Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

Postal Subscription Code 80-970

2018 Impact Factor: 1.129

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Comput. Sci.    2022, Vol. 16 Issue (5) : 165611    https://doi.org/10.1007/s11704-021-1057-6
LETTER
Heterogeneous information network embedding with incomplete multi-view fusion
Susu ZHENG1,2, Weiwei YUAN1,2, Donghai GUAN1,2()
1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, China
2. Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 211100, China
 Download: PDF(3146 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Corresponding Author(s): Donghai GUAN   
Just Accepted Date: 11 June 2021   Issue Date: 31 December 2021
 Cite this article:   
Susu ZHENG,Weiwei YUAN,Donghai GUAN. Heterogeneous information network embedding with incomplete multi-view fusion[J]. Front. Comput. Sci., 2022, 16(5): 165611.
 URL:  
https://academic.hep.com.cn/fcs/EN/10.1007/s11704-021-1057-6
https://academic.hep.com.cn/fcs/EN/Y2022/V16/I5/165611
Fig.1  The architecture of IMHE framework. Circles and squares represent nodes and node embeddings, and white circles and squares represent missing nodes and node embeddings
Methods Training ratio
10% 15% 20% 30% 40% 50%
Line 0.497 0.522 0.536 0.566 0.576 0.572
Metapath2vec 0.526 0.553 0.595 0.637 0.643 0.645
Hin2vec 0.649 0.643 0.679 0.668 0.689 0.692
MNE 0.584 0.587 0.591 0.596 0.604 0.613
AHE 0.633 0.646 0.648 0.658 0.675 0.690
IMHE 0.675 0.683 0.695 0.712 0.724 0.732
Tab.1  Micro-F1 scores of Node classification task
Methods Training ratio
10% 15% 20% 30% 40% 50%
Line 0.497 0.530 0.532 0.554 0.562 0.567
Metapath2vec 0.530 0.558 0.582 0.581 0.618 0.632
Hin2vec 0.642 0.646 0.651 0.662 0.674 0.686
MNE 0.575 0.573 0.580 0.585 0.594 0.611
AHE 0.648 0.657 0.658 0.675 0.682 0.679
IMHE 0.677 0.679 0.689 0.700 0.708 0.716
Tab.2  Macro-F1 scores of Node classification task
1 Y X Dong, N V Chawla, A Swami. metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2017, 135– 144
2 Z Y Zhao , H Zhou , C Li , J Tang , Q T Zeng . DeepEmLAN: deep embedding learning for attributed networks. Information Sciences, 2021, 543 : 382– 397
3 D J Yang, S Z Wang, C Z Li, X M Zhang, Z J Li. From properties to links: deep network embedding on incomplete graphs. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 2017, 367– 376
4 Z Y Zhao , H Zhou , L Qi , L Chang , M C Zhou . Inductive representation learning via CNN for partially-unseen attributed networks. IEEE Transactions on Network Science and Engineering, 2021, 8( 1): 695– 706
5 A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, A N Gomez, Ł Kaiser, I Polosukhin. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017, 6000−6010
6 J Tang, M Qu, M Z Wang, M Zhang, J Yan, Q Z Mei. LINE: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web. 2015, 1067−1077
7 A M Winkler , O Renaud , S M Smith , T E Nichols . Permutation inference for canonical correlation analysis. NeuroImage, 2020, 220 : 117065–
8 T Y Fu, W C Lee, Z Lei. HIN2Vec: explore meta-paths in heterogeneous information networks for representation learning. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. 2017, 1797−1806
9 H M Zhang, L W Qiu, L L Yi, Y Q Song. Scalable multiplex network embedding. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018: 3082−3088
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed