TY - GEN
T1 - Deep active learning for anchor user prediction
AU - Cheng, Anfeng
AU - Zhou, Chuan
AU - Yang, Hong
AU - Wu, Jia
AU - Li, Lei
AU - Tan, Jianlong
AU - Guo, Li
PY - 2019
Y1 - 2019
N2 - Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches.
AB - Predicting pairs of anchor users plays an important role in the cross-network analysis. Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction. To this end, we present a deep active learning model for anchor user prediction (DALAUP for short). However, active learning for anchor user sampling meets the challenges of non-i.i.d. user pair data caused by network structures and the correlation among anchor or non-anchor user pairs. To solve the challenges, DALAUP uses a couple of neural networks with shared-parameter to obtain the vector representations of user pairs, and ensembles three query strategies to select the most informative user pairs for labeling and model training. Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches.
UR - http://www.scopus.com/inward/record.url?scp=85074955499&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2019/298
DO - 10.24963/ijcai.2019/298
M3 - Conference proceeding contribution
AN - SCOPUS:85074955499
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 2151
EP - 2157
BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
A2 - Kraus, Sarit
PB - International Joint Conferences on Artificial Intelligence
CY - Freiburg, Germany
T2 - 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
Y2 - 10 August 2019 through 16 August 2019
ER -