From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment

Cross-lingual entity alignment (EA) aims to find the equivalent entities between cross-lingual KGs (Knowledge Graphs), which is a crucial step for integrating KGs. Recently, many GNN-based EA methods are proposed and show decent performance improvements on several public datasets. However, existing GNN-based EA methods inevitably inherit poor interpretability and low efficiency from neural networks. Motivated by the isomorphic assumption of GNN-based methods, we successfully transform the cross-lingual EA problem into an assignment problem. Based on this re-definition, we propose a frustratingly Simple but Effective Unsupervised entity alignment method (SEU) without neural networks. Extensive experiments have been conducted to show that our proposed unsupervised approach even beats advanced supervised methods across all public datasets while having high efficiency, interpretability, and stability.

In recent years, the related research of entity alignment has mainly focused on entity alignment via knowledge embeddings and graph neural networks; however, these proposed models usually suffer from structural heterogeneity and the large-scale problem of knowledge graph. A novel entity alignment model based on graph isomorphic network and compressed sensing is proposed. First, for the problem of structural heterogeneity, graph isomorphic network encoder is applied in knowledge graph to capture structural similarity of entity relation. Second, for the problem of large scale, key node and community are integrated for priority entity alignment to improve execution speed. However, the exiting node importance ranking algorithm cannot accurately identify key node in knowledge graph. So the compressed sensing is adopted in node importance ranking to improve the accuracy of identifying key node. The authors have carried out several experiments to test the effect and efficiency of the proposed entity alignment model.

Entity alignment refers to discovering identical entity pairs in 2 knowledge graphs, which is a significant task in knowledge fusion. Early automated entity alignment techniques are based mainly on similarity calculation and comparing symbolic features, i.e., entity names, between entities. Nevertheless, such methods’ performance would reduce significantly when the difference between knowledge graphs is enormous because of relying on predefined comparison rules. Recently, embedding-based methods calculate the similarity between entity pairs through vector embeddings and thus can deal with different knowledge graphs. However, embedding-based methods mostly require humans to annotate data, which is laborious. Therefore, we learn from each other to propose an unsupervised entity alignment framework in this work, which can generate initial alignment seeds automatically by considering symbolic similarities. It can effectively avoid the waste of human resources and is suitable for handling multiple types of knowledge graphs. In addition, we investigate improving the quality and quantity of initial alignment by integrating multiple symbolic similarity features of entities and dealing with the situation of entity information missing better. Experimental results on 3 real datasets demonstrate its state-of-the-art performance.

Multilingual knowledge graph (KG) embeddings provide latent semantic representations of entities and structured knowledge with cross-lingual inferences, which benefit various knowledge-driven cross-lingual NLP tasks. However, precisely learning such cross-lingual inferences is usually hindered by the low coverage of entity alignment in many KGs. Since many multilingual KGs also provide literal descriptions of entities, in this paper, we introduce an embedding-based approach which leverages a weakly aligned multilingual KG for semi-supervised cross-lingual learning using entity descriptions. Our approach performs co-training of two embedding models, i.e. a multilingual KG embedding model and a multilingual literal description embedding model. The models are trained on a large Wikipedia-based trilingual dataset where most entity alignment is unknown to training. Experimental results show that the performance of the proposed approach on the entity alignment task improves at each iteration of co-training, and eventually reaches a stage at which it significantly surpasses previous approaches. We also show that our approach has promising abilities for zero-shot entity alignment, and cross-lingual KG completion.

A comprehensive survey of entity alignment for knowledge graphs

In recent years, interest in knowledge graphs (KGs) has increased exponentially in both the scientific and industrial communities. Integration of various KGs is a pressing problem and is used, for example, to develop complex digital twins of industrial systems. Knowledge graph integration is also necessary when combining KGs extracted from natural language texts using large language models. One component of solving the KG integration problem is entity alignment (EA), which attempts to identify entities in different KGs that describe the same real-world object. In reality, many entities in real KGs have no equivalents in other KGs. In particular, each knowledge graph fragment extracted from a single publication may have its own structure of entity names and identifiers, which significantly complicates the task of identifying entities. This paper describes experiments on entity alignment in the presence of unmatchable entities using a Russian-English dataset as an example.

Entity alignment is a basic and vital technique in knowledge graph (KG) integration. Over the years, research on entity alignment has resided on the assumption that KGs are static, which neglects the nature of growth of real-world KGs. As KGs grow, previous alignment results face the need to be revisited while new entity alignment waits to be discovered. In this paper, we propose and dive into a realistic yet unexplored setting, referred to as continual entity alignment. To avoid retraining an entire model on the whole KGs whenever new entities and triples come, we present a continual alignment method for this task. It reconstructs an entity’s representation based on entity adjacency, enabling it to generate embeddings for new entities quickly and inductively using their existing neighbors. It selects and replays partial pre-aligned entity pairs to train only parts of KGs while extracting trustworthy alignment for knowledge augmentation. As growing KGs inevitably contain non-matchable entities, different from previous works, the proposed method employs bidirectional nearest neighbor matching to find new entity alignment and update old alignment. Furthermore, we also construct new datasets by simulating the growth of multilingual DBpedia. Extensive experiments demonstrate that our continual alignment method is more effective than baselines based on retraining or inductive learning.KeywordsKnowledge graphsContinual entity alignmentRepresentation learning

The prosperous development of cognition and human-level intelligence have made the creation of large-scale domain knowledge graphs (KGs) a hot research field. Entity alignment (EA), which discovers entity pairs that represent the same real object in different KGs, is the key technology for building large scale knowledge graph. Existing EA methods rely mainly on the vector representation of the entity and ignoring the semantic features of an entity in a KG, result in poor alignment quality. To address this limitation, we propose a new EA framework based on knowledge embeddings (KEs) and type matching constraints. By embedding two KGs into a unified vector space, we combine the similarity of the entity vector and the degree of the entity type matching to perform more accurate cross-KG EA. The experimental results show that our proposed method has very good performance on both cross-KG and cross-language data sets. On the DBP-YG dataset, in terms of Hit@1, Hits@10, and MRR, our methods have an average increase of 27% over the baseline method MTransE. In most cases, our method significantly improves the accuracy of EA compared with state-of-the-art methods.

Entity Alignment (EA) aims to identify equivalent entities across different Knowledge Graphs (KGs), enabling knowledge fusion and integration. In recent years, Graph Neural Networks (GNNs) have emerged as a powerful paradigm for EA by leveraging structural information in KGs. However, most existing studies emphasize novel message passing mechanisms while overlooking other crucial GNN design components. This paper presents a comprehensive and systematic evaluation of GNN-based EA methods, focusing on three key aspects: message passing strategies, the number of GNN layers, and the construction of final entity representations. We benchmark a diverse set of GNN models originally developed for tasks such as node classification and knowledge graph completion, and we assess their adaptability to the EA task. Additionally, we explore the effectiveness of skip connection techniques, activation functions, and relational information integration. Our experiments, conducted on standard EA benchmarks including DBP15K and SRPRS, reveal several counterintuitive findings: (1) message passing is indispensable for EA; (2) many node classification GNNs are highly competitive for EA; (3) one or two GNN layers generally achieve optimal performance; and (4) activation functions have minimal impact, while skip connections significantly enhance results. This study provides a principled framework and empirical foundation for designing more effective GNN-based EA models. Code and datasets are publicly available at <uri xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://github.com/kg-bnu/GNN-EA">https://github.com/kg-bnu/GNN-EA</uri>.

CTEA: Context and Topic Enhanced Entity Alignment for knowledge graphs

Entity alignment (EA) is the task of finding equivalent entities in various knowledge graphs (KGs) that represent the same object in the real world, which aims at building a unified large-scale knowledge graph with rich and high-quality content. Existing EA works have achieved promising performance. These works mainly focus on learning the entity embeddings by capturing the structural semantics of entities on the relational triples in KG. Some works also take utilization of attributes information in entity embeddings. However, they are still hindered by the lack of prior seed alignment known as labeled training data. In this paper, we propose a novel approach for KG entity alignment based on transfer learning named DAEA, which incorporates both attributes triples and relational triples to generate the entity embeddings. DAEA first uses the J-GCN model to learn the entity representation model in source domain KG. Then, it combines domain adversarial network to learn entity representation model of the target domain. Since DAEA can transfer common entity information from the source domain to the target domain, it mitigates the problem of poor alignment performance due to lack of prior seed alignment. Experiments results show that DAEA significantly outperforms the state-of-the-art EA approaches on both monolingual and cross-lingual entity alignment datasets. Ablation studies on different components further demonstrate the effectiveness of our approach.

Multilingual knowledge graph completion predicts missing facts in the target language knowledge graph by learning and inferring knowledge and rules in other language knowledge graphs. Existing methods tend to use aligned entities between knowledge graphs in different languages as alignment seeds, and receive information from them through alignment seeds to promote entity alignment between different knowledge graphs. However, these methods only consider the local structural information of the knowledge graph by aggregating entity neighborhood information through aligned entities, and ignore the global structural information. At the same time, the methods aboved are hardly to learn the entity representation with sparse neighborhood in isolated subgraphs. To address these two problems, this paper proposes a multilingual knowledge graph completion method based on double-branch graph neural network and self-supervised entity alignment (DBGNN-SSL). The global and local topological structures of the knowledge graph are learned through a double-branch graph attention neural network, and more aligned entities can be iteratively generated through self-supervised learning. The experimental results on datasets DBP-5L and E-PKG verify the effectiveness of the proposed method.

The symmetry between different representation spaces plays a crucial role in effectively modeling complex multimodal data. To address the challenge of equipment knowledge graphs containing hierarchical relationships that cannot be fully represented in a single space, this study proposes UMEAD, an unsupervised multimodal entity alignment method based on dual-space embeddings. The method simultaneously learns graph embeddings in both Euclidean and hyperbolic spaces, forming a structural symmetry where the Euclidean space captures local regularities and the hyperbolic space models global hierarchies. Their complementarity achieves a balanced and symmetric representation of multimodal knowledge. An adaptive feature fusion strategy is further employed to dynamically weight semantic and visual modalities, enhancing the symmetry and complementarity between different modalities. To reduce reliance on scarce pre-aligned data, pseudo seed instances are generated from multimodal features, and an iterative constraint mechanism progressively enlarges the training set, enabling unsupervised alignment. Experiments on public datasets, including EMMEAD, FB15K-DB15K, and FB15K-YAGO15K, demonstrate that the combination of dual-space embeddings, adaptive fusion, and iterative constraints significantly improves alignment accuracy. In summary, the proposed method reduces dependence on pre-aligned data, strengthens multimodal and structural alignment, and its symmetric embedding and fusion design offers a promising approach for the construction and application of multimodal knowledge graphs in the equipment domain.

Entity alignment aims to discover unique equivalent entity pairs with the same meaning across different knowledge graphs (KGs). Existing models have focused on projecting KGs into a latent embedding space so that inherent semantics between entities can be captured for entity alignment. However, the adverse impacts of alignment conflicts have been largely overlooked during training, thereby limiting the entity alignment performance. To address this issue, we propose a novel Conflict-aware Pseudo Labeling via Optimal Transport model (CPL-OT) for entity alignment. The key idea is to iteratively pseudo-label alignment pairs empowered with conflict-aware optimal transport (OT) modeling to boost the precision of entity alignment. CPL-OT is composed of two key components—entity embedding learning with global-local aggregation and iterative conflict-aware pseudo labeling—that mutually reinforce each other. To mitigate alignment conflicts during pseudo labeling, we propose to use optimal transport as an effective means to warrant one-to-one entity alignment between two KGs with the minimal overall transport cost. Extensive experiments on benchmark datasets validate the superiority of CPL-OT over state-of-the-art baselines under both settings with and without prior alignment seeds.

In recent years, the tourism field related websites are increasing day by day, the network has produced massive tourist generation data. Based on the semi-structured data of scenic spots, hotels and caterings on tourist websites and the travel notes published by tourists, this paper constructed the tourism knowledge graph. The extraction of entities from travel notes was faced with the problems of named entity recognition and entity alignment. In order to improve the accuracy of extracting entities from travel notes, in this paper, the named entity recognition model based on BiLSTM-CRF and the entity alignment model based on siamese network were proposed. F values can reach 90.8% and 93.0%, respectively.