Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets

TL;DR

This paper investigates entity alignment in highly heterogeneous knowledge graphs, introduces new datasets that reflect real-world complexity, and evaluates existing methods, revealing their limitations and proposing a more adaptable approach for practical scenarios.

Contribution

It introduces two new HHKG datasets that better mimic real-world heterogeneity and provides an in-depth analysis of existing EA methods' performance on these datasets.

Findings

Existing GNN-based EA methods perform poorly on HHKGs.

Structure information is hard to exploit in practical HHKGs.

Adaptable, multi-information integration improves EA performance.

Abstract

The flourishing of knowledge graph applications has driven the need for entity alignment (EA) across KGs. However, the heterogeneity of practical KGs, characterized by differing scales, structures, and limited overlapping entities, greatly surpasses that of existing EA datasets. This discrepancy highlights an oversimplified heterogeneity in current EA datasets, which obstructs a full understanding of the advancements achieved by recent EA methods. In this paper, we study the performance of EA methods in practical settings, specifically focusing on the alignment of highly heterogeneous KGs (HHKGs). Firstly, we address the oversimplified heterogeneity settings of current datasets and propose two new HHKG datasets that closely mimic practical EA scenarios. Then, based on these datasets, we conduct extensive experiments to evaluate previous representative EA methods. Our findings reveal that, in aligning HHKGs, valuable structure information can hardly be exploited through message-passing and aggregation mechanisms. This phenomenon leads to inferior performance of existing EA methods, especially those based on GNNs. These findings shed light on the potential problems associated with the conventional application of GNN-based methods as a panacea for all EA datasets. Consequently, in light of these observations and to elucidate what EA methodology is genuinely beneficial in practical scenarios, we undertake an in-depth analysis by implementing a simple but effective approach: Simple-HHEA. This method adaptly integrates entity name, structure, and temporal information to navigate the challenges posed by HHKGs. Our experiment results conclude that the key to the future EA model design in practice lies in their adaptability and efficiency to varying information quality conditions, as well as their capability to capture patterns across HHKGs.