Embedding-based Entity Alignment Research Articles

Embedding-based entity alignment between multi-source temporal knowledge graphs

The goal of entity alignment is to identify entities in two multi-source knowledge graphs (KGs) that represent the same real-world object. Recent researches on multi-source entity alignment mainly concentrate on static KGs. In fact, temporal KGs have become valuable resources for numerous artificial intelligence applications, and entity alignment between multi-source temporal KGs is becoming more and more important. Current entity alignment models cannot support temporal tasks and fail to deal with the attributes with low literal similarity that share the same semantics through attribute embedding. Therefore, we propose a RDF (Resource Description Framework)-based model for representing temporal KGs, and an embedding-based entity alignment method for multi-source temporal KGs. This method computes for the similarity of temporal information and generates aligned attribute pairs in the predicate alignment module. We design an interactive module to make matched attributes and the matched entities help to find each other based on aligned attribute pairs. This module can calculate the similarity of attributes with low literal similarity. After getting the structure similarity of the structure embedding module, the final entity alignment result of temporal KGs is produced by the calculation of a binary linear regression function. Experimental results demonstrate that our proposed model outperforms existing approaches significantly.

Probing the Impacts of Visual Context in Multimodal Entity Alignment

We study the problem of multimodal embedding-based entity alignment (EA) between different knowledge graphs. Recent works have attempted to incorporate images (visual context) to address EA in a multimodal view. While the benefits of multimodal information have been observed, its negative impacts are non-negligible as injecting images without constraints brings much noise. It also remains unknown under what circumstances or to what extent visual context is truly helpful to the task. In this work, we propose to learn entity representations from graph structures and visual context, and combine feature similarities to find alignments at the output level. On top of this, we explore a mechanism which utilizes classification techniques and entity types to remove potentially un-helpful images (visual noises) during alignment learning and inference. We conduct extensive experiments to examine this mechanism and provide thorough analysis about impacts of the visual modality on EA.

Knowledge Graph Entity Alignment Using Relation Structural Similarity

Embedding-based entity alignment, which represents knowledge graphs as low-dimensional embeddings and finds entities in different knowledge graphs that semantically represent the same real-world entity by measuring the similarities between entity embeddings, has achieved promising results. However, existing methods are still challenged by the error accumulation of embeddings along multi-step paths and the semantic information loss. This paper proposes a novel embedding-based entity alignment method that iteratively aligns both entities and relations with high similarities as training data. Newly-aligned entities and relations are used to calibrate the corresponding embeddings in the unified embedding space, which reduces the error accumulation. To reduce the negative impact of semantic information loss, the authors propose to use relation structural similarity instead of embedding similarity to align relations. Experimental results on five widely used real-world datasets show that the proposed method significantly outperforms several state-of-the-art methods for entity alignment.

Ensemble Semi-supervised Entity Alignment via Cycle-Teaching

Entity alignment is to find identical entities in different knowledge graphs. Although embedding-based entity alignment has recently achieved remarkable progress, training data insufficiency remains a critical challenge. Conventional semi-supervised methods also suffer from the incorrect entity alignment in newly proposed training data. To resolve these issues, we design an iterative cycle-teaching framework for semi-supervised entity alignment. The key idea is to train multiple entity alignment models (called aligners) simultaneously and let each aligner iteratively teach its successor the proposed new entity alignment. We propose a diversity-aware alignment selection method to choose reliable entity alignment for each aligner. We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher. Besides, considering the influence of cycle-teaching order, we elaborately design a strategy to arrange the optimal order that can maximize the overall performance of multiple aligners. The cycle-teaching process can break the limitations of each model's learning capability and reduce the noise in new training data, leading to improved performance. Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed cycle-teaching framework, which significantly outperforms the state-of-the-art models when the training data is insufficient and the new entity alignment has much noise.

Entity alignment via summary and attribute embeddings

AbstractEntity alignment is the task of integrating heterogeneous knowledge among different knowledge graphs (KGs). KG is a popular way of storing facts about real-world entities. Unfortunately, a very limited number of the entities stored in different KGs are aligned. This paper presents an embedding-based entity alignment method that finds entity alignment by measuring the similarities between entity embeddings. Existing methods mainly focus on the relational structures and attributes information for the alignment process. Such methods fail while the entities have a fewer number of attributes or when the relational structure could not capture the meaningful representation of the entities. To address this problem, we propose EASAE, an entity alignment method using summary and attribute embeddings. We exploit the entity summary information available in KGs for entities’ summary embedding. To learn the semantics of the entity summary, we employ bidirectional encoder representations from transformers (BERT). Our model learns the representations of entities by using relational triples, attribute triples and summary as well. We perform experiments on real-world datasets, and the results indicate that the proposed approach outperformed the state-of-the-art models for entity alignment.

Revisiting Embedding-based Entity Alignment: A Robust and Adaptive Method

Entity alignment—the discovery of identical entities across different knowledge graphs (KGs)—is a critical task in data fusion. In this paper, we revisit existing entity alignment methods in practical and challenging scenarios. Our empirical studies show that current work has a low level of robustness to long-tail entities and the lack of entity names or relation triples. We aim to develop a robust and adaptive entity alignment method, and the availability of relations, attributes, or names is not required. Our method consists of an attribute encoder and a relation encoder, representing an entity by aggregating its attributes or relational neighbors using the attention mechanisms that can highlight the useful attributes and relations in end-to-end learning. To let the encoders complement each other and produce a coherent representation space, we propose adaptive embedding fusion via a gating mechanism. We consider four evaluation settings, i.e., the conventional setting with both relation and attribute triples, as well as three challenging settings without attributes, without relations, without both relations and names, respectively. Results show that our method can achieve state-of-the-art performance. Even in the most challenging setting without relations and names, our method can still achieve promising results while existing methods fail.

Combining embedding-based and symbol-based methods for entity alignment

The objective of entity alignment is to judge whether entities refer to the same object in the real world. Methods for entity alignment can be grossly divided into two groups: conventional symbol-based entity alignment methods and embedding-based entity alignment methods. Both groups of methods have advantages and disadvantages (which are detailed in Section 1). Therefore, combining the advantages of both methods might be a promising strategy. However, to the best of our knowledge, only the RTEA algorithm that was proposed in our previous conference paper (Proceeding of Pacific Rim International Conference on Artificial Intelligence, pp. 162–175, 2019) utilizes this strategy for entity alignment. This manuscript is an extended version of that conference paper, in which an improved algorithm, namely, ESEA (combining embedding-based and symbol-based methods for entity alignment), is proposed based on the following steps. First, a novel method for combining embedding models with symbol-based models is proposed. Entities with high vector similarities are obtained through a hybrid embedding model, and the final aligned entity pairs are calculated via symbol-based methods. Second, a series of symbol-based methods, instead of only the edit distance method in the original version, are combined with embedding-based methods for relation alignment. Third, we combine symbol-based and embedding-based methods in a more complicated framework with the objective of better exploiting the advantages of both methods. The experimental results on real-world datasets demonstrate that the proposed method outperformed several state-of-the-art embedding-based entity alignment approaches and outperformed our previous RTEA method.

Russian-English dataset and comparative analysis of algorithms for cross-language embedding-based entity alignment

The problem of data fusion from data bases and knowledge graphs in different languages is becoming increasingly important. The main step of such a fusion is the identification of equivalent entities in different knowledge graphs and merging their descriptions. This problem is known as the identity resolution, or entity alignment problem. Recently, a large group of new entity alignment methods has emerged. They look for the so called “embeddings” of entities and establish the equivalence of entities by comparing their embeddings. This paper presents experiments with embedding-based entity alignment algorithms on a Russian-English dataset. The purpose of this work is to identify language-specific features of the entity alignment algorithms. Also, future directions of research are outlined.

Fuzzy entity alignment via knowledge embedding with awareness of uncertainty measure

Entity alignment refers to associate entities in different knowledge graphs if they are semantically identical. Embedding-based entity alignment approaches encode entities in a continuous embedding space where entities are aligned based on the similarity of learned embeddings. However, there exists ambiguity and uncertainty in entity alignment caused by single alignment metric. In this paper, a fuzzy entity alignment method FuzzyEA is proposed to model the uncertainty in alignment process based on intuitionistic fuzzy set (IFS). Iterative TransE model is designed to learn relational structure of knowledge graphs, where mutual selection and error correction mechanism is proposed to enhance the effect of iteration. The alignment results obtained by name/description embedding and structure embedding are fused based on Dempster’s combination rule. Experiments on three benchmark datasets demonstrate that the proposed FuzzyEA consistently outperforms other entity alignment methods and contributes to promising improvement in alignment accuracy and discrimination ability.

A benchmarking study of embedding-based entity alignment for knowledge graphs

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. We survey 23 recent embedding-based entity alignment approaches and categorize them based on their techniques and characteristics. We also 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. We develop an open-source library including 12 representative embedding-based entity alignment approaches, and extensively evaluate these approaches, 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.

CTEA: Context and Topic Enhanced Entity Alignment for knowledge graphs

We study the problem of finding entities referring to the same real world object in multilingual knowledge graphs(KGs), i.e., entity alignment for multilingual KGs. Recently, embedding-based entity alignment methods get extended attention in this area. Most of them firstly embed the entities in low dimensional vectors space via relation structure of entities, and then align entities via these learned embeddings combined with some entity similarity function. Even achieved promising performances, these methods are defective in utilizing entity contexts and entity topic information. In this paper, we propose a novel entity alignment framework CTEA (Context and Topic Enhanced Entity Alignment), which integrates entity context information and entity topic information to help alignment. This framework learns entity topic distributions from their attributes with a specially designed topic model BTM4EA, and the learned entity topic distributions are used to filter some weakly correlated entities for each entity to be aligned. Meanwhile, we embed KGs to low dimensional vectors space via translation-based KG embedding model and mine context information from these vectors with an attention attached Convolutional Neural Network(CNN). The entity embeddings, entity contexts and entity topics are combined to get the final alignment results. Extended experiments reveal that our method achieves promising performances in most cases.

Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation

Graph neural networks (GNNs) have emerged as a powerful paradigm for embedding-based entity alignment due to their capability of identifying isomorphic subgraphs. However, in real knowledge graphs (KGs), the counterpart entities usually have non-isomorphic neighborhood structures, which easily causes GNNs to yield different representations for them. To tackle this problem, we propose a new KG alignment network, namely AliNet, aiming at mitigating the non-isomorphism of neighborhood structures in an end-to-end manner. As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures. It employs an attention mechanism to highlight helpful distant neighbors and reduce noises. Then, it controls the aggregation of both direct and distant neighborhood information using a gating mechanism. We further propose a relation loss to refine entity representations. We perform thorough experiments with detailed ablation studies and analyses on five entity alignment datasets, demonstrating the effectiveness of AliNet.

Self-learning and embedding based entity alignment

Entity alignment aims to identify semantical matchings between entities from different groups. Traditional methods (e.g., attribute comparison-based methods, graph operation-based methods and activ...