TY - JOUR

T1 - Toward an Adaptive Skip-Gram Model for Network Representation Learning

AU - Hsieh, I. Chung

AU - Li, Cheng Te

N1 - Publisher Copyright:
© 2013 IEEE.

PY - 2022

Y1 - 2022

N2 - The random walk process on network data is a widely-used approach for network representation learning. However, we argue that the sampling of node sequences and the subsampling for the Skip-gram's contexts have two drawbacks. One is less possible to precisely find the most correlated context nodes for every central node with only uniform graph search. The other is not easily controlled due to the expensive cost of hyperparameter tuning. Such two drawbacks lead to higher training cost and lower accuracy due to abundant and irrelevant samples. To solve these problems, we compute the adaptive probability of random walk based on Personalized PageRank (PPR), and propose an Adaptive SKip-gram (ASK) model without using complicated sampling process and negative sampling. We utilize k-most important neighbors for positive samples selection, and attach their corresponding PPR probability into the objective function. Based on benchmark datasets with three citation networks and three social networks, we demonstrate the improvement of our ASK model for network representation learning in tasks of link prediction, node classification, and embedding visualization. The results achieve more effective performance and efficient learning time.

AB - The random walk process on network data is a widely-used approach for network representation learning. However, we argue that the sampling of node sequences and the subsampling for the Skip-gram's contexts have two drawbacks. One is less possible to precisely find the most correlated context nodes for every central node with only uniform graph search. The other is not easily controlled due to the expensive cost of hyperparameter tuning. Such two drawbacks lead to higher training cost and lower accuracy due to abundant and irrelevant samples. To solve these problems, we compute the adaptive probability of random walk based on Personalized PageRank (PPR), and propose an Adaptive SKip-gram (ASK) model without using complicated sampling process and negative sampling. We utilize k-most important neighbors for positive samples selection, and attach their corresponding PPR probability into the objective function. Based on benchmark datasets with three citation networks and three social networks, we demonstrate the improvement of our ASK model for network representation learning in tasks of link prediction, node classification, and embedding visualization. The results achieve more effective performance and efficient learning time.

UR - http://www.scopus.com/inward/record.url?scp=85127789130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85127789130&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2022.3164670

DO - 10.1109/ACCESS.2022.3164670

M3 - Article

AN - SCOPUS:85127789130

SN - 2169-3536

VL - 10

SP - 37506

EP - 37514

JO - IEEE Access

JF - IEEE Access

ER -