NODDLE: Node2vec Based Deep Learning Model for Link Prediction

Khanam, Kazi Zainab; Singhal, Aditya; Mago, Vijay

doi:10.1007/978-3-031-33614-0_14

Cited by 2 publications

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of our proposed dynamic social network link prediction method combining entropy, causality, and a GCN model, we compared it with several other hybrid algorithms. Among them, several hybrid algorithms were designed specifically with reference to the work of Khanam et al [34], who combined Node2Vec with a deep learning model and optimized the model performance by comparing the design methods of different optimizers. In addition, the Node2Vec algorithm we chose in the comparison method is based on the research of Grover et al [18]; the Deep Autoencoder model is based on the research of Yi et al [19]; the GraphSage model is based on the research of Hamilton et al [35]; and the selection of a GCN model is based on the research of Zhang et al [36].…”

Section: Resultsmentioning

confidence: 99%

Link Prediction in Dynamic Social Networks Combining Entropy, Causality, and a Graph Convolutional Network Model

Huang,

Li,

Yuan

2024

Entropy

View full text Add to dashboard Cite

Link prediction is recognized as a crucial means to analyze dynamic social networks, revealing the principles of social relationship evolution. However, the complex topology and temporal evolution characteristics of dynamic social networks pose significant research challenges. This study introduces an innovative fusion framework that incorporates entropy, causality, and a GCN model, focusing specifically on link prediction in dynamic social networks. Firstly, the framework preprocesses the raw data, extracting and recording timestamp information between interactions. It then introduces the concept of “Temporal Information Entropy (TIE)”, integrating it into the Node2Vec algorithm’s random walk to generate initial feature vectors for nodes in the graph. A causality analysis model is subsequently applied for secondary processing of the generated feature vectors. Following this, an equal dataset is constructed by adjusting the ratio of positive and negative samples. Lastly, a dedicated GCN model is used for model training. Through extensive experimentation in multiple real social networks, the framework proposed in this study demonstrated a better performance than other methods in key evaluation indicators such as precision, recall, F1 score, and accuracy. This study provides a fresh perspective for understanding and predicting link dynamics in social networks and has significant practical value.

show abstract

Section: Resultsmentioning

confidence: 99%