Cross-Graph Learning of Multi-Relational Associations

被引:0
|
作者
Liu, Hanxiao [1 ]
Yang, Yiming [1 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
基金
美国国家科学基金会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Cross-graph Relational Learning (CGRL) refers to the problem of predicting the strengths or labels of multi-relational tuples of heterogeneous object types, through the joint inference over multiple graphs which specify the internal connections among each type of objects. CGRL is an open challenge in machine learning due to the daunting number of all possible tuples to deal with when the numbers of nodes in multiple graphs are large, and because the labeled training instances are extremely sparse as typical. Existing methods such as tensor factorization or tensor-kernel machines do not work well because of the lack of convex formulation for the optimization of CGRL models, the poor scalability of the algorithms in handling combinatorial numbers of tuples, and/or the non-transductive nature of the learning methods which limits their ability to leverage unlabeled data in training. This paper proposes a novel framework which formulates CGRL as a convex optimization problem, enables transductive learning using both labeled and unlabeled tuples, and offers a scalable algorithm that guarantees the optimal solution and enjoys a linear time complexity with respect to the sizes of input graphs. In our experiments with a subset of DBLP publication records and an Enzyme multi-source dataset, the proposed method successfully scaled to the large cross-graph inference problem, and outperformed other representative approaches significantly.
引用
收藏
页数:9
相关论文
共 50 条
  • [21] A RECURRENT GRAPH NEURAL NETWORK FOR MULTI-RELATIONAL DATA
    Ioannidis, Vassilis N.
    Marques, Antonio G.
    Giannakis, Georgios B.
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 8157 - 8161
  • [22] Fashion Recommendation with Multi-relational Representation Learning
    Li, Yang
    Luo, Yadan
    Huang, Zi
    [J]. ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2020, PT I, 2020, 12084 : 3 - 15
  • [23] Sequential Pattern Knowledge in Multi-Relational Learning
    Ferreira, Carlos Abreu
    Gama, Joao
    Costa, Vitor Santos
    [J]. COMPUTER AND INFORMATION SCIENCES II, 2012, : 539 - 545
  • [24] Efficient Knowledge Graph Validation via Cross-Graph Representation Learning
    Wang, Yaqing
    Ma, Fenglong
    Gao, Jing
    [J]. CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 1595 - 1604
  • [25] Active Learning for Multi-relational Data Construction
    Kajino, Hiroshi
    Kishimoto, Akihiro
    Botea, Adi
    Daly, Elizabeth
    Kotoulas, Spyros
    [J]. PROCEEDINGS OF THE 24TH INTERNATIONAL CONFERENCE ON WORLD WIDE WEB (WWW 2015), 2015, : 560 - 569
  • [26] Contrasting logical sequences in multi-relational learning
    Carlos Abreu Ferreira
    João Gama
    Vítor Santos Costa
    [J]. Progress in Artificial Intelligence, 2019, 8 : 487 - 503
  • [27] Contrasting logical sequences in multi-relational learning
    Ferreira, Carlos Abreu
    Gama, Joao
    Costa, Vitor Santos
    [J]. PROGRESS IN ARTIFICIAL INTELLIGENCE, 2019, 8 (04) : 487 - 503
  • [28] A Structural Representation Learning for Multi-relational Networks
    Liu, Lin
    Li, Xin
    Cheung, William K.
    Xu, Chengcheng
    [J]. PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 4047 - 4053
  • [29] Multi-Relational Script Learning for Discourse Relations
    Lee, I-Ta
    Goldwasser, Dan
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4214 - 4226
  • [30] A Multi-Relational Graph Encoder Network for Fine-Grained Prediction of MiRNA-Disease Associations
    Yu, Shengpeng
    Wang, Hong
    Li, Jing
    Zhao, Jun
    Liang, Cheng
    Sun, Yanshen
    [J]. IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2024, 21 (01) : 45 - 56