Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction

Developing link prediction models to automatically complete knowledge graphs has recently been the focus of significant research interest. The current methods for the link prediction task have two natural problems: 1) the relation distributions in knowledge graphs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations. These two problems limit the training effectiveness and practical applications of the existing link prediction models. We advocate a holistic understanding of KGs and we propose in this work a unified Generalized Relation Learning framework GRL to address the above two problems, which can be plugged into existing link prediction models. GRL conducts a generalized relation learning, which is aware of semantic correlations between relations that serve as a bridge to connect semantically similar relations. After training with GRL, the closeness of semantically similar relations in vector space and the discrimination of dissimilar relations are improved. We perform comprehensive experiments on six benchmarks to demonstrate the superior capability of GRL in the link prediction task. In particular, GRL is found to enhance the existing link prediction models making them insensitive to unbalanced relation distributions and capable of learning unseen

[1]  Fabian M. Suchanek,et al.  YAGO3: A Knowledge Base from Multilingual Wikipedias , 2015, CIDR.

[2]  Mo Yu,et al.  One-Shot Relational Learning for Knowledge Graphs , 2018, EMNLP.

[3]  M. de Rijke,et al.  Conversational Recommendation: Formulation, Methods, and Evaluation , 2020, SIGIR.

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

[5]  Pasquale Minervini,et al.  Convolutional 2D Knowledge Graph Embeddings , 2017, AAAI.

[6]  Xiangnan He,et al.  Interactive Path Reasoning on Graph for Conversational Recommendation , 2020, KDD.

[7]  Guillaume Bouchard,et al.  Complex Embeddings for Simple Link Prediction , 2016, ICML.

[8]  Hao Zhu,et al.  Quantifying Similarity between Relations with Fact Distribution , 2019, ACL.

[9]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[10]  Danqi Chen,et al.  Observed versus latent features for knowledge base and text inference , 2015, CVSC.

[11]  Piji Li,et al.  Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion , 2019, EMNLP.

[12]  Timothy M. Hospedales,et al.  TuckER: Tensor Factorization for Knowledge Graph Completion , 2019, EMNLP.

[13]  Dai Quoc Nguyen,et al.  A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network , 2017, NAACL.

[14]  Qiang Chen,et al.  Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs , 2019, EMNLP-IJCNLP 2019.

[15]  Chang Zhou,et al.  Cognitive Knowledge Graph Reasoning for One-shot Relational Learning , 2019, ArXiv.

[16]  Seungwhan Moon,et al.  OpenDialKG: Explainable Conversational Reasoning with Attention-based Walks over Knowledge Graphs , 2019, ACL.

[17]  Seyed Mehran Kazemi,et al.  SimplE Embedding for Link Prediction in Knowledge Graphs , 2018, NeurIPS.

[18]  Chunyun Zhang,et al.  Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs , 2020, AAAI.

[19]  Jun Zhao,et al.  Knowledge Graph Completion with Adaptive Sparse Transfer Matrix , 2016, AAAI.

[20]  Max Welling,et al.  Modeling Relational Data with Graph Convolutional Networks , 2017, ESWC.

[21]  Xiangnan He,et al.  Learning Intents behind Interactions with Knowledge Graph for Recommendation , 2021, WWW.

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

[23]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[24]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[25]  Gerhard Weikum,et al.  Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion , 2019, CIKM.

[26]  Tim Weninger,et al.  Open-World Knowledge Graph Completion , 2017, AAAI.

[27]  Ruijiang Li,et al.  Relation Embedding with Dihedral Group in Knowledge Graph , 2019, ACL.

[28]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[29]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[30]  Wenhan Xiong,et al.  DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning , 2017, EMNLP.

[31]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[32]  Xin Lv,et al.  Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations , 2019, EMNLP.

[33]  De-Chuan Zhan,et al.  Learning Classifier Synthesis for Generalized Few-Shot Learning , 2019, ArXiv.

[34]  Soujanya Poria,et al.  Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering , 2021, ArXiv.

[35]  Minyi Guo,et al.  Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation , 2019, WWW.

[36]  Xi Chen,et al.  Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks , 2019, NAACL.

[37]  Richard Socher,et al.  Multi-Hop Knowledge Graph Reasoning with Reward Shaping , 2018, EMNLP.

[38]  Zeynep Akata,et al.  Relational Generalized Few-Shot Learning , 2019, BMVC.

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

[40]  Stella X. Yu,et al.  Large-Scale Long-Tailed Recognition in an Open World , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Sharath Pankanti,et al.  RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).