A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs

Abstract

Entity alignment seeks to find entities in different knowledge graphs (KGs) that refer to the same real-world object. Recent advancement in KG embedding impels the advent of embedding-based entity alignment, which encodes entities in a continuous embedding space and measures entity similarities based on the learned embeddings. In this paper, we conduct a comprehensive experimental study of this emerging field. This study surveys 23 recent embeddingbased entity alignment approaches and categorizes them based on their techniques and characteristics. We further observe that current approaches use different datasets in evaluation, and the degree distributions of entities in these datasets are inconsistent with real KGs. Hence, we propose a new KG sampling algorithm, with which we generate a set of dedicated benchmark datasets with various heterogeneity and distributions for a realistic evaluation. This study also produces an open-source library, which includes 12 representative embedding-based entity alignment approaches. We extensively evaluate these approaches on the generated datasets, to understand their strengths and limitations. Additionally, for several directions that have not been explored in current approaches, we perform exploratory experiments and report our preliminary findings for future studies. The benchmark datasets, open-source library and experimental results are all accessible online and will be duly maintained.

Integration of Semantic and Topological Structural Similarity Comparison for Entity Alignment without Pre-Training

“…The statistics of these selected datasets are summarized in Table 1. DBP15K(EN-FR) and DBP-WIK [33] are two simple EA datasets, which share a similar structure for their KG pairs, with an equivalent number of entities. Furthermore, the structural features, such as the number of facts and density, of these two datasets closely align.…”

Knowledge Graphs for Seismic Data and Metadata

“…If one earthquake appears in two catalogs, our model will regard them as two independent event records. Subsequent entity resolution-or deduplication-may be used to associate event records with a unique seismic event (Sun et al, 2020;Obraczka et al, 2021). Each entity has a mandatory and single-valued reference scheme, which we verbalize as: E2.…”

UVA Resources for the Biomedical Vocabulary Alignment at Scale in the UMLS Metathesaurus

“…There are several families of KG embedding techniques [15,36]. They aim to map entities and relations into low-dimensional vectors while capturing their structural and semantic meanings [40], and have shown to benefit a variety of knowledge-driven tasks [20].…”

“…We evaluated their performance in the UVA task, but did not benchmark them against other forms of graph representation techniques [15,43]. Many embedding techniques listed in [36] are not selected due to the specific characteristics of context in our datasets, e.g., having no attributes/literals (but 10 techniques in [36] including AttrE [37] and KDCoE [5] leveraging attributes), having English-only (but MTransE [6] leveraging multilingual), or very large (RDGCN [42] being not scalable).…”