← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph

Showing 35 papers for 2026-05-05

PhaseNet++: Phase-Aware Frequency-Domain Anomaly Detection for Industrial Control Systems via Phase Coherence Graphs
Graph Learning

PhaseNet++ proposes phase-aware anomaly detection in the frequency domain for industrial control systems. It argues that phase information from time-frequency transforms provides a complementary detection modality to amplitude-based features and leverages phase coherence graphs to model inter-sensor relationships for anomaly detection.

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
GNN Graph Learning

This survey reviews graph rewiring techniques to mitigate over-squashing and over-smoothing in GNNs. It discusses topology-aware rewiring methods, provides a taxonomy of approaches, and highlights open challenges and future research directions.

Topological Neural Tangent Kernel
Graph Learning

TopoNTK introduces an infinite-width kernel for simplicial message passing on edge features, enabling higher-order interactions beyond pairwise graphs. It combines lower and upper Hodge interactions to capture multi-way relationships in relational systems.

Spectral Graph Sparsification Preserves Representation Geometry in Graph Neural Networks
GNN Graph Theory Graph Learning

We study whether spectral graph sparsification preserves representation geometry in polynomial-filter GNNs. The main result shows that an epsilon-spectral sparsifier induces only O(epsilon) perturbations in polynomial graph filters and in the learned representations across layers, preserving the overall geometry.

Rethinking Multi-Label Node Classification: Do Tuned Classic GNNs Suffice?
GNN Graph Learning

This paper rethinks multi-label node classification by asking whether carefully tuned classic full-graph GNNs can match specialized label-aware models. Through systematic experiments, it shows strong baseline performance for well-tuned GNNs, challenging the need for complex label-aware designs.

Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
LLM × Graph

Evaluating LLMs on large-scale graph property estimation via random walks to probe reasoning abilities on graph algorithms. The study benchmarks how well LLMs can infer graph properties and perform related graph-analytic reasoning tasks.

Mesh Based Simulations with Spatial and Temporal awareness
GNN Graph Learning

Identifies bottlenecks in ML surrogates for CFD, noting that node-wise supervision and explicit Euler time-stepping ignore stiff dynamics and local flux continuity. Proposes incorporating spatial-temporal awareness in mesh-based surrogates to address these gaps.

Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction
GNN Graph Learning

FedTGNN-SS is a privacy-preserving federated semi-supervised GNN framework with prototype-guided pseudo-labeling for gestational diabetes prediction. It enables cross-hospital learning with limited labels while protecting patient privacy.

Misclassification Rate and Privacy-Utility Trade-offs in Graph Convolutional Networks via Subsampling Stability
GNN Graph Learning

This work studies differential privacy in GCNs via subsampling stability, deriving upper bounds on misclassification rate as a function of the subsampling probability ps. It analyzes the privacy-utility trade-off and identifies feasible ranges of ps for meaningful guarantees.

Large margin classifier with graph-based adaptive regularization
Graph Learning Graph Theory

This paper introduces a large-margin classifier with graph-based adaptive regularization on Gabriel graphs. By using per-class regularization hyperparameters, it better handles outliers and class imbalance by shaping margins and decision thresholds.

TIJERE: A Novel Threat Intelligence Joint Extraction Model Based on Analyst Expert Knowledge
Knowledge Graph

TIJERE presents a novel threat intelligence joint extraction model that leverages analyst expert knowledge to jointly extract entities and relations from threat reports, addressing feature confusion, language ambiguity, and noise propagation.

H3: A Healthcare Three-Hop Index for Physician Referral Network Prediction
GNN Graph Learning

H3 proposes a healthcare three-hop index to predict physician referral networks, capturing indirect pathways through intermediate nodes to overcome sparsity, disassortative degree mixing, and hub-dominated topology.

Spatial-Temporal Learning-Based Distributed Routing for Dynamic LEO Satellite Networks
GNN Graph Learning

This spatial-temporal learning-based distributed routing framework for dynamic LEO satellite networks combines GAT, LSTM, and DQN within a POMDP framework to enable distributed routing decisions based on local observations.

Middle-mile logistics through the lens of goal-conditioned reinforcement learning
GNN Graph Learning

Middle-mile logistics is reformulated as a multi-objective goal-conditioned MDP, integrating graph neural networks with model-free reinforcement learning to extract compact feature graphs from the environment for routing parcels.

Learning Equivariant Neural-Augmented Object Dynamics From Few Interactions
GNN Graph Learning

PIEGraph couples analytical physics with graph neural networks to learn equivariant object dynamics from few interactions, enabling accurate modeling of both rigid and deformable bodies with improved data efficiency and long-horizon feasibility.

Fine-Grained Graph Generation through Latent Mixture Scheduling
Graph Learning Graph Theory

Fine-Grained Graph Generation through Latent Mixture Scheduling introduces a conditional variational autoencoder that dynamically aligns graph and property representations to enable fine-grained control over generated graphs.

GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data
Graph Learning

GraphLand evaluates graph machine learning models on diverse industrial data, arguing that current benchmarks cover limited domains and advocating evaluation of graph foundation models across varied datasets for robust transferability.

Effective Capacitance Modeling Using Graph Neural Networks
GNN Graph Learning

Effective Capacitance Modeling Using Graph Neural Networks applies GNNs to predict effective capacitance for VLSI timing analysis, enabling improved early-stage timing predictions and better placement/routing decisions.

Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation
Knowledge Graph LLM × Graph

Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation explores using LLMs to enrich medical concept representations with textual attributes, addressing missing cross-type dependencies in ontology resources.

On the Expressive Power of GNNs to Solve Linear SDPs
GNN

On the Expressive Power of GNNs to Solve Linear SDPs investigates what graph-based capacity is sufficient for recovering optimal SDP solutions, providing theoretical insights into the capabilities of GNN-based surrogates.

Ligandformer: A Graph Neural Network for Predicting Compound Property with Robust Interpretation
GNN Graph Learning

Ligandformer introduces a multi-layer self-attention graph neural network for predicting compound properties with interpretable attention. The model provides robust interpretation of QSAR predictions, enabling validation of explanations by chemists and offering heuristic guidance for structure optimization.

Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
GNN

This paper studies backdoor attacks on graphs that transfer across learning paradigms. It introduces promptable subgraph triggers to enhance cross-paradigm transferability and attack success across graph supervised, contrastive, and prompt-based learning, and evaluates the effectiveness under diverse GNN frameworks.

Recurrent Graph Neural Networks and Arithmetic Circuits
GNN

We define recurrent GNNs as Recurrent Arithmetic Circuits (RACs), generalizing beyond standard GNN architectures. RACs behave like memory-enabled arithmetic circuits, with memory gates storing information across iterations, enabling richer computation. We analyze their computational power and expressiveness relative to other models.

Hypergraph and Latent ODE Learning for Multimodal Root Cause Localization in Microservices
Graph Learning

HyperODE RCA combines hypergraph attention, latent ODEs, and multimodal cross-attention to localize root causes in microservice systems. It learns higher-order service interactions via differentiable hyperedges and models irregular observation dynamics with latent ODEs, enabling fine-grained RCA.

Scalable Context-Aware Graph Attention for Unsupervised Anomaly Detection in Large-Scale Mobile Networks
GNN

Introduces C-MTAD-GAT, a context-aware multivariate time-series graph attention model for unsupervised anomaly detection in large-scale mobile networks. It handles thousands of KPI time series, supports a single shared model, and is robust to context shifts and nonstationarity without labeled data.

Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment
GNN Graph Learning

Proposes Decoupled Relation Alignment to empower heterogeneous Graph Foundation Models on multi-domain heterogeneous graphs. Unlike global feature alignment, which distorts type-specific semantics, the approach decouples relation alignment from domain features to avoid Type Collapse and Relation Confusion, preserving topology while aligning cross-domain information.

Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs
Knowledge Graph

We introduce controllable hypothesis generation for abductive reasoning on knowledge graphs to reduce redundant or irrelevant hypotheses. The task adds controllability constraints and ranking incentives to steer generation toward relevant, high-quality hypotheses, enabling practical use in domains like clinical diagnosis and scientific discovery.

G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
Knowledge Graph Graph Learning

G-reasoner presents a foundation-model-based system for unified reasoning over graph-structured knowledge. It addresses limitations of static parametric knowledge in LLMs by using retrieval-augmented reasoning and graph-aware structure modeling, integrating GraphRAG-style retrieval with graph reasoning for knowledge-intensive tasks.

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
GNN Graph Learning

This survey reviews graph rewiring techniques to mitigate over-squashing and over-smoothing in GNNs. It categorizes methods (e.g., skip connections, edge rewiring, topology-aware propagation), discusses theoretical insights, empirical outcomes, and challenges for scalable, robust graph learning.

Semantic Level of Detail for Knowledge Graphs: Discovering Abstraction Boundaries via Spectral Heat Diffusion
Knowledge Graph Graph Theory

Introduces Semantic Level of Detail (SLoD) for knowledge graphs, enabling continuous control of abstraction boundaries via spectral heat diffusion. It provides a principled framework for navigating graphs at different granularities with formal guarantees about abstraction transitions.

KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation
Knowledge Graph

KG-First, LLM-Fallback introduces SkillGraph-Service, a hybrid microservice unifying competency resources into a provenance-preserving knowledge graph. It uses a KG-first approach with LLM fallback to support grounded skill search and explanation.

Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items
GNN Graph Learning

MMSC is a self-supervised, multi-modal relational item representation learning framework for inferring substitutable and complementary items. It leverages multi-modal content and behavior signals to overcome noisy supervision and long-tail data, producing robust item recommendations.

TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation
Knowledge Graph

TagRAG introduces a tag-guided hierarchical retrieval-augmented generation framework for knowledge graphs. Tags guide retrieval and enable efficient, scalable graph-aware generation, addressing inefficiencies and incremental updates in GraphRAG.

Graph Query Generation with Constraint-guided Large Language Agents
Knowledge Graph

UniQGen is a constraint-guided framework that uses LLM agents to extract and refine graph query clauses into executable queries across languages. It employs a variant of Chase & Backchase to ensure queries are correct and aligned with user intent.

U-HNSW: An Efficient Graph-based Solution to ANNS Under Universal Lp Metrics
Graph Theory

U-HNSW proposes an efficient graph-based ANNS method for universal Lp metrics. A single index supports queries across all p in (0,2], achieving better query efficiency than MLSH, with performance advantages on diverse p-values.