Entity Alignment

106 papers with code • 10 benchmarks • 8 datasets

Entity Alignment is the task of finding entities in two knowledge bases that refer to the same real-world object. It plays a vital role in automatically integrating multiple knowledge bases.
Note: results that have incorporated machine translated entity names (introduced in the RDGCN paper) or pre-alignment name embeddings are considered to have used extra training labels (both are marked with "Extra Training Data" in the leaderboard) and are not adhere to a comparable setting with others that have followed the original setting of the benchmark.

Source: Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding

The task of entity alignment is related to the task of entity resolution which focuses on matching structured entity descriptions in different contexts.

Most implemented papers

Iterative Entity Alignment via Joint Knowledge Embeddings

thunlp/IEAJKE International Joint Conference on Artificial Intelligence 2017

During this process, we can align entities according to their semantic distance in this joint semantic space.

Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding

nju-websoft/JAPE 16 Aug 2017

Our experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.

Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks

1049451037/GCN-Align EMNLP 2018

Embeddings can be learned from both the structural and attribute information of entities, and the results of structure embedding and attribute embedding are combined to get accurate alignments.

SecureBoost: A Lossless Federated Learning Framework

Koukyosyumei/AIJack 25 Jan 2019

This federated learning system allows the learning process to be jointly conducted over multiple parties with common user samples but different feature sets, which corresponds to a vertically partitioned data set.

Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs

nju-websoft/RSN 13 May 2019

Moreover, triple-level learning is insufficient for the propagation of semantic information among entities, especially for the case of cross-KG embedding.

Multi-view Knowledge Graph Embedding for Entity Alignment

nju-websoft/MultiKE 6 Jun 2019

Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs.

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

StephanieWyt/RDGCN 22 Aug 2019

Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.

Multi-Channel Graph Neural Network for Entity Alignment

thunlp/MuGNN ACL 2019

Entity alignment typically suffers from the issues of structural heterogeneity and limited seed alignments.

Jointly Learning Entity and Relation Representations for Entity Alignment

StephanieWyt/HGCN-JE-JR IJCNLP 2019

Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs).