LinkNBed: Multi-Graph Representation Learning with Entity Linkage

被引:26
|
作者
Trivedi, Rakshit [1 ]
Sisman, Bunyamin [2 ]
Ma, Jun [2 ]
Faloutsos, Christos [2 ,3 ]
Zha, Hongyuan [1 ]
Dong, Xin Luna [2 ]
机构
[1] Georgia Tech, Coll Comp, Atlanta, GA 30332 USA
[2] Amazon Com, Seattle, WA USA
[3] CMU, SCS, Pittsburgh, PA USA
来源
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1 | 2018年
关键词
D O I
10.18653/v1/P18-1024
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Knowledge graphs have emerged as an important model for studying complex multi-relational data. This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources. An effective and scalable approach to jointly learn over multiple graphs and eventually construct a unified graph is a crucial next step for the success of knowledge-based inference for many downstream applications. To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multiple graphs. We identify entity linkage across graphs as a vital component to achieve our goal. We design a novel objective that leverage entity linkage and build an efficient multi-task training procedure. Experiments on link prediction and entity linkage demonstrate substantial improvements over the state-of-the-art relational learning approaches.
引用
收藏
页码:252 / 262
页数:11
相关论文
共 50 条
  • [41] Multi-graph Multi-label Learning with Dual-granularity Labeling
    Zhao, Yuhai
    Wang, Yejiang
    Wang, Zhengkui
    Zhang, Chengqi
    KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, : 2327 - 2337
  • [42] Enabling Location-based Services—Multi-Graph Representation of Transportation Networks
    Laurynas Speičys
    Christian S. Jensen
    GeoInformatica, 2008, 12 : 219 - 253
  • [43] Multi-Graph Contrastive Learning for Community Detection in Multi-Layer Networks
    Cao, Songen
    Lv, Xiaoyi
    Ma, Yaxiong
    Ma, Xiaoke
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024,
  • [44] A Segmentation Scheme Based on a Multi-graph Representation: Application to Colour Cadastral Maps
    Raveaux, Romain
    Burie, Jean-Christophe
    Ogier, Jean-Marc
    GRAPHICS RECOGNITION: RECENT ADVANCES AND NEW OPPORTUNITIES, 2008, 5046 : 202 - 212
  • [45] Multi-graph Regularized Deep Auto-Encoders for Multi-view Image Representation
    Fang, Jiaying
    Zhan, Yongzhao
    Shen, Xiangjun
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT I, 2018, 11164 : 797 - 807
  • [46] Multi-Graph Cooperative Learning Towards Distant Supervised Relation Extraction
    Yuan, Changsen
    Huang, Heyan
    Feng, Chong
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2021, 12 (05)
  • [47] Multiple Embeddings Enhanced Multi-Graph Neural Networks for Chinese Healthcare Named Entity Recognition
    Lee, Lung-Hao
    Lu, Yi
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2021, 25 (07) : 2801 - 2810
  • [48] Temporal Knowledge Graph Entity Alignment via Representation Learning
    Song, Xiuting
    Bai, Luyi
    Liu, Rongke
    Zhang, Han
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS, DASFAA 2022, PT II, 2022, : 391 - 406
  • [49] Parallel multi-graph classification using extreme learning machine and MapReduce
    Pang, Jun
    Gu, Yu
    Xu, Jia
    Kong, Xiaowang
    Yu, Ge
    NEUROCOMPUTING, 2017, 261 : 171 - 183
  • [50] Parallel Multi-graph Classification Using Extreme Learning Machine and MapReduce
    Pang, Jun
    Gu, Yu
    Xu, Jia
    Kong, Xiaowang
    Yu, Ge
    PROCEEDINGS OF ELM-2015, VOL 1: THEORY, ALGORITHMS AND APPLICATIONS (I), 2016, 6 : 77 - 92