Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Weidong Bao, Yilin Wang, Ruyu Gao, Fangling Leng, Yubin Bao, Ge Yu

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.

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

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.
Paper Structure (21 sections, 6 equations, 4 figures, 3 tables)

This paper contains 21 sections, 6 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Rule and supervised-learning--based KGC.
  4. LLM-based KGC.
  5. Preliminaries
  6. Meta-Knowledge Base
  7. Task Definition: Incremental Knowledge Graph Construction
  8. Knowledge Graph State Definition
  9. Entity and Event Normalization
  10. Knowledge Increment Definition
  11. Methodology
  12. Stage 1: Dual-Track Extraction
  13. Stage 2: Governance Adjudication
  14. Stage 3: Schema Evolution
  15. Transactional Integration
  16. ...and 6 more sections

Figures (4)

  • Figure 1: Comparison of extraction paradigms for dynamic and complex knowledge. Traditional methods (Top) rely on predefined static schemas, forcing the model (depicted as the overwhelmed agent) to compress dynamic histories and complex events into simple triples. This results in severe semantic distortion and temporal ambiguity. In contrast, DIAL-KG (Bottom) introduces a Dual-Track Extraction mechanism. By routing simple attribute changes (Static Track) and complex structural changes (Event Track) separately, DIAL-KG achieves schema-free evolution, ensuring both temporal clarity and comprehensive context preservation.
  • Figure 2: Overall DIAL-KG framework.
  • Figure 3: Dual-Track Extraction .
  • Figure 4: Schema quality comparison. DIAL-KG achieves higher precision with lower redundancy.