3 papers
cs.LG2026
A Unified Benchmark for Evaluating Knowledge Graph Construction Methods and Graph Neural Networks
Othmane Kabal, Mounira Harzallah, Fabrice Guillet +2
Knowledge graphs automatically constructed from text are increasingly used in real-world applications. However, their inherent noise, fragmentation, and semantic inconsistencies si…
cs.LG2026
Robustness of Graph Self-Supervised Learning to Real-World Noise: A Case Study on Text-Driven Biomedical Graphs
Othmane Kabal, Mounira Harzallah, Fabrice Guillet +2
Graph Self-Supervised Learning (GSSL) offers a powerful paradigm for learning graph representations without labeled data. However, existing work assumes clean, manually curated gra…
cs.CL2026
Diagnosing and Mitigating Semantic Inconsistencies in Wikidata's Classification Hierarchy
Shixiong Zhao, Hideaki Takeda
Wikidata is currently the largest open knowledge graph on the web, encompassing over 120 million entities. It integrates data from various domain-specific databases and imports a s…