A novel link prediction algorithm based on inductive matrix completion

Zhao, Zhili; Gou, Zhuoyue; Du, Yarong; Ma, Jun; Li, Tongfeng; Zhang, Ruisheng

doi:10.1016/j.eswa.2021.116033

Cited by 28 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This finding is corroborated by a recent survey conducted in the field [12]. It is important to recognize that contemporary network-based methods bear relevance to matrix completion techniques [13][14][15]. Therefore, for the remainder of this study, we will adopt the nomenclature and approach of matrix completion.…”

Section: Introductionmentioning

confidence: 60%

WITHDRAWN: Antibiotic Bacteria Interaction: Dataset and Benchmarking

Chatterjee,

Majumdar,

Chouzenoux

2024

Preprint

View full text Add to dashboard Cite

This study introduces a dataset for drug-bacteria associations (DBA) that affects humans. Our contribution extends beyond merely curating the association matrix; we also conduct genomic similarity computations for all known bacteria impacting humans and assess structural similarities for all antibiotic drugs. This is a first of a kind dataset serving the fundamental goal of streamlining antibiotic repurposing for bacterial infections. We conducted thorough benchmarking on this dataset using state-of-the-art drug repurposing models. Furthermore, we applied this dataset to three case studies involving drug-resistant bacterial infections. Our results indicate that the dataset coupled with the algorithms are indeed effective for repurposing drugs with the potential for treating drug resistant bacterial infections.

show abstract

Section: Introductionmentioning

confidence: 60%

WITHDRAWN: Antibiotic Bacteria Interaction: Dataset and Benchmarking

Chatterjee,

Majumdar,

Chouzenoux

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Given an undirected and unweighted network 𝐺 = (𝑉 , 𝐸), where 𝑉 = {𝑣 1 , 𝑣 2 , … , 𝑣 𝑢 } is the set of nodes, 𝐸 = {(𝑣 𝑠 , 𝑣 𝑡 ) | 𝑣 𝑠 , 𝑣 𝑡 ∈ 𝑉 , s ≠ t} is the set of edges [6]. The basic idea of link prediction is to estimate a score 𝑠 𝑒 (s, t) to a pair of nodes p and q without edges.…”

Section: Methodsmentioning

confidence: 99%

“…Local indices, global indices, and quasi-local indices can be used to further categorise similarity-based methodologies [5]. Similarity-based methods are limited by their simplicity, which prevents them from identifying underlying potential patterns in complex networks [6]. The probabilistic methods emphasise the construction of probabilistic models that map multiple parameters to the connection probability between two nodes.…”

Section: Introductionmentioning

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

“…26,27 Static software defect prediction mainly quantifies the software code into software metric elements based on the historical development data. 28,29 A defect prediction model can be established by passing the statistical analysis of these metric elements and historical defect information. Then the model is used to predict the new software module.…”

Section: Problem Descriptionmentioning

confidence: 99%

“…Generally, the development of software defect prediction is mainly divided into static and dynamic software defect prediction 26,27 . Static software defect prediction mainly quantifies the software code into software metric elements based on the historical development data 28,29 . A defect prediction model can be established by passing the statistical analysis of these metric elements and historical defect information.…”

Section: Problem Descriptionmentioning

confidence: 99%

A novel multi‐objective immune optimization algorithm for under sampling software defect prediction problem

Ye¹,

Li²,

Zhang

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Data imbalance and parameter selection have always been two important factors affecting the accuracy of software defect prediction. However, the existing methods have been poor in balancing these two factors. To address this challenge, a multi‐objective software defect prediction model is employed to describe the under sampled software defect prediction problem. And in this model, defect detection rate and defect false alarm rate are deemed as two objectives which should be optimized. Simultaneously, we design a novel multi‐objective immune optimization algorithm based on the comprehensive fitness of evaluation mechanism to effectively address the employed model. In the algorithm, the original mechanism based on neighborhood individual selection is replaced based on comprehensive fitness evaluation,which have better selection ability to attaining the predicted effect of software to improving in the process of selection solution of population evolution and further effectively help decision makers choose better scheme that meets requirements. In addition, in order to verify the effectiveness of the designed algorithm, the proposed algorithm is compared on eight different public data sets. Simulation results show that the proposed algorithm has better performance in handling with the multi‐objective under sampling software defect prediction problem.

show abstract

A novel link prediction algorithm based on inductive matrix completion

Cited by 28 publications

References 38 publications

WITHDRAWN: Antibiotic Bacteria Interaction: Dataset and Benchmarking

WITHDRAWN: Antibiotic Bacteria Interaction: Dataset and Benchmarking

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

A novel multi‐objective immune optimization algorithm for under sampling software defect prediction problem

Contact Info

Product

Resources

About