DIAL-KG: Schema-Free Incremental Knowledge Graph Construction via Dynamic Schema Induction and Evolution-Intent Assessment

2026-03-20

AI Summary

This work addresses the limitations of traditional knowledge graph construction, which relies on static, predefined schemas and struggles to efficiently handle dynamic data streams, often requiring costly full-graph reconstructions for updates. To overcome these challenges, the authors propose DIAL-KG, a novel framework that introduces a schema-agnostic, incremental construction mechanism. DIAL-KG integrates dual-track extraction (of both triples and events), employs a meta-knowledge base to govern fact adjudication, and dynamically induces and evolves its schema in a closed-loop knowledge fusion process. Experimental results demonstrate that this approach significantly outperforms existing static and semi-incremental methods, achieving state-of-the-art performance in both knowledge graph quality and schema induction accuracy.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Description Logics
• Machine Learning: Graph-based Machine Learning

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Knowledge Graphs (KGs) are foundational to applications such as search, question answering, and recommendation. Conventional knowledge graph construction methods are predominantly static, rely ing on a single-step construction from a fixed corpus with a prede f ined schema. However, such methods are suboptimal for real-world sce narios where data arrives dynamically, as incorporating new informa tion requires complete and computationally expensive graph reconstruc tions. Furthermore, predefined schemas hinder the flexibility of knowl edge graph construction. To address these limitations, we introduce DIAL KG, a closed-loop framework for incremental KG construction orches trated by a Meta-Knowledge Base (MKB). The framework oper ates in a three-stage cycle: (i) Dual-Track Extraction, which ensures knowledge completeness by defaulting to triple generation and switching to event extraction for complex knowledge; (ii) Governance Adjudica tion, which ensures the fidelity and currency of extracted facts to prevent hallucinations and knowledge staleness; and (iii) Schema Evolution, in which new schemas are induced from validated knowledge to guide subsequent construction cycles, and knowledge from the current round is incrementally applied to the existing KG. Extensive experiments demon strate that our framework achieves state-of-the-art (SOTA) performance in the quality of both the constructed graph and the induced schemas.

Problem

• Knowledge Graph Construction
• Dynamic Data
• Schema Flexibility
• Incremental Learning
• Static Schema Limitation

Innovation

• incremental knowledge graph construction
• schema evolution
• dynamic schema induction
• closed-loop framework
• governance adjudication