Towards Temporal Knowledge Graph Alignment in the Wild

2025-07-19

AI Summary

To address the challenges of multi-scale temporal element entanglement and cross-source temporal structural imbalance in entity alignment for heterogeneous temporal knowledge graphs (TKGs) under realistic scenarios, this paper proposes HyDRA—a novel framework that reformulates TKG alignment as a multi-scale hypergraph retrieval-augmented generation problem. HyDRA introduces a scale-weaving coordination mechanism, enabling intra-scale interaction and cross-scale conflict detection to achieve robust alignment under fragmented temporal modeling and imbalanced event densities. To support systematic evaluation, we construct two new benchmark datasets: BETA and WildBETA. Extensive experiments demonstrate that HyDRA achieves state-of-the-art performance among 24 baselines, while maintaining high efficiency and scalability. This work significantly advances the practical deployment of heterogeneous TKG alignment.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Temporal Knowledge Graph Alignment (TKGA) seeks to identify equivalent entities across heterogeneous temporal knowledge graphs (TKGs) for fusion to improve their completeness. Although some approaches have been proposed to tackle this task, most assume unified temporal element standards and simplified temporal structures across different TKGs. They cannot deal with TKGA in the wild (TKGA-Wild), where multi-scale temporal element entanglement and cross-source temporal structural imbalances are common. To bridge this gap, we study the task of TKGA-Wild and propose HyDRA, a new and effective solution. HyDRA is the first to reformulate the task via multi-scale hypergraph retrieval-augmented generation to address the challenges of TKGA-Wild.In addition, we design a new scale-weave synergy mechanism for HyDRA, which incorporates intra-scale interactions and cross-scale conflict detection. This mechanism is designed to alleviate the fragmentation caused by multi-source temporal incompleteness and resolves inconsistencies arising from complex and uneven temporal event density distributions, thereby enhancing the model capacity to handle the intricacies of real-world temporal alignment. Finally, there is no standard benchmark that captures these challenges of TKGA-Wild and effectively evaluates existing methods. To this end, we formally propose to benchmark challenges for TKGA-Wild and validate the effectiveness of the method by establishing two new datasets(BETA and WildBETA). Extensive experiments on the new datasets and six representative benchmarks show that BETA and WildBETA better reflect real-world challenges. Meanwhile, HyDRA proposes a new paradigm for TKGA-Wild, consistently outperforming 24 competitive baselines, while maintaining strong efficiency and scalability.

Problem

• Identify equivalent entities across heterogeneous temporal knowledge graphs
• Address multi-scale temporal element entanglement and structural imbalances
• Develop benchmark datasets for real-world temporal alignment challenges

Innovation

• Multi-scale hypergraph retrieval-augmented generation for TKGA-Wild
• Scale-weave synergy mechanism for intra-scale and cross-scale interactions
• New benchmark datasets BETA and WildBETA for real-world validation