Multi-Channel Graph Neural Network for Entity Alignment

Abstract

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments. In this paper, we propose a novel Multi-channel Graph Neural Network model (MuGNN) to learn alignment-oriented knowledge graph (KG) embeddings by robustly encoding two KGs via multiple channels. Each channel encodes KGs via different relation weighting schemes with respect to self-attention towards KG completion and cross-KG attention for pruning exclusive entities respectively, which are further combined via pooling techniques. Moreover, we also infer and transfer rule knowledge for completing two KGs consistently. MuGNN is expected to reconcile the structural differences of two KGs, and thus make better use of seed alignments. Extensive experiments on five publicly available datasets demonstrate our superior performance (5% Hits@1 up on average). Source code and data used in the experiments can be accessed at https:// github.com/thunlp/MuGNN.

Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned

“…MTransE [5] WK3l-15K, WK3l-120K, CN3l H@10(, MR) yes IPTransE [29] DFB-{1,2,3} H@{1,10}, MR yes JAPE [19] DBP15K(JAPE) H@{1,10,50}, MR yes KDCoE [4] WK3l-60K H@{1,10}, MR yes BootEA [20] DBP15K(JAPE), DWY100K H@{1,10}, MRR yes SEA [15] WK3l-15K, WK3l-120K H@{1,5,10}, MRR yes MultiKE [28] DWY100K H@{1,10}, MR, MRR yes AttrE [22] DBP-LGD,DBP-GEO,DBP-YAGO H@{1,10}, MR yes RSN [8] custom DBP15K, DWY100K H@{1,10}, MRR yes GCN-Align [24] DBP15K(JAPE) H@{1,10,50} yes CL-GNN [27] DBP15K(JAPE) H@{1,10} yes MuGNN [3] DBP15K(JAPE), DWY100K H@{1,10}, MRR yes NAEA [30] DBP15K(JAPE), DWY100K H@{1,10}, MRR no…”

REA: Robust Cross-lingual Entity Alignment Between Knowledge Graphs

“…Recently, GCNs have been firstly used by [38] to embed entities of KGs into a unified vector space combining structure and attributes information. Then MuGNN [5] combined GNN with self attention to encode KGs, and contextual information also can be utilized with a GNN-based graph matching model [43]. Moreover, simple relation information can be encoded with the GNN models [40,41,45], and MRAEA [24] further takes the meta semantic information of relations into consideration.…”

JarKA: Modeling Attribute Interactions for Cross-lingual Knowledge Alignment

“…However, the issue of the missing attributes or relationships triplets may result in the inaccurate attribute or structure embeddings, which will propagate the errors to the combined embeddings. Besides the above two challenges, most of the existing works [3,9,15] only focus on aligning entities, or at most relationships, but ignore attributes and values. However, the alignment of different objects influence each other.…”

“…Baseline Methods. We compare several existing methods: MuGNN [3]: Learns the structure embeddings by a multi-channel GNNs.…”

“…Recently, much attention has been paid to leveraging the embedding techniques to align entities between two KGs. Some of them only leverage the structures of the KGs, i.e., the relationship triplets in the form of entity, relationship, entity to learn the structure embeddings of entities [3,6,10]. However, the structures of some KGs are sparse, making it difficult to learn the structure embeddings accurately.…”