Weakly-supervised Knowledge Graph Alignment with Adversarial Learning

This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obtain in many domains. Therefore, in this paper we propose to study aligning knowledge graphs in fully-unsupervised or weakly-supervised fashion, i.e., without or with only a few aligned triplets. We propose an unsupervised framework to align the entity and relation embddings of different knowledge graphs with an adversarial learning framework. Moreover, a regularization term which maximizes the mutual information between the embeddings of different knowledge graphs is used to mitigate the problem of mode collapse when learning the alignment functions. Such a framework can be further seamlessly integrated with existing supervised methods by utilizing a limited number of aligned triples as guidance. Experimental results on multiple datasets prove the effectiveness of our proposed approach in both the unsupervised and the weakly-supervised settings.

[1]  Ramanathan V. Guha,et al.  Semantic search , 2003, WWW '03.

[2]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[3]  Jens Lehmann,et al.  DBpedia: A Nucleus for a Web of Open Data , 2007, ISWC/ASWC.

[4]  Carlo Zaniolo,et al.  Multi-graph Affinity Embeddings for Multilingual Knowledge Graphs , 2017, AKBC@NIPS.

[5]  Juan-Zi Li,et al.  Cross-lingual knowledge linking across wiki knowledge bases , 2012, WWW.

[6]  Juan-Zi Li,et al.  Boosting Cross-Lingual Knowledge Linking via Concept Annotation , 2013, IJCAI.

[7]  Regina Barzilay,et al.  Style Transfer from Non-Parallel Text by Cross-Alignment , 2017, NIPS.

[8]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[9]  Steven Skiena,et al.  Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment , 2018, IJCAI.

[10]  Yoshua Bengio,et al.  Maximum-Likelihood Augmented Discrete Generative Adversarial Networks , 2017, ArXiv.

[11]  Carlo Zaniolo,et al.  Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment , 2016, IJCAI.

[12]  Gerhard Weikum,et al.  WWW 2007 / Track: Semantic Web Session: Ontologies ABSTRACT YAGO: A Core of Semantic Knowledge , 2022 .

[13]  Stefano Ermon,et al.  Generative Adversarial Imitation Learning , 2016, NIPS.

[14]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[15]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[16]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[17]  Aaron C. Courville,et al.  MINE: Mutual Information Neural Estimation , 2018, ArXiv.

[18]  Sergey Levine,et al.  A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models , 2016, ArXiv.

[19]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[20]  Eneko Agirre,et al.  Learning bilingual word embeddings with (almost) no bilingual data , 2017, ACL.

[21]  Pietro Liò,et al.  Deep Graph Infomax , 2018, ICLR.

[22]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[23]  Alexei A. Efros,et al.  Toward Multimodal Image-to-Image Translation , 2017, NIPS.

[24]  R. J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[25]  Guillaume Lample,et al.  Word Translation Without Parallel Data , 2017, ICLR.

[26]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

[27]  Craig A. Knoblock,et al.  Retrieving and Integrating Data from Multiple Information Sources , 1993, Int. J. Cooperative Inf. Syst..

[28]  Zhiyuan Liu,et al.  Iterative Entity Alignment via Joint Knowledge Embeddings , 2017, IJCAI.

[29]  Gjergji Kasneci,et al.  SIGMa: simple greedy matching for aligning large knowledge bases , 2012, KDD.

[30]  Wei Hu,et al.  Bootstrapping Entity Alignment with Knowledge Graph Embedding , 2018, IJCAI.

[31]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.