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

Xuhui Jiang, Chengjin Xu, Yinghan Shen, Yuanzhuo Wang, Fenglong Su, Zhichao Shi, Fei Sun, Zixuan Li, Jian Guo, Huawei Shen

Keywords: Knowledge Graphs, Entity Alignment, Graph Neural Networks

TL;DR: We present two datasets for entity alignment in highly heterogeneous KGs, highlighting existing EA methods' limitations. We also introduce Simple-HHEA, a simple but effective framework, with experiments to inform future practical EA design.

Abstract:

The flourishing of knowledge graph (KG) 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 practical lies in their adaptability and efficiency to varying information quality conditions, as well as their capability to capture patterns across HHKGs.
The datasets and source code are available at \textit{https://anonymous.4open.science/r/HHEA/}.

Track: Semantics and Knowledge

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: Yes

Submission Number: 2540