Graph Representations and Applications of Citation Networks

AbstractSimple graph convolution (SGC) achieves competitive classification accuracy to graph convolutional networks (GCNs) in various tasks while being computationally more efficient and fitting fewer parameters. However, the width of SGC is narrow due to the over-smoothing of SGC with higher power, which limits the learning ability of graph representations. Here, we propose AdjMix, a simple and attentional graph convolutional model, that is scalable to wider structure and captures more nodes features information, by simultaneously mixing the adjacency matrices of different powers. We point out that the key factor of over-smoothing is the mismatched weights of adjacency matrices, and design AdjMix to address the over-smoothing of SGC and GCNs by adjusting the weights to matching values. Experiments on citation networks including Pubmed, Citeseer, and Cora show that our AdjMix improves over SGC by 2.4%, 2.2%, and 3.2%, respectively, while achieving same performance in terms of parameters and complexity, and obtains better performance in terms of classification accuracy, parameters, and complexity, compared to other baselines.

Download Full-text

Models of network formation

10.1093/oso/9780198805090.003.0013 ◽

2018 ◽

Author(s):

Mark Newman

Keyword(s):

Degree Distribution ◽

Network Formation ◽

Preferential Attachment ◽

Network Size ◽

Large Network ◽

Citation Networks ◽

Airline Networks ◽

Attachment Model ◽

Delivery Networks

This chapter describes models of the growth or formation of networks, with a particular focus on preferential attachment models. It starts with a discussion of the classic preferential attachment model for citation networks introduced by Price, including a complete derivation of the degree distribution in the limit of large network size. Subsequent sections introduce the Barabasi-Albert model and various generalized preferential attachment models, including models with addition or removal of extra nodes or edges and models with nonlinear preferential attachment. Also discussed are node copying models and models in which networks are formed by optimization processes, such as delivery networks or airline networks.

Download Full-text

Applying graph database technology for analyzing perturbed co-expression networks in cancer

Database ◽

10.1093/database/baaa110 ◽

2020 ◽

Vol 2020 ◽

Author(s):

Claire M Simpson ◽

Florian Gnad

Keyword(s):

Relational Databases ◽

Molecular Mechanisms ◽

Biological Data ◽

Database Management System ◽

Graph Database ◽

Graph Databases ◽

Graph Representations ◽

Rnaseq Data ◽

Database Technology ◽

Speed Accuracy

Abstract Graph representations provide an elegant solution to capture and analyze complex molecular mechanisms in the cell. Co-expression networks are undirected graph representations of transcriptional co-behavior indicating (co-)regulations, functional modules or even physical interactions between the corresponding gene products. The growing avalanche of available RNA sequencing (RNAseq) data fuels the construction of such networks, which are usually stored in relational databases like most other biological data. Inferring linkage by recursive multiple-join statements, however, is computationally expensive and complex to design in relational databases. In contrast, graph databases store and represent complex interconnected data as nodes, edges and properties, making it fast and intuitive to query and analyze relationships. While graph-based database technologies are on their way from a fringe domain to going mainstream, there are only a few studies reporting their application to biological data. We used the graph database management system Neo4j to store and analyze co-expression networks derived from RNAseq data from The Cancer Genome Atlas. Comparing co-expression in tumors versus healthy tissues in six cancer types revealed significant perturbation tracing back to erroneous or rewired gene regulation. Applying centrality, community detection and pathfinding graph algorithms uncovered the destruction or creation of central nodes, modules and relationships in co-expression networks of tumors. Given the speed, accuracy and straightforwardness of managing these densely connected networks, we conclude that graph databases are ready for entering the arena of biological data.

Download Full-text

Global publication trends and hotspots of molecular biomarkers in DILI from 1991 to 2020: A 30-year bibliometric analysis

Science Progress ◽

10.1177/00368504211000535 ◽

2021 ◽

Vol 104 (1) ◽

pp. 003685042110005

Author(s):

Mingnan Cao ◽

Li Wang ◽

Lin Zhang ◽

Jingli Duan

Keyword(s):

Bibliometric Analysis ◽

Research Collaboration ◽

Citation Networks ◽

Publication Trends ◽

Drug Induced ◽

Topic Area ◽

The Past ◽

Black Box Warnings ◽

The Usa ◽

Post Marketing

Drug-induced liver injury (DILI) is one of the common adverse drug reactions and the leading cause of drug development attritions, black box warnings, and post-marketing withdrawals. Current biomarkers are suboptimal in detecting DILI and predicting its outcome. This study aimed to quantitatively and qualitatively investigate the research trends on DILI biomarkers using bibliometric analysis. All relevant publications were extracted from the Web of Science database. An online analysis platform of literature metrology, bibliographic item co-occurrence matrix builder, and CiteSpace software were used to analyze the publication trends. CitNetExplorer was used to construct direct citation networks and VOSviewer was used to analyze the keywords and research hotspots. We found a total of 485 publications related to DILI biomarkers published from 1991 to 2020. Toxicological Sciences had been the most popular journal in this field over the past 30 years. The USA maintained a top position worldwide and provided a pivotal influence, followed by China. Among all the institutions, the University of Liverpool was regarded as a leader for research collaboration. Moreover, Professors Paul B. Watkins and Tsuyoshi Yokoi made great achievements in topic area. We analyzed the citation networks and keywords, therefore identified five and six research hotspot clusters, respectively. We considered the publication information regarding different countries/regions, organizations, authors, journals, et al. by summarizing the literature on DILI biomarkers over the past 30 years. Notably, the subject of DILI biomarkers is an active area of research. In addition, the investigation and discovery of novel promising biomarkers such as microRNAs, keratin18, and bile acids will be future developing hotspots.

Download Full-text

Evolution of interdependent co-authorship and citation networks

Scientometrics ◽

10.1007/s11192-020-03616-0 ◽

2020 ◽

Vol 125 (1) ◽

pp. 385-404

Author(s):

Chakresh Kumar Singh ◽

Demival Vasques Filho ◽

Shivakumar Jolad ◽

Dion R. J. O’Neale

Keyword(s):

Citation Networks

Download Full-text

Visual support for analyzing network traffic and intrusion detection events using TreeMap and graph representations

Proceedings of the Symposium on Computer Human Interaction for the Management of Information Technology - CHiMiT '09 ◽

10.1145/1641587.1641590 ◽

2009 ◽

Cited By ~ 22

Author(s):

Florian Mansmann ◽

Fabian Fischer ◽

Daniel A. Keim ◽

Stephen C. North

Keyword(s):

Intrusion Detection ◽

Network Traffic ◽

Graph Representations ◽

Visual Support

Download Full-text

A measure of standing for citation networks within a wider environment

Information Processing & Management ◽

10.1016/0306-4573(94)90021-3 ◽

1994 ◽

Vol 30 (1) ◽

pp. 21-31 ◽

Cited By ~ 6

Author(s):

Patrick Doreian

Keyword(s):

Citation Networks

Download Full-text

A New Technique Based on Loops to Investigate Displacement Isomorphism in Planetary Gear Trains

Journal of Mechanical Design ◽

10.1115/1.1503373 ◽

2002 ◽

Vol 124 (4) ◽

pp. 662-675 ◽

Cited By ~ 17

Author(s):

V. V. N. R. Prasad Raju Pathapati ◽

A. C. Rao

Keyword(s):

Graph Isomorphism ◽

Planetary Gear ◽

Degree Of Freedom ◽

Gear Train ◽

Graph Representation ◽

Kinematic Structure ◽

Graph Representations ◽

Planetary Gear Trains ◽

Gear Trains ◽

A New Technique

The most important step in the structural synthesis of planetary gear trains (PGTs) requires the identification of isomorphism (rotational as well as displacement) between the graphs which represent the kinematic structure of planetary gear train. Previously used methods for identifying graph isomorphism yielded incorrect results. Literature review in this area shows there is inconsistency in results from six link, one degree-of-freedom onwards. The purpose of this paper is to present an efficient methodology through the use of Loop concept and Hamming number concept to detect displacement and rotational isomorphism in PGTs in an unambiguous way. New invariants for rotational graphs and displacement graphs called geared chain hamming strings and geared chain loop hamming strings are developed respectively to identify rotational and displacement isomorphism. This paper also presents a procedure to redraw conventional graph representation that not only clarifies the kinematic structure of a PGT but also averts the problem of pseudo isomorphism. Finally a thorough analysis of existing methods is carried out using the proposed technique and the results in the category of six links one degree-of-freedom are established and an Atlas comprises of graph representations in conventional form as well as in new form is presented.

Download Full-text