#knowledge graphs
14 resultsFully Inductive Cardinality Estimation
Tim Schwabe, Lukas Ketzer, Maribel Acosta
The paper introduces FICE, a graph neural network‑based estimator that can predict the cardinalities of SPARQL Basic Graph Pattern queries on knowledge graphs it has never seen bef…
OptGraph: Large Language Models Enhanced Evolutionary Optimization Via Graph Retrieval-Augmented Generation
Xianchao Xiu, Jianhao Li, Huangyue Chen +1
The paper introduces OptGraph, a system that enhances automated evolutionary optimization by using large language models together with a graph‑based retrieval‑augmented generation…
Shapes from Examples: Foundations of Shape Learning in Recursive SHACL
Bente Gortworst, Cem Okulmus, Magdalena Ortiz +1
The paper studies automatic learning of SHACL shapes for knowledge graph validation by fitting positive and negative example nodes, focusing on a core SHACL fragment equivalent to…
GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
Maya Arseven, Anette Frank, Beni Egressy +2
The paper introduces a graph language model (GLM) based retriever for retrieval-augmented generation over knowledge graphs and compares it with GNN‑based and vector‑search retrieve…
GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
Ziyi Yang, Thanh-Son Nguyen, Tuan Anh Nguyen +1
The paper introduces GGC, a framework that lets a language model generate a SPARQL query, predicts if it needs fixing, and only corrects high‑risk cases, boosting accuracy and cutt…
SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions
Jennifer D'Souza, Sameer Sadruddin, Anisa Rula +23
The paper introduces SciSchema.org, a multidisciplinary collection of 16 expert‑annotated schemas for describing scientific processes in a structured way, created using a human‑in‑…
AuthentiCity: A Multi-Source Provenance-Aware Knowledge Graph and Benchmark for 3D City Models
Huynh Duc An Son Nguyen, Lukas Arzoumanidis, Youness Dehbi
AuthentiCity is a large, provenance‑aware knowledge graph that integrates authoritative, crowd‑sourced, and machine‑learned data for 3D city models across five global cities, enabl…
IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment
Xinran Liu, Shengtao Li, Shouqian Shi +2
The paper introduces IRIS, a training-free method that uses frozen large language models to generate stable identity signatures for entities, enabling direct similarity-based align…
Detecting Knowledge Inconsistencies Across Text, Tables, and Knowledge Graphs
Fanfu Wei, Thibault Ehrhart, Raphaël Troncy
The paper introduces Kontrast, a framework that automatically detects and categorizes inconsistencies between textual information, tables, and knowledge graphs by converting text t…
MedBeads: An AI-Native Clinical Context Graph Built from Immutable Beads and Reconstructable Clinical Links
Takahito Nakajima
The paper presents MedBeads, an AI‑native clinical context graph that stores immutable, hash‑identified clinical objects (Beads) in an append‑only, patient‑scoped structure and der…
Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge
A. Mayeux
The paper proposes a relational bridge database that links bibliographic metadata with formal proof libraries and introduces a formalization score to estimate how much of a publica…
NeuroGRIP: Retrieval-Augmented Graph Refinement for Knowledge-Grounded EEG Seizure Diagnosis
Lincan Li, Zheng Chen, Yushun Dong
NeuroGRIP is a framework that refines EEG-based graph neural network predictions for seizure diagnosis by retrieving and integrating clinical knowledge from a domain-specific knowl…
Knowledge Tectonics: A Geodynamic Inspired Framework for Modeling Epistemic Changes
Thomas Van Erven, Stelios Kontogiannis, Efstratios Kontopoulos +3
The paper proposes a geodynamic-inspired framework called Knowledge Tectonics to model and visualize how concepts and metadata evolve over time in semantic web knowledge graphs, de…
FAIR GraphRAG: A Retrieval-Augmented Generation Approach for Semantic Data Analysis
Marlena Flüh, Soo-Yon Kim, Carolin Victoria Schneider +1
The paper presents FAIR GraphRAG, a framework that combines Retrieval‑Augmented Generation with FAIR Digital Objects to enable graph‑based retrieval and question answering over bio…