← 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 12 papers for 2026-07-13

Pattern-Aware Graph Neural Networks for Handling Missing Data
GNN Graph Learning

This work introduces pattern-aware graph neural networks that explicitly encode which features are missing alongside observed values, enabling the model to exploit informative missingness patterns. Four encoding strategies are studied—learned embeddings, frozen random embeddings, statistical features, and hierarchical encodings—and the approach improves performance over traditional imputation and baseline GNNs.

Model Agnostic Graph Prompt Learning for Crystal Property Prediction
GNN Graph Learning

They propose a model-agnostic graph prompt learning framework for crystal property prediction, using soft prompts to inject domain knowledge into GNN encoders without greatly increasing parameters. The approach reduces reliance on heavy feature engineering and enhances robustness and transferability across crystal-property tasks.

Power Flow Feasibility Assessment Using Variational Graph Autoencoders
GNN Graph Learning

A variational graph autoencoder is developed to assess the feasibility of power-flow solutions produced by AI solvers. Trained on the IEEE 118-bus system, the VGAE can identify feasible versus infeasible solutions, providing a reliability check for data-driven power system solvers.

Temporal Knowledge Graph Forecasting under Distribution Shifts: A Synthetic Evaluation
Knowledge Graph Graph Learning

This work studies temporal knowledge graph forecasting under distribution shifts with a synthetic TKG generator that encodes recurrence, homophily, and periodicity as data-generating mechanisms. This framework enables controlled evaluation of model robustness beyond standard benchmarks.

Graph Neural Networks for Scalable and Transferable Node Centrality Approximation
GNN Graph Learning

We investigate using graph neural networks to scalablely approximate node centralities such as betweenness and closeness, using exact centrality values as supervision and Kendall’s tau to measure ranking quality. The study also examines how well the learned representations transfer across different graph topologies, not just fit a single distribution.

Self-Improving Neural-Guided Pruning: A Graph Neural Network Framework for Scalable Mixed Bundle Pricing
GNN Graph Learning

Self-Improving Neural-Guided Pruning presents a GNN-guided pruning-then-optimization framework for scalable mixed bundle pricing, where pruning reduces the combinatorial bundle space before optimization for additively and non-additively valued bundles.

Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
Knowledge Graph

The paper argues that urban mining decisions should be defensible, proposing a combination of knowledge graphs and Explainable AI to support auditors in pre-demolition assessment with legibility, plausibility, sourcing, and contestability.

PRecG: Legal Precedent Retrieval with Graph Neural Networks and Rhetorical Role Segmentation
GNN Graph Learning

PRecG is a graph-based legal precedent retrieval approach that integrates graph neural networks with rhetorical role segmentation to capture document structure. By accounting for the contextual significance of legal entities and arguments, it improves retrieval performance over text-only representations.

Integrating Large Language Models and Graph Convolutional Networks for Semi-Supervised Image Classification
GNN Graph Learning

This work integrates large language models and graph convolutional networks for semi-supervised image classification, using language-informed relations to guide graph construction for GCN learning and improving performance.

Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Approach
Graph Learning

Conceptual Networks for cross-linguistic idiomatic expressions builds a feature-based graph of 160 idioms across eight languages, with binary conceptual features and Jaccard-based edge weights. Community detection reveals idioms cluster by conceptual schema rather than by language.

H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification
Graph Learning Graph Theory

H3Former introduces a hypergraph-based semantic-aware aggregation for fine-grained visual classification, employing a token-to-region framework and a hyperbolic hierarchical contrastive loss to improve discrimination among closely related categories.

RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches
GNN Graph Learning

RIS-Assisted Downlink Pinching-Antenna Systems investigates RIS-assisted multi-user downlink transmission and formulates sum-rate and energy-efficiency optimization under constraints on movable region of pinching antennas, total power, and RIS phase settings, proposing GNN-enabled optimization approaches.