TY - GEN
T1 - EsiNet
T2 - 31st IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2019
AU - Zheng, Anqing
AU - Feng, Chong
AU - Yang, Fang
AU - Zhang, Huanhuan
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - Network representation learning (NRL) is a crucial method to learn low-dimensional vertex representations to capture network information. However, conventional NRL models only regard each edge as a binary or continuous value while neglecting the rich semantic information on edges. To enhance network representation for Social Relation Extraction (SRE) task, we present a novel deep neural network based model, EsiNet, by learning the structure and semantic information of edges simultaneously. Compared with previous work, EsiNet focuses on further learning the interactions between vertices and capturing the correlations between labels. By jointly optimizing the objective function of these two components, EsiNet can preserve both the semantic and structural information of edges. Extensive experiments on several public datasets demonstrate that EsiNet outperforms other baselines significantly, by around 3% to 5% on hits@10 absolutely.
AB - Network representation learning (NRL) is a crucial method to learn low-dimensional vertex representations to capture network information. However, conventional NRL models only regard each edge as a binary or continuous value while neglecting the rich semantic information on edges. To enhance network representation for Social Relation Extraction (SRE) task, we present a novel deep neural network based model, EsiNet, by learning the structure and semantic information of edges simultaneously. Compared with previous work, EsiNet focuses on further learning the interactions between vertices and capturing the correlations between labels. By jointly optimizing the objective function of these two components, EsiNet can preserve both the semantic and structural information of edges. Extensive experiments on several public datasets demonstrate that EsiNet outperforms other baselines significantly, by around 3% to 5% on hits@10 absolutely.
KW - Multi-label classification
KW - Network representation learning
KW - Social relation extraction
UR - https://www.scopus.com/pages/publications/85081081695
U2 - 10.1109/ICTAI.2019.00142
DO - 10.1109/ICTAI.2019.00142
M3 - Conference contribution
AN - SCOPUS:85081081695
T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
SP - 1011
EP - 1018
BT - Proceedings - IEEE 31st International Conference on Tools with Artificial Intelligence, ICTAI 2019
PB - IEEE Computer Society
Y2 - 4 November 2019 through 6 November 2019
ER -