraphRAG with three core innovations: Ontology-Guided Knowledge Extraction using predefined ontologies or schemas to improve extraction precision; Multi-Dimensional Clustering to organize retrieved knowledge across modalities and queries; and Dual-Channel Fusion that combines graph-structured signals with text-based signals for better retrieval and reasoning. The framework targets addressing challenges in knowledge extraction precision, community report integrity, and retrieval performance in complex reasoning tasks.

Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning
Knowledge Graph LLM × Graph

Self-signals Driven Multi-LLM Debate for Efficient and Accurate Reasoning introduces a self-signal-guided multi-LLM debate (MAD) approach that uses internal generation signals (e.g., token logits and attention) to steer discussions, reducing redundancy from relying solely on external debate graphs or judges. This self-signal integration improves efficiency and accuracy in multi-agent reasoning.

SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
GNN Graph Learning

SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs presents a self-evolving agentic learning framework to improve knowledge-graph-based conversational QA. It addresses coreference resolution, contextual dependency, and complex logical reasoning while reducing inaccuracies and computational costs associated with generating and parsing complex logical forms.

MuNet: A Mutualistic Network for Joint 3D Human Mesh Recovery and 3D Clothed Human Reconstruction from Single Images
GNN Graph Learning

MuNet proposes a mutualistic network for joint 3D human mesh recovery and 3D clothed human reconstruction from single images, enabling the two related tasks to benefit from shared representations. The approach uses 2-manifold graphs to model geometric relations and perform joint optimization, yielding improvements over separate-task baselines.

Rethinking Agentic RAG: Toward LLM-Driven Logical Retrieval Beyond Embeddings
GNN Graph Learning LLM × Graph

Rethinking Agentic RAG argues for moving beyond embedding-based retrieval toward LLM-driven logical retrieval. It emphasizes that agentic RAG should enable LLMs to construct structured, logical queries and reason over retrieved results, rather than relying solely on dense embeddings or back-end retrieval complexity. The paper outlines a framework for delegating query construction to the LLM to improve retrieval efficiency and reasoning quality.