Abstract
Numerous network representation-based algorithms for network classification have emerged in recent years, but many suffer from two limitations. First, they separate the network representation learning and node classification in networks into two steps, which may result in sub-optimal results because the node representation may not fit the classification model well, and vice versa. Second, they are mostly shallow methods that can only capture the linear and simple relationships in the data. In this paper, we propose an effective deep learning model, Graph Ladder Networks (GLN), for node classification in networks. Our model learns a ladder network which unifies the representation learning and network classification into one single framework by exploiting both labeled and unlabeled nodes in a network. To integrate both structure and node content information in the networks, the most recently developed graph convolution network, is further employed. The experiments on the most popular academic network dataset, Citeseer, demonstrate that our approach reaches outstanding performance compared to other state-of-the-art algorithms.
| Original language | English |
|---|---|
| Title of host publication | CIKM'17 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management |
| Subtitle of host publication | November 6–10, 2017 Singapore, Singapore |
| Editors | Shane Culpepper, Eric Lo, Joyce Ho |
| Place of Publication | New York NY USA |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 2103-2106 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781450349185 |
| DOIs | |
| Publication status | Published - 2017 |
| Externally published | Yes |
| Event | ACM International Conference on Information and Knowledge Management 2017 - Singapore, Singapore Duration: 6 Nov 2017 → 10 Nov 2017 Conference number: 26th http://www.cikmconference.org/CIKM2017/ |
Conference
| Conference | ACM International Conference on Information and Knowledge Management 2017 |
|---|---|
| Abbreviated title | CIKM 2017 |
| Country | Singapore |
| City | Singapore |
| Period | 6/11/17 → 10/11/17 |
| Internet address |
Cite this
}
Graph ladder networks for network classification. / Hu, Ruiqi; Pan, Shirui; Jiang, Jing; Long, Guodong.
CIKM'17 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management: November 6–10, 2017 Singapore, Singapore. ed. / Shane Culpepper; Eric Lo; Joyce Ho. New York NY USA : Association for Computing Machinery (ACM), 2017. p. 2103-2106.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - Graph ladder networks for network classification
AU - Hu, Ruiqi
AU - Pan, Shirui
AU - Jiang, Jing
AU - Long, Guodong
PY - 2017
Y1 - 2017
N2 - Numerous network representation-based algorithms for network classification have emerged in recent years, but many suffer from two limitations. First, they separate the network representation learning and node classification in networks into two steps, which may result in sub-optimal results because the node representation may not fit the classification model well, and vice versa. Second, they are mostly shallow methods that can only capture the linear and simple relationships in the data. In this paper, we propose an effective deep learning model, Graph Ladder Networks (GLN), for node classification in networks. Our model learns a ladder network which unifies the representation learning and network classification into one single framework by exploiting both labeled and unlabeled nodes in a network. To integrate both structure and node content information in the networks, the most recently developed graph convolution network, is further employed. The experiments on the most popular academic network dataset, Citeseer, demonstrate that our approach reaches outstanding performance compared to other state-of-the-art algorithms.
AB - Numerous network representation-based algorithms for network classification have emerged in recent years, but many suffer from two limitations. First, they separate the network representation learning and node classification in networks into two steps, which may result in sub-optimal results because the node representation may not fit the classification model well, and vice versa. Second, they are mostly shallow methods that can only capture the linear and simple relationships in the data. In this paper, we propose an effective deep learning model, Graph Ladder Networks (GLN), for node classification in networks. Our model learns a ladder network which unifies the representation learning and network classification into one single framework by exploiting both labeled and unlabeled nodes in a network. To integrate both structure and node content information in the networks, the most recently developed graph convolution network, is further employed. The experiments on the most popular academic network dataset, Citeseer, demonstrate that our approach reaches outstanding performance compared to other state-of-the-art algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85037355658&partnerID=8YFLogxK
U2 - 10.1145/3132847.3133124
DO - 10.1145/3132847.3133124
M3 - Conference Paper
SP - 2103
EP - 2106
BT - CIKM'17 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
A2 - Culpepper, Shane
A2 - Lo, Eric
A2 - Ho, Joyce
PB - Association for Computing Machinery (ACM)
CY - New York NY USA
ER -