Collaborative linear manifold learning for link prediction in heterogeneous networks

Liu, Jiahui; Xu, Jin; Hong, Yuxiang; Liu, Fan; Chen, QiXiang; Huang, Yalou; Liu, Mingming; Xie, MaoQiang; Sun, FengChi

doi:10.1016/j.ins.2019.09.054

Cited by 9 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The manifold was regularized to reduce dimensionality; the representation needs to remain within an approximate low-dimensional space; by combining matrix factorization with manifold regularization, the final objective function is obtained. Similarly, Liu et al 56 (2020) embedded both the DDI network and auxiliary network in a manifold. This approach, called the collaborative linear manifold learning model (CLML) ensures consistency in optimizing node similarity between the two networks.…”

Section: Based On Matrix Factorization Prediction Methodsmentioning

confidence: 99%

Application of Artificial Intelligence in Drug–Drug Interactions Prediction: A Review

Zhang

Deng

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Drug–drug interactions (DDI) are a critical aspect of drug research that can have adverse effects on patients and can lead to serious consequences. Predicting these events accurately can significantly improve clinicians’ ability to make better decisions and establish optimal treatment regimens. However, manually detecting these interactions is time-consuming and labor-intensive. Utilizing the advancements in Artificial Intelligence (AI) is essential for achieving accurate forecasts of DDIs. In this review, DDI prediction tasks are classified into three types according to the type of DDI prediction: undirected DDI prediction, DDI events prediction, and Asymmetric DDI prediction. The paper then reviews the progress of AI for each of these three prediction tasks in DDI and provides a summary of the data sets used as well as the representative methods used in these three prediction directions. In this review, we aim to provide a comprehensive overview of drug interaction prediction. The first section introduces commonly used databases and presents an overview of current research advancements and techniques across three domains of DDI. Additionally, we introduce classical machine learning techniques for predicting undirected drug interactions and provide a timeline for the progression of the predicted drug interaction events. At last, we debate the difficulties and prospects of AI approaches at predicting DDI, emphasizing their potential for improving clinical decision-making and patient outcomes.

show abstract

Section: Based On Matrix Factorization Prediction Methodsmentioning

confidence: 99%

Application of Artificial Intelligence in Drug–Drug Interactions Prediction: A Review

Zhang

Deng

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…e autoencoder, proposed by Hinton et al as a generative model [47], shows excellent performance in nonlinear manifold learning [6]. is neural model projects data from high dimension to low dimension [48] and makes sure the extracted features are robust even in learning multiple modalities [49]. is method shall be suitable to capture traffic features in real-time traffic condition maps.…”

Section: Complexitymentioning

confidence: 99%

How to Identify Patterns of Citywide Dynamic Traffic at a Low Cost? An In‐Depth Neural Network Approach with Digital Maps

Zhang

Гонг

et al. 2021

Complexity

View full text Add to dashboard Cite

The identification and analysis of the spatiotemporal dynamic traffic patterns in citywide road networks constitute a crucial process for complex traffic management and control. However, city-scale and synchronal traffic data pose challenges for such kind of quantification, especially during peak hours. Traditional studies rely on data from road-based detectors or multiple communication systems, which are limited in not only access but also coverage. To avoid these limitations, we introduce real-time, traffic condition digital maps as our input. The digital maps keep spatiotemporal urban traffic information in nature and are open to access. Their pixel colors represent traffic conditions on corresponding road segments. We propose a stacked convolutional autoencoder-based method to extract a low-dimension feature vector for each input. We compute and analyze the distances between vectors. The statistical results show different traffic patterns during given periods. With the actual data of Chongqing city, we compare the feature extraction performance between our proposed method and histogram. The result shows our proposed method can extract spatiotemporal features better. For the same data set, there is little difference in the number distribution of red pixels found in the statistics result of the histogram, while differences do exist in the results of our proposed method. We find the most fluctuated morning is on Friday; the most fluctuated evening is on Tuesday; and the most stable evening is on Wednesday. The distance captured by our method can represent the evolution of different traffic conditions during the morning and evening peak hours. Our proposed method provides managers with assistance to sense the dynamics of citywide traffic conditions in quantity.

show abstract

“…J. Liu et al [62] have introduced the Collaborative Linear Manifold Learning (CLML) algorithm. It is useful to optimize node similarities' consistency [62].…”

Section: ) Node Type-basedmentioning

confidence: 99%

“…Liu et al [62] have introduced the Collaborative Linear Manifold Learning (CLML) algorithm. It is useful to optimize node similarities' consistency [62]. Furthermore, Jichao Li et al [107] proposed a heterogeneous combat network link prediction based on the meta-path approach (HCNMP) to solve the simultaneous prediction problem of multiple link types for a heterogeneous combat network (HCN).…”

Section: ) Node Type-basedmentioning

confidence: 99%

Taxonomy of Link Prediction for Social Network Analysis: A Review

2020

View full text Add to dashboard Cite

Link prediction is a technique to forecast future new or missing relationships between entities based on the current network information. Graph theory and network science are theoretical concepts that have influenced the link prediction research. Although previous reviews clearly outlined the link prediction research, it was focused on describing prediction approaches only. However, analysis of related studies identified other components that influence link prediction. This review aims to present a continued review and introduce the taxonomy of link prediction using three main components: the prediction approaches, prediction features, and prediction measurements. Each component has been detailed using its own taxonomy available at the present review. Furthermore, this review compares the prediction approaches and prediction features also benchmark algorithms and measurement methods of previous link prediction studies. In conclusion, the previous studies mostly focused on structural features and similarity-based approaches, while measuring the proposed methods using the Area Under the Curve (AUC) score. The proposed link prediction taxonomy can guide the researchers to generate new ideas and innovations that contribute to the link prediction research.

show abstract

Collaborative linear manifold learning for link prediction in heterogeneous networks

Cited by 9 publications

References 21 publications

Application of Artificial Intelligence in Drug–Drug Interactions Prediction: A Review

Application of Artificial Intelligence in Drug–Drug Interactions Prediction: A Review

How to Identify Patterns of Citywide Dynamic Traffic at a Low Cost? An In‐Depth Neural Network Approach with Digital Maps

Taxonomy of Link Prediction for Social Network Analysis: A Review

Contact Info

Product

Resources

About