| Paper ID | MLSP-30.2 |
| Paper Title |
Fast Hierarchy Preserving Graph Embedding via Subspace Constraints |
| Authors |
Xu Chen, Peking University, China; Lun Du, Microsoft Research, China; Mengyuan Chen, Beijing Normal University, China; Yun Wang, QingQing Long, Kunqing Xie, Peking University, China |
| Session | MLSP-30: Graph Signal Processing |
| Location | Gather.Town |
| Session Time: | Thursday, 10 June, 14:00 - 14:45 |
| Presentation Time: | Thursday, 10 June, 14:00 - 14:45 |
| Presentation |
Poster
|
| Topic |
Machine Learning for Signal Processing: [MLR-SSUP] Self-supervised and semi-supervised learning |
| IEEE Xplore Open Preview |
Click here to view in IEEE Xplore |
| Virtual Presentation |
Click here to watch in the Virtual Conference |
| Abstract |
Hierarchy preserving network embedding is a method that project nodes into feature space by preserving the hierarchy property of networks. Recently, researches on network representation have considerably profited from taking hierarchy into consideration. Among these works, SpaceNE stands out by preserving hierarchy with the help of subspace constraints on the hierarchy subspace system. However, like all other hierarchy preserving network embedding methods, SpaceNE is time-consuming and cannot generalize to new nodes. In this paper, we propose an inductive method, FastHGE, to learn node representations more efficiently and generalize to new nodes more easily. Empirically, the experiment of node classification demonstrates that the convergence speed of FastHGE is increased by 30 times in the case of the same accuracy with SpaceNE. |
