Journal
INFORMATION PROCESSING & MANAGEMENT
Volume 59, Issue 3, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.ipm.2022.102902
Keywords
Graph convolutional network; Node classification; Link prediction; Multi-task learning
Funding
- National Natural Science Foundation of China [61876046]
- Guangxi ``Bagui'' Teams for Innovation and Research
- Sichuan Science and Technology Program [2018GZDZX0032, 2019YFG0535]
- Natural Science Project of Guangxi Universities [2021KY0061]
Ask authors/readers for more resources
In this paper, a Multi-Task and Multi-Graph Convolutional Network (MTGCN) is proposed to conduct node classification and link prediction simultaneously. MTGCN consists of multiple multi-task learning to capture the complementary information between node classification and link prediction, and enhances the information to guarantee the quality of representations by exploring the complex structure inherent in the graph data.
Both node classification and link prediction are popular topics of supervised learning on the graph data, but previous works seldom integrate them together to capture their complementary information. In this paper, we propose a Multi-Task and Multi-Graph Convolutional Network (MTGCN) to jointly conduct node classification and link prediction in a unified framework. Specifically, MTGCN consists of multiple multi-task learning so that each multi-task learning learns the complementary information between node classification and link prediction. In particular, each multi-task learning uses different inputs to output representations of the graph data. Moreover, the parameters of one multi-task learning initialize the parameters of the other multi-task learning, so that the useful information in the former multi-task learning can be propagated to the other multi-task learning. As a result, the information is augmented to guarantee the quality of representations by exploring the complex constructure inherent in the graph data. Experimental results on six datasets show that our MTGCN outperforms the comparison methods in terms of both node classification and link prediction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available