TY - GEN
T1 - Unsupervised Attributed Network Embedding via Cross Fusion
AU - Pan, Guosheng
AU - Yao, Yuan
AU - Tong, Hanghang
AU - Xu, Feng
AU - Lu, Jian
N1 - Funding Information:
This work is supported by the Key-Area Research and Development Program of Guangdong Province (No. 2020B010164003), the National Natural Science Foundation of China (No. 61690204, 61672274), and the Collaborative Innovation Center of Novel Software Technology and Industrialization. Hanghang Tong is partially supported by NSF (1947135, 2003924, and 1939725).
Publisher Copyright:
© 2021 ACM.
PY - 2021/8/3
Y1 - 2021/8/3
N2 - Attributed network embedding aims to learn low dimensional node representations by combining both the network's topological structure and node attributes. Most of the existing methods either propagate the attributes over the network structure or learn the node representations by an encoder-decoder framework. However, propagation based methods tend to prefer network structure to node attributes, whereas encoder-decoder methods tend to ignore the longer connections beyond the immediate neighbors. In order to address these limitations while enjoying the best of the two worlds, we design cross fusion layers for unsupervised attributed network embedding. Specifically, we first construct two separate views to handle network structure and node attributes, and then design cross fusion layers to allow flexible information exchange and integration between the two views. The key design goals of the cross fusion layers are three-fold: 1) allowing critical information to be propagated along the network structure, 2) encoding the heterogeneity in the local neighborhood of each node during propagation, and 3) incorporating an additional node attribute channel so that the attribute information will not be overshadowed by the structure view. Extensive experiments on three datasets and three downstream tasks demonstrate the effectiveness of the proposed method.
AB - Attributed network embedding aims to learn low dimensional node representations by combining both the network's topological structure and node attributes. Most of the existing methods either propagate the attributes over the network structure or learn the node representations by an encoder-decoder framework. However, propagation based methods tend to prefer network structure to node attributes, whereas encoder-decoder methods tend to ignore the longer connections beyond the immediate neighbors. In order to address these limitations while enjoying the best of the two worlds, we design cross fusion layers for unsupervised attributed network embedding. Specifically, we first construct two separate views to handle network structure and node attributes, and then design cross fusion layers to allow flexible information exchange and integration between the two views. The key design goals of the cross fusion layers are three-fold: 1) allowing critical information to be propagated along the network structure, 2) encoding the heterogeneity in the local neighborhood of each node during propagation, and 3) incorporating an additional node attribute channel so that the attribute information will not be overshadowed by the structure view. Extensive experiments on three datasets and three downstream tasks demonstrate the effectiveness of the proposed method.
KW - local community
KW - network embedding
KW - network structure
KW - node attributes
UR - http://www.scopus.com/inward/record.url?scp=85102991172&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102991172&partnerID=8YFLogxK
U2 - 10.1145/3437963.3441763
DO - 10.1145/3437963.3441763
M3 - Conference contribution
AN - SCOPUS:85102991172
T3 - WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining
SP - 797
EP - 805
BT - WSDM 2021 - Proceedings of the 14th ACM International Conference on Web Search and Data Mining
PB - Association for Computing Machinery, Inc
T2 - 14th ACM International Conference on Web Search and Data Mining, WSDM 2021
Y2 - 8 March 2021 through 12 March 2021
ER -