← 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 2026-06-20

Implicit Semantic-Aware Communication Based on Hypergraph Reasoning
Graph Learning

This work develops a semantic-aware communication framework that uses hypergraph reasoning to represent and transmit the meaning of source messages. By modeling semantic content as a hypergraph, the receiver can more reliably recover intended meaning, improving both communication efficiency and semantic inference accuracy. The approach aims to go beyond traditional bit-level transmission by embedding semantics into the graph structure and enabling implicit reasoning.

Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
Knowledge Graph

This paper tackles hallucinations in large language model–based knowledge graph reasoning. It proposes methods to detect when LLMs generate outputs that are inconsistent with retrieved or underlying KG facts, enhancing reliability of KG-assisted reasoning. The work includes an evaluation framework and strategies to mitigate hallucinations in knowledge graph reasoning tasks.

Protein Representation Learning with Secondary-Structure and Energy-Filtered Hydrogen-Bond Graphs
Graph Learning

We introduce a secondary-structure-aware graph neural network for protein representation learning that integrates secondary structure elements and energy-filtered hydrogen-bond graphs. This representation better captures folding principles beyond simple sequence adjacency or proximity. The approach improves protein modeling tasks by encoding recurring motifs and stabilizing interactions.

GDGU: A Gradient Difference-based Graph Unlearning Method for Cyberattack Localization in Electric Vehicle Charging Networks
GNN

GDGU introduces a gradient-difference-based graph unlearning method to localize cyberattacks in electric vehicle charging networks. It enables removal of specific training data contributions without full retraining, addressing privacy regulations. The method supports efficient, privacy-preserving re-training and improves robustness of attack localization on EV charging graphs.

FineREX: Fine-Tuned NER-RE for Human Smuggling Knowledge Graphs
Knowledge Graph

FineREX presents a fine-tuned NER-RE pipeline tailored for human smuggling knowledge graphs. By adapting an LLM to domain-specific entity and relation definitions, the approach improves extraction accuracy from court documents and accelerates KG construction. The pipeline emphasizes reliable, domain-focused information extraction over generic models.

AI Economist Agent: An Agentic Framework for Model-Grounded Economic Analysis with RAG, Knowledge Graphs, and Large Language Models
Knowledge Graph

The AI Economist Agent introduces a model-grounded, RAG-based framework that uses knowledge graphs and LLM-based agents to perform economic scenario analysis. It blends theory- and data-grounded reasoning, planning analyses, retrieving evidence, and selecting appropriate models to back its economic claims. The system aims to produce economist-grade analyses that are transparent and verifiable.

Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
GNN Graph Learning

This work tackles graph structural disentanglement by introducing Boundary Embedding Shaping with Adaptive Contrastive Learning. It recognizes that nodes near class boundaries suffer from amplified structural noise and proposes boundary-aware shaping to improve embedding quality. The approach uses adaptive contrasts to stabilize decisions and enhance robustness of GNNs.

FundaPod: A Multi-Persona Agent Pod Platform with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research
Knowledge Graph

FundaPod introduces a multi-persona agent pod platform with knowledge graph memory for AI-assisted fundamental investment research. The platform orchestrates multiple AI agents to gather evidence, compare viewpoints, and generate investment memos, guided by a knowledge graph that stores structured financial knowledge. It aims to enhance transparency, reusability, and verifiability in fundamental research.

KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data
Knowledge Graph Graph Learning

KG-SoftMAP proposes soft knowledge-graph priors for Bayesian network structure learning from sparse discrete data. It encodes domain knowledge as a finite-strength, weighted prior and combines the BDeu score with a logit-form prior to guide structure discovery. The approach improves structure recovery under data sparsity by integrating prior knowledge.