Year: 2025
Type: conference-paper
Abstract: Uncertainty quantification in Knowledge Graph Embedding (KGE) methods is crucial for ensuring the reliability of downstream applications.A recent work applies conformal prediction to KGE methods, providing uncertainty estimates by generating a set of answers that is guaranteed to include the true answer with a predefined confidence level.However, existing methods provide probabilistic guarantees averaged over a reference set of queries and answers (marginal coverage guarantee).In highstakes applications such as medical diagnosis, a stronger guarantee is often required: the predicted sets must provide consistent coverage per query (conditional coverage guarantee).We propose CONDKGCP, a novel method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.CONDKGCP merges predicates with similar vector representations and augments calibration with rank information.We prove the theoretical guarantees and demonstrate empirical effectiveness of CONDKGCP by comprehensive evaluations.
Authors: Yuqicheng Zhu, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Evgeny Kharlamov, Steffen Staab
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Awards: SFB 1574: Kreislauffabrik für das ewige Produkt, G434337789, Scalable and Quantum Resilient Heterogeneous Edge Computing enabling Trustworthy AI, Automated Verification of Textual Claims, Enabling Data Enrichment Pipelines for AI-driven Business Products and Services, Extreme and Sustainable Graph Processing for Urgent Societal Challenges in Europe
OpenAlex ID: W4412888741