← 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 10 papers for 2026-08-07

THBKG: A Temporal Biomedical Knowledge Graph for Decision-Aligned Clinical Advancement Prediction
Knowledge Graph

THBKG introduces the Temporal Heterogeneous Biomedical Knowledge Graph, designed to capture evidence for target–disease linkages as they stood at specific past dates, enabling retrospective analysis of clinical advancement potential. The graph aims to help predict which programmes are most likely to advance by aligning evidence with the time of clinic entry, addressing a gap where prior knowledge graphs could not assemble such historic evidence profiles.

MetaboLLM: a metabolomics-specialized large language model for biochemical knowledge integration and predictive metabolite graph construction
Graph Learning

MetaboLLM is a metabolomics-specialized large language model achieved via continual pretraining, supervised fine-tuning, and structured retrieval, designed to integrate biochemical knowledge. It is paired with MetaboLLM-GIN, which converts generated descriptions into metabolite graphs for patient-level prediction using a graph neural network; across four backbone families, it outperforms baselines.

RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
Graph Learning

RxnCLF proposes a self-supervised contrastive learning framework for reaction representations to improve reactivity prediction when data are scarce and reaction space is large. It goes beyond traditional string-, fingerprint-, and graph-based encodings by capturing chemical transformations through contrastive objectives, helping generalize to new substrates.

Integrating Implicit and Explicit Relational Biases through Graph-Based Multiple Instance Learning: A Case Study in Skin Lesion Diagnosis
Graph Learning

The paper presents a dual-level relational framework for image classification that integrates implicit inter-patch relations learned via a convolutional masked autoencoder with explicit relational biases through a graph-based multiple instance learning scheme. Starting from EfficientNetB3 as a baseline, the approach leverages patch-based interactions to improve skin lesion diagnosis.

ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph Completion
Knowledge Graph Graph Learning

ViSR-KGC introduces Visual Subgraph Reasoning for multimodal knowledge graph completion by leveraging vision-language models to reason over subgraphs formed from visual and textual modalities. It addresses limitations of embedding-based approaches and prompt-based LLM reasoning by preserving structural topology and evidence in multimodal graphs.

Improving Interoperability among Defence and National Security Ontologies: Analysis and Evaluation Tasks
Knowledge Graph

The paper surveys and analyzes over 60 publicly available defence and national security ontologies to improve interoperability, and proposes a new OAEI track to evaluate interoperability tasks among these ontologies.

Universal Pathologies, Conditional Consequences: A Triple-Robustness Analysis of RAG for Multi-Hop Traceability
Graph Learning

The authors conduct a triple-robustness analysis of Retrieval-Augmented Generation (RAG) for multi-hop traceability, holding the retrieval architecture fixed while varying embedder, corpus, and judge across thousands of runs. They identify where over-citation and fidelity issues arise due to architectural choices and corpus selection, providing systematic insights into RAG reliability.

DREAM: LLM-based Dynamic Role-playing via Event-Aware Memory Graph
Graph Learning

DREAM introduces a dynamic role-playing framework for LLM-driven agents using an event-aware memory graph to ensure temporally consistent and causally grounded behaviors. The structured memory supports maintaining long-term narrative coherence and character personality across interactions.

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
Graph Learning

SkillZip proposes contract-preserving graph compression to scale agent skill libraries, addressing the need to expose the smallest executable context under limited context windows. It aims to compress at sub-skill granularity while preserving procedural contracts, ensuring executability and updatability of the library.

TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views
Graph Learning

TRW (TRACE-RealWorld) presents an auditable consistency contract for world models by treating predicted state as a materialized view and a physical observation as a read with expiration. It defines typed, calibrated claims about freshness and verifiable consequences, enabling adaptive刷新 of world models.