Co-authorship Network Embedding and Recommending Collaborators via Network Embedding

Makarov, Ilya; Gerasimova, Olga; Sulimov, Pavel; Zhukov, Leonid

doi:10.1007/978-3-030-11027-7_4

Cited by 20 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The masked graph is then used to learn node embeddings (using text or graph information or both). We use simple element-wise (Hadamard) product of node embeddings as encoding for the corresponding edge, leaving other edge encoder operators for future work (see Makarov et al, 2019 , 2018a , 2018b ). Finally, we train Logistic Regression on obtained vectors to classify the presence or absence of the links between pairs of nodes in the graph.…”

Section: Methodsmentioning

confidence: 99%

Fusion of text and graph information for machine learning problems on networks

Makarov

Kiselev

2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Today, increased attention is drawn towards network representation learning, a technique that maps nodes of a network into vectors of a low-dimensional embedding space. A network embedding constructed this way aims to preserve nodes similarity and other specific network properties. Embedding vