← 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 9 papers for 2026-07-09

STAGformer: A Spatio-temporal Agent Graph Transformer for Micro Mobility Demand Forecasting
GNN Graph Learning

STAGformer introduces a Spatio-Temporal Agent Graph Transformer with a two-step agent attention mechanism. A small set of learnable spatial and temporal agent tokens first aggregate global information and then broadcast it, enabling efficient global modeling with linear computational complexity for station-level bike-sharing demand forecasting. The model effectively handles complex spatio-temporal dependencies in large urban networks.

Generative Diffusion Models of Stochastic Graph Signals
Graph Learning

This work unifies sampling of stochastic graph signals under conditional distributions using diffusion models, addressing the gap where previous methods often regress to the conditional mean. It formulates conditional graph signal generative modeling to sample diverse realizations from the conditional law. The framework is applicable to tasks such as recommender systems, financial forecasting, and wireless network optimization.

Structural Adversarial Attacks on Relational Deep Learning under Integrity Constraints
GNN Graph Learning

The paper studies the adversarial robustness of Relational Deep Learning (RDL) on relational databases modeled as heterogeneous temporal graphs with PK-FK dependencies. It analyzes white-box perturbations to the graph under integrity constraints and examines how such perturbations affect model performance. The work provides insights into robustness and potential defense strategies for relational learning pipelines.

Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
GNN Graph Learning

Hypergraph neural networks capture higher-order relations, but their predictive uncertainty is understudied. The paper introduces Hypergraph Neural Stochastic Diffusion (SDE) frameworks to quantify uncertainty arising from noisy attributes, ambiguous labels, and varying node-hyperedge incidences. This approach offers a principled way to estimate uncertainty in hypergraph-based predictions.

Asymmetric Focal Loss Improves Graph Neural Network Prediction of Drug-Drug Interactions
GNN Graph Learning

The authors propose an asymmetric focal loss (ClinicalFocal loss) integrated into a relation-aware graph convolutional network to improve drug–drug interaction (DDI) predictions. By emphasizing difficult positive interactions, the method enhances the detection of clinically significant polypharmacy side effects. The approach improves performance over standard binary cross-entropy training.

When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
Graph Learning LLM × Graph

The work introduces ARGTCA, where class-attribute pairs are modeled as nodes in a Symbolic Attribute Graph and a Graph Attention Network is trained to reason over their relations. This approach improves calibrated confidence in vision-language models (VLMs) when prompts are tuned, by incorporating relational attribute structure rather than treating attributes independently.

Stability of Flow Models for Graph Signals
GNN Graph Learning

This paper analyzes the stability of continuous normalizing flow models for graph signals, showing that permutation equivariance is preserved in flow models parameterized by GNNs. It studies how structural perturbations propagate through the dynamics and establishes stability properties for graph-based flow generation.

Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory
GNN Graph Learning

The authors present FB-GNN-MBE, a transferable framework that integrates a fragment-based GNN into many-body expansion theory to reproduce first-principles potential energy surfaces for large systems. The approach enables data-adaptive transfer learning to predict accurate PES across chemical systems.

InductWave: Inductive Multi-Hop Logical Query Answering on Knowledge Graphs
Knowledge Graph Graph Learning

InductWave tackles inductive multi-hop logical query answering on knowledge graphs, moving beyond transductive reasoning to handle unseen entities. It addresses queries inExistential First-Order Logic with conjunction, disjunction, and negation, enabling reasoning over entities not seen during training.