← Home

Daily arXiv Papers

Graph Neural Networks · Graph Learning · LLM × Graph
Conferences
Archives
2026-08-11 2026-08-10 2026-08-09 2026-08-08 2026-08-07 2026-08-06 2026-08-05 2026-08-04 2026-08-03 2026-08-02 2026-08-01 2026-07-31 2026-07-30 2026-07-29 2026-07-28 2026-07-27 2026-07-26 2026-07-25 2026-07-24 2026-07-23 2026-07-22 2026-07-21 2026-07-20 2026-07-19 2026-07-18 2026-07-17 2026-07-16 2026-07-15 2026-07-14 2026-07-13 2026-07-12 2026-07-11 2026-07-10 2026-07-09 2026-07-08 2026-07-07 2026-07-06 2026-07-05 2026-07-04 2026-07-03 2026-07-02 2026-07-01 2026-06-30 2026-06-29 2026-06-28 2026-06-27 2026-06-26 2026-06-25 2026-06-24 2026-06-23 2026-06-22 2026-06-21 2026-06-20 2026-06-19 2026-06-18 2026-06-17 2026-06-16 2026-06-15 2026-06-14 2026-06-13 2026-06-12 2026-06-11 2026-06-10 2026-06-09 2026-06-08 2026-06-07 2026-06-06 2026-06-05 2026-06-04 2026-06-03 2026-06-02 2026-06-01 2026-05-31 2026-05-30 2026-05-29 2026-05-28 2026-05-27 2026-05-26 2026-05-25 2026-05-24 2026-05-23 2026-05-22 2026-05-21 2026-05-20 2026-05-19 2026-05-18 2026-05-17 2026-05-16 2026-05-15 2026-05-14 2026-05-13 2026-05-12 2026-05-11 2026-05-10 2026-05-09 2026-05-08 2026-05-07 2026-05-06 2026-05-05 2026-05-04 2026-05-03 2026-05-02 2026-05-01 2026-04-30 2026-04-29 2026-04-28 2026-04-27 2026-04-26 2026-04-25 2026-04-24 2026-04-23 2026-04-22 2026-04-21 2026-04-20 2026-04-19 2026-04-18 2026-04-17 2026-04-16 2026-04-15 2026-04-14 2026-04-13 2026-04-12 2026-04-11 2026-04-10 2026-04-09 2026-04-08 2026-04-07 2026-04-06 2026-04-05 2026-04-04 2026-04-03 2026-04-02 2026-04-01 2026-03-31 2026-03-30 2026-03-29 2026-03-28 2026-03-27 2026-03-26 2026-03-25 2026-03-24 2026-03-23 2026-03-22 2026-03-21 2026-03-20 2026-03-19 2026-03-18 2026-03-17 2026-03-16 2026-03-15 2026-03-14 2026-03-13 2026-03-12 2026-03-11 2026-03-10 2026-03-09 2026-03-07 2026-03-06 2026-03-05 2026-03-04 2026-03-03 2026-03-02 2026-03-01 2026-02-28 2026-02-27 2026-02-26 2026-02-25 2026-02-24 2026-02-23 2026-02-22 2026-02-21 2026-02-20 2026-02-19 2026-02-18 2026-02-17 2026-02-16 2026-02-15 2026-02-14 2026-02-13 2026-02-12

Showing 17 papers for 2026-07-20

Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
Graph Learning

Multimodal-attributed graphs (MAGs) preserve modality-rich signals but often reside in privacy-restricted silos. Federated training is necessary to build broadly transferable models without sharing raw data. This paper outlines a topology-aware framework for aligning multimodal semantics across fragmented MAGs to enable federated foundation-model development.

From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks
GNN Graph Learning

Hypergraph neural networks gain expressive power with higher-order connections but suffer oversmoothing as depth increases due to strong multi-way mixing. We adopt a dynamical-systems perspective and develop a reaction-diffusion framework to understand and mitigate depth-induced oversmoothing. By defining hypergraph gradient and divergence, we view message passing as diffusion, and derive conditions under which pure diffusion causes signal decay, guiding depth-resistant design.

