Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation

Graph neural networks (GNNs) have emerged as a powerful paradigm for embedding-based entity alignment due to their capability of identifying isomorphic subgraphs. However, in real knowledge graphs (KGs), the counterpart entities usually have non-isomorphic neighborhood structures, which easily causes GNNs to yield different representations for them. To tackle this problem, we propose a new KG alignment network, namely AliNet, aiming at mitigating the non-isomorphism of neighborhood structures in an end-to-end manner. As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures. It employs an attention mechanism to highlight helpful distant neighbors and reduce noises. Then, it controls the aggregation of both direct and distant neighborhood information using a gating mechanism. We further propose a relation loss to refine entity representations. We perform thorough experiments with detailed ablation studies and analyses on five entity alignment datasets, demonstrating the effectiveness of AliNet.

Download Full-text

BERT-INT:A BERT-based Interaction Model For Knowledge Graph Alignment

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/439 ◽

2020 ◽

Author(s):

Xiaobin Tang ◽

Jing Zhang ◽

Bo Chen ◽

Yang Yang ◽

Hong Chen ◽

...

Keyword(s):

Neural Networks ◽

State Of The Art ◽

Side Information ◽

Interaction Model ◽

Experimental Results ◽

Knowledge Graph ◽

Fine Grained ◽

Graph Alignment ◽

Knowledge Graphs ◽

Graph Neural Networks

Knowledge graph alignment aims to link equivalent entities across different knowledge graphs. To utilize both the graph structures and the side information such as name, description and attributes, most of the works propagate the side information especially names through linked entities by graph neural networks. However, due to the heterogeneity of different knowledge graphs, the alignment accuracy will be suffered from aggregating different neighbors. This work presents an interaction model to only leverage the side information. Instead of aggregating neighbors, we compute the interactions between neighbors which can capture fine-grained matches of neighbors. Similarly, the interactions of attributes are also modeled. Experimental results show that our model significantly outperforms the best state-of-the-art methods by 1.9-9.7% in terms of HitRatio@1 on the dataset DBP15K.

Download Full-text

Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6508 ◽

2020 ◽

Vol 34 (05) ◽

pp. 9612-9619

Author(s):

Zhao Zhang ◽

Fuzhen Zhuang ◽

Hengshu Zhu ◽

Zhiping Shi ◽

Hui Xiong ◽

...

Keyword(s):

Neural Network ◽

Missing Values ◽

State Of The Art ◽

Attention Mechanism ◽

Knowledge Graph ◽

Incomplete Knowledge ◽

Neighborhood Information ◽

Local Neighborhood ◽

Proposed Model ◽

Knowledge Graphs

The rapid proliferation of knowledge graphs (KGs) has changed the paradigm for various AI-related applications. Despite their large sizes, modern KGs are far from complete and comprehensive. This has motivated the research in knowledge graph completion (KGC), which aims to infer missing values in incomplete knowledge triples. However, most existing KGC models treat the triples in KGs independently without leveraging the inherent and valuable information from the local neighborhood surrounding an entity. To this end, we propose a Relational Graph neural network with Hierarchical ATtention (RGHAT) for the KGC task. The proposed model is equipped with a two-level attention mechanism: (i) the first level is the relation-level attention, which is inspired by the intuition that different relations have different weights for indicating an entity; (ii) the second level is the entity-level attention, which enables our model to highlight the importance of different neighboring entities under the same relation. The hierarchical attention mechanism makes our model more effective to utilize the neighborhood information of an entity. Finally, we extensively validate the superiority of RGHAT against various state-of-the-art baselines.

Download Full-text

Multi-hop Attention Graph Neural Networks

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/425 ◽

2021 ◽

Author(s):

Guangtao Wang ◽

Rex Ying ◽

Jing Huang ◽

Jure Leskovec

Keyword(s):

Neural Networks ◽

Large Scale ◽

Performance Metrics ◽

State Of The Art ◽

Structural Information ◽

Representation Learning ◽

Attention Mechanism ◽

Graph Representation ◽

Knowledge Graph ◽

Graph Neural Networks

Self-attention mechanism in graph neural networks (GNNs) led to state-of-the-art performance on many graph representation learning tasks. Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the representation of the two nodes. However, such attention mechanism does not account for nodes that are not directly connected but provide important network context. Here we propose Multi-hop Attention Graph Neural Network (MAGNA), a principled way to incorporate multi-hop context information into every layer of attention computation. MAGNA diffuses the attention scores across the network, which increases the receptive field for every layer of the GNN. Unlike previous approaches, MAGNA uses a diffusion prior on attention values, to efficiently account for all paths between the pair of disconnected nodes. We demonstrate in theory and experiments that MAGNA captures large-scale structural information in every layer, and has a low-pass effect that eliminates noisy high-frequency information from graph data. Experimental results on node classification as well as the knowledge graph completion benchmarks show that MAGNA achieves state-of-the-art results: MAGNA achieves up to 5.7% relative error reduction over the previous state-of-the-art on Cora, Citeseer, and Pubmed. MAGNA also obtains the best performance on a large-scale Open Graph Benchmark dataset. On knowledge graph completion MAGNA advances state-of-the-art on WN18RR and FB15k-237 across four different performance metrics.

Download Full-text

Gated Knowledge Graph Neural Networks for Top-N Recommendation System

2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD) ◽

10.1109/cscwd49262.2021.9437829 ◽

2021 ◽

Author(s):

Nan Mu ◽

Daren Zha ◽

Rui Gong

Keyword(s):

Neural Networks ◽

Recommendation System ◽

Knowledge Graph ◽

Graph Neural Networks

Download Full-text

Knowledge Reasoning Method for Military Decision Support Knowledge Graph Mixing Rule and Graph Neural Networks Learning together

2020 Chinese Automation Congress (CAC) ◽

10.1109/cac51589.2020.9327031 ◽

2020 ◽

Author(s):

Kai Nie ◽

Kejun Zeng ◽

Qinghai Meng

Keyword(s):

Neural Networks ◽

Decision Support ◽

Knowledge Graph ◽

Mixing Rule ◽

Knowledge Reasoning ◽

Graph Neural Networks ◽

Learning Together

Download Full-text

SeMi: A SEmantic Modeling machIne to build Knowledge Graphs with graph neural networks

SoftwareX ◽

10.1016/j.softx.2020.100516 ◽

2020 ◽

Vol 12 ◽

pp. 100516

Author(s):

Giuseppe Futia ◽

Antonio Vetrò ◽

Juan Carlos De Martin

Keyword(s):

Neural Networks ◽

Semantic Modeling ◽

Knowledge Graphs ◽

Graph Neural Networks

Download Full-text

GCFA: Graph Neural Networks on Collaborative Filtering Recommendation via Attention Mechanism

2020 5th IEEE International Conference on Big Data Analytics (ICBDA) ◽

10.1109/icbda49040.2020.9101190 ◽

2020 ◽

Author(s):

Hui Zou ◽

Guanwen Yu ◽

Zhaogong Zhang

Keyword(s):

Neural Networks ◽

Collaborative Filtering ◽

Attention Mechanism ◽

Graph Neural Networks

Download Full-text

Knowledge Graph Integrated Graph Neural Networks for Chinese Medical Text Classification

10.1109/bibm52615.2021.9669286 ◽

2021 ◽

Author(s):

Ge Lan ◽

Ye Li ◽

Mengting Hu ◽

Yufei Sun ◽

Yuzhi Zhang

Keyword(s):

Neural Networks ◽

Text Classification ◽

Knowledge Graph ◽

Medical Text ◽

Graph Neural Networks

Download Full-text

End-to-End Argumentation Knowledge Graph Construction

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6231 ◽

2020 ◽

Vol 34 (05) ◽

pp. 7367-7374

Author(s):

Khalid Al-Khatib ◽

Yufang Hou ◽

Henning Wachsmuth ◽

Charles Jochim ◽

Francesca Bonin ◽

...

Keyword(s):

Large Scale ◽

Question Answering ◽

Knowledge Graph ◽

Exploratory Search ◽

Text Generation ◽

Fake News ◽

High Quality ◽

Web Based ◽

Knowledge Graphs ◽

End To End

This paper studies the end-to-end construction of an argumentation knowledge graph that is intended to support argument synthesis, argumentative question answering, or fake news detection, among others. The study is motivated by the proven effectiveness of knowledge graphs for interpretable and controllable text generation and exploratory search. Original in our work is that we propose a model of the knowledge encapsulated in arguments. Based on this model, we build a new corpus that comprises about 16k manual annotations of 4740 claims with instances of the model's elements, and we develop an end-to-end framework that automatically identifies all modeled types of instances. The results of experiments show the potential of the framework for building a web-based argumentation graph that is of high quality and large scale.

Download Full-text