Supervised Link Prediction Using Random Walks

Liu, Yuechang; Tong, Hanghang; Xie, Lei; Tang, Yong

doi:10.1007/978-981-10-0080-5_10

Cited by 2 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RW [21]. Random walks is a commonly link prediction algorithm and it suggests that a random walker is more likely to visit the nodes to which new links will be created in the future.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…These correlations can be achieved by learning network structures and user attribute information, and we can analyze user correlations for link prediction. Various methods such as similarity computation [19,20], random walks [21,22], topic model, and probability model [23,24] are used for prediction. This section focuses on the research on link prediction and application of the LDA topic model in recent years.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Correlations multiplexing for link prediction in multidimensional network spaces

Xiao

Liu

et al. 2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Uncovering the network evolution mechanism by link prediction SCIENTIA SINICA Physica, Mechanica & Astronomica 41, 816 (2011); Link prediction in social networks: the state-of-the-art SCIENCE CHINA Information Sciences 58, 011101 (2015); Exploring link generation in a temporal evolution network for human mobility SCIENCE CHINA Technological Sciences 59, 16 (2016); Network selection based on available link bandwidth in multi-access networks 数字通信和网络 2, 15 (2016); SCIENCE CHINA Information Sciences

show abstract

“…RW [21]. Random walks is a commonly link prediction algorithm and it suggests that a random walker is more likely to visit the nodes to which new links will be created in the future.…”

Section: Baseline Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Correlations multiplexing for link prediction in multidimensional network spaces

Xiao

Liu

et al. 2018

Sci. China Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…LHN assumes that two nodes are similar if one of them has a neighbour that is similar to the other. The random walk-based methods take into account the link structures by treating all nodes of a network equally and ignoring the centrality of nodes, and have demonstrated exceptional performance in link prediction [14,15]. However, due to the fact that they take into account the entire structural topology of a network, these methods are typically time-consuming.…”

Section: Related Workmentioning

confidence: 99%

Link prediction grounded upon complex networks based model, based on MJMI-RW

Bakhat¹,

Kifayat²,

Islam

et al. 2023

Preprint

View full text Add to dashboard Cite

Link prediction is the process of predicting the connection probability between two nodes based on observable network data, such as network structural topology and node properties. Despite the fact that traditional similarity-based methods are basic and effective, their generalisation performance varies greatly across networks. In this paper, we propose a novel link prediction approach, MJMI-RW, based on the Maxwell Jüttner distribution endowed by the Mutual Information, which recovers the probability of a node's connection by applying node characteristics to a system with less computation. Initially, the method investigates a comprehensive node feature representation by combining diverse structural topology information with node importance properties through feature construction and selection. The selected node features are then fed into a supervised learning task that solves the features matrix using the node features as input. The enhancements of MJMI-RW in terms of the average area under the curve and the precision of state-of-the-art algorithms compared to the finest baseline networks when compared to baseline methods. The limitation of MJMI-RW is its minimal computational complexity feature construction and substitution of complex features with semantic node attributes. Moreover, since inductive matrix completion is a supervised learning task in which the underlying low-rank matrix can be solved by representative nodes instead of all their nodes, it offers a potential link prediction solution for large-scale networks.

show abstract

Supervised Link Prediction Using Random Walks

Cited by 2 publications

References 19 publications

Correlations multiplexing for link prediction in multidimensional network spaces

Correlations multiplexing for link prediction in multidimensional network spaces

Link prediction grounded upon complex networks based model, based on MJMI-RW

Contact Info

Product

Resources

About