Does William Shakespeare REALLY Write Hamlet? Knowledge Representation Learning with Confidence
Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin

TL;DR
This paper introduces CKRL, a confidence-aware framework for knowledge graph learning that detects noise and improves representation quality by leveraging structural information, enhancing tasks like noise detection and KG completion.
Contribution
The paper proposes a novel confidence-aware learning framework that utilizes structural information to detect noise and improve knowledge graph representations.
Findings
Significant improvements in noise detection accuracy.
Enhanced performance in KG completion tasks.
Effective modeling of confidence improves triple classification.
Abstract
Knowledge graphs (KGs), which could provide essential relational information between entities, have been widely utilized in various knowledge-driven applications. Since the overall human knowledge is innumerable that still grows explosively and changes frequently, knowledge construction and update inevitably involve automatic mechanisms with less human supervision, which usually bring in plenty of noises and conflicts to KGs. However, most conventional knowledge representation learning methods assume that all triple facts in existing KGs share the same significance without any noises. To address this problem, we propose a novel confidence-aware knowledge representation learning framework (CKRL), which detects possible noises in KGs while learning knowledge representations with confidence simultaneously. Specifically, we introduce the triple confidence to conventional translation-based…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Topic Modeling · Data Quality and Management