Knowledge-Assisted Multi-Graph Dependency Learning for Multivariate Time Series Anomaly Detection in Multi-Stage Industrial Processes
Graph Learning

Industrial processes generate multivariate time series across stages, with complex dependencies. Graph neural networks leverage data-driven graphs to model variable and stage dependencies for MTAD. This work introduces knowledge-assisted multi-graph dependency learning to better capture cross-variable and cross-stage relationships for improved anomaly detection in multi-stage processes.

Graph Coloring Approach to Solving Sudoku with Oscillatory Neural Networks
Graph Theory

Oscillatory Neural Networks (ONNs) offer physics-inspired computing with coupled oscillators to minimize an energy function. We formulate Sudoku as a Graph Coloring problem and adapt an existing ONN-based solver to a cheaper variant, adding a term that enforces color constraints, enabling efficient Sudoku solving via oscillator dynamics.

AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
GNN Graph Learning

AuditVotes introduces a provable defense framework for GNNs by integrating graph rewiring augmentation and conditional smoothing into randomized smoothing. The approach improves clean accuracy while delivering stronger certified robustness against adaptive attacks, bridging the accuracy-robustness trade-off in smoothing-based defenses.

Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspective
GNN Graph Learning

A causal perspective questions whether HGNNs are intrinsically effective for node classification, by distinguishing genuine causal effects from spurious correlations. The paper analyzes whether the benefits of heterogeneous GNNs come from the model architecture or from confounded signals, offering insights on when HGNNs truly help.

Analysis of Semi-Supervised Learning on Hypergraphs
Graph Learning

We analyze semi-supervised learning on random geometric hypergraphs, establishing asymptotic consistency in the large-data limit. We identify scaling regimes that ensure nontrivial label propagation instead of collapse to a constant, and show that discrete minimizers converge to the solution of a density-weighted p-Laplacian equation; a Higher-Order H extension is proposed.

Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
Graph Learning Graph Theory

Although UMAP is widely used for embeddings, its internal kNN graph encodes the data manifold in high dimensions. We show that this internal graph enables meaningful sensemaking using standard graph algorithms such as PageRank to identify representatives, structural roles, and communities, enhancing data understanding before projection.

MxGPS: Multiplex Graph Transformers for a Power Grid Foundation Model
GNN Graph Learning

MxGPS proposes multiplex graph transformers to address topology overfitting in power-grid foundation-model style tasks. Models trained on one grid degrade under topology shifts; multiplex graphs promote generalization across different topologies by learning shared representations. The paper introduces MxGPS as a scalable foundation-model for power-grid problems.

Pretrained Event Classification Model for High Energy Physics Analysis
GNN Graph Learning

Presented is a pretrained event classification model for high-energy physics built on graph neural networks and trained on 120 million simulated proton-proton collision events spanning 12 physics processes. The model is evaluated on seven tasks, including new physics processes not encountered during pretraining.

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction
Graph Learning

Causal-Audit: Explicit and Auditable Graph-based Reasoning via Target-Aware Causal Chain Construction

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion
Knowledge Graph Graph Learning

MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection
GNN Graph Learning

HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection

A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data
GNN Graph Learning

A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data

Learning the Brain's Dynamics as a Port-Hamiltonian System: A GNN-Surrogate Metriplectic Twin for Non-Equilibrium Cortical Dynamics and Closed-Loop Neuromodulation
GNN Graph Learning

Learning the Brain's Dynamics as a Port-Hamiltonian System: A GNN-Surrogate Metriplectic Twin for Non-Equilibrium Cortical Dynamics and Closed-Loop Neuromodulation

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs
Graph Learning

Code-MUE: Measuring Code LLMs' Uncertainty through Execution-based Semantic Interaction Graphs

Efficient and Effective In-place Graph-based Vector Index Updates
Graph Learning

Efficient and Effective In-place Graph-based Vector Index Updates