Supervised Machine Learning for Link Prediction Using Path-Based Similarity Features

SummaryThe quality of the solution in resolving a complex network depends on either the speed or accuracy of the results. While some health studies prioritize high performance, fast algorithms are favored in scenarios requiring rapid decision‐making. A comprehensive understanding of the problem necessitates a detailed analysis of the network and its individual components. Betweenness Centrality (BC) and Closeness Centrality (CC) are commonly employed measures in network studies. This study introduces a new strategy to compute BC and CC that assesses their sensitivity in the scale space while measuring the shortest path. The scale space is generated by incorporating a scale parameter that is shown to achieve up to 60% performance improvements for various datasets. The study provides in‐depth insights into the importance of the scale space analysis. Finally, a flexible measurement tool is provided that is suitable for various types of problems. To demonstrate the flexibility and applicability, we experimented with two methods for 10 different graphs using the proposed approach.

“…[12][13][14] These metrics have been employed as path discriminative features to predict missing links in networks. 15 Path-based methods have been integrated…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Improving model performance of shortest‐path‐based centrality measures in network models through scale space

Menguc,

Yilmaz

2024

“…Regarding unsupervised techniques, 7 suggested leveraging node proximity and property data, and 8 used a hierarchical network method to forecast missing connections. Contrarily, supervised techniques have included supervised random walk algorithms that use labels to boost the likelihood of traversing established links, 9 while 10,11 extract features from outside sources as well as train methods on them to anticipate link development.…”

Section: Review Of Literaturementioning

confidence: 99%

Social network based link correlation using graph neural network with deep learning architectures for feature vectors prediction and classification

Sonti,

Mulpuri Santhi Sri,

Pamulapati

2024

SummaryIn recent years, social network analysis has received a lot of interest. A critical area of research in this field is link prediction. Link prediction is researched for other forms of social networks. Still, because social link networks (SLNs) change over time and depend on the discussed topics, this network has unique difficulties. Recent studies have focused on three main issues: extending link prediction to a dynamic environment, forecasting formation, and destroying network linkages that change over time. Although it is a challenging issue, deep learning (DL) techniques have been demonstrated to increase prediction accuracy significantly. This research proposes a novel approach to link correlation for social networks based on DL architectures in feature vector prediction and classification. Here the input data has been processed for smoothening and normalization with noise removal. Then, the feature vector was predicted using a dynamically structured convolutional radial basis neural network for this data. The expected feature vector has been classified using a stochastic gradient‐based graph neural network. The experimental analysis is carried out for various social network data in terms of accuracy of 98%, precision of 85%, recall of 86%, F‐1 score of 75%, AUC of 72%, and RMSE of 76%.

“…For the same reason, unmeant phrases not having a link on Wikipedia are disadvantaged, even though they might have considerable N-gram probability. In this article, the score of segment S on Wikipedia is shown with Wiki(S) computed using Equation (5).…”

Section: Segmentation Scoringmentioning

confidence: 99%

“…On the other hand, the L parameter in the proposed method is sensitive to the length of posts and not to window size. Table 4 Another discussed matter is the calculation of Wikipedia probability in Equation (5). Apart from the corpus of Wikipedia link texts, a corpus of Wikipedia titles is also collected.…”

Section: Parameters Tuningmentioning

confidence: 99%

Named entities detection by beam search algorithm

Gholami-Dastgerdi

Feizi‐Derakhshi

Forouzandeh

2022

Named entity recognition (NER) is a fundamental process in NLP and a requirement for most processes. This article aims to identify the named entities in the context of social networks. For this purpose, the idea of segmenting text into suitable and unsuitable expressions for the named entities has been used. So the contribution of this article is to process informal text in the Persian language by the Beam search algorithm to detect named entities. Due to the reproductive nature of language, new words and names are always produced, and available NER systems are inefficient in detecting new entities. The other contribution of this article is to make it possible to recognize the emerging named entity by applying dynamic external knowledge. According to a sense of the lack of datasets in low‐resource languages, N‐Gram and Wikipedia anchor datasets have been prepared for Persian and deployed as external knowledge. Also, a corpus of named entities in Persian from the telegram dataset has been generated. Three native experts have done labeling of this corpus. Evaluation of these three experts and the proposed method shows that the result of the proposed method is acceptable compared to the result of a human‐to‐human also to other methods.