.png){kind=icon}
.png){kind=icon}
Return
MTGCN: A multi-task approach for node classification and link prediction in graph data
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ipm.2022.102902.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Graph convolutional network
Node classification
Link prediction
Multi-task learning
Journal
I
IF:
6.9
Papers:
5.2K
Citations:
1.4W