ENHANCED LINK PREDICTION USING MACHINE LEARNING AND DEEP LEARNING TECHNIQUES

Abstract

The ultimate aim of link prediction is to identify the possible potential connections in a network. The study on this topic has gained impetus as it results in efficiently saving resources, time, cost and effort to analyze future possibilities in a network. With the refined use of this technique, it significantly improves how the complex networks like social network analysis, biological networks, and recommendation systems are interpreted vis-à-vis experimental processes. In this paper, we propose a novel combination of five node centralities and four similarity measures with the aim of capturing both local and global features of networks. Consequently, feature vector made by integration of these five node centralities and four similarity indices are then passed through Machine Learning(ML) classifiers. By combination of results of different classifiers according to dynamic weighting scheme, the integrated classifier is then utilized for final link prediction. We have also analyzed the effect of varying thresholds on the ROC AUC and F1 scores and the same have been tabulated. This paper provides insights into the effectiveness of combining graph-theoretic features with ML models for accurate link prediction. The understanding of time dependent dynamics in evolving network interactions is crucial for applications ranging across various domains. In this paper, we introduce TA-GC-LSTM (Temporal Adaptive Graph Convolutional Long Short- Term Memory) which uses deep learning framework with novel combination of models. This proposed model of ours, efficiently captures spatial dependencies through graph convolution, temporal sequences using LSTM, and gives selective importance to influential time steps through the attention mechanism. In contravention to traditional methods, which rely on static graph representations, TA-GC-LSTM dynamically learns the temporal evolution of node relationships, enhancing predictive accuracy in link prediction tasks. In our framework, we have carried out processing of datasets by binning interactions into fixed time windows, encoding unique nodes with learnable embeddings, and filtering sparse time steps to optimize computational efficiency. To validate our approach, we have tested the model on three real-world datasets and compared our model performance against Graph Convolution Embedded LSTM (GC-LSTM) and Temporal Graph Convolutional Network (T-GCN) as benchmarks across multiple evaluation metrics. Our results demonstrated that TA-GC- LSTM outperforms baseline models, achieving an AUC score of 93%, while maintaining computational efficiency, making it a robust solution for modelling evolving graph structures.