Type Information-Assisted Self-Supervised Knowledge Graph Denoising

2025-03-13

AI Summary

Knowledge graph (KG) auto-generation often introduces noise, and existing detection methods rely on external facts, logical rules, or structural embeddings—limiting their robustness due to entity alignment errors, poor rule generalizability, and structural overfitting. To address this, we propose a fully self-supervised denoising framework that requires no external supervision, handcrafted rules, or alignment annotations. Our approach uniquely models type consistency between entities and relations as an intrinsic self-supervised signal. It employs a type-aware encoder-decoder architecture that performs topology-aware, type-dependent reasoning, and identifies noisy triples via reconstruction error. Crucially, the method implicitly supports knowledge compression and completion. Extensive experiments on multiple real-world KGs demonstrate significant improvements in noise detection accuracy. Results validate type consistency as a robust, generalizable signal for KG denoising—offering a principled alternative to conventional supervision- or rule-based paradigms.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Unsupervised & Self-Supervised Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise detection often rely on external facts, logical rule constraints, or structural embeddings. These methods are often challenged by imperfect entity alignment, flexible knowledge graph construction, and overfitting on structures. In this paper, we propose to exploit the consistency between entity and relation type information for noise detection, resulting a novel self-supervised knowledge graph denoising method that avoids those problems. We formalize type inconsistency noise as triples that deviate from the majority with respect to type-dependent reasoning along the topological structure. Specifically, we first extract a compact representation of a given knowledge graph via an encoder that models the type dependencies of triples. Then, the decoder reconstructs the original input knowledge graph based on the compact representation. It is worth noting that, our proposal has the potential to address the problems of knowledge graph compression and completion, although this is not our focus. For the specific task of noise detection, the discrepancy between the reconstruction results and the input knowledge graph provides an opportunity for denoising, which is facilitated by the type consistency embedded in our method. Experimental validation demonstrates the effectiveness of our approach in detecting potential noise in real-world data.

Problem

• Detects noise in knowledge graphs using type consistency.
• Avoids issues like imperfect entity alignment and overfitting.
• Proposes a self-supervised method for knowledge graph denoising.

Innovation

• Self-supervised denoising using type consistency
• Encoder-decoder model for type dependency representation
• Noise detection via reconstruction discrepancy analysis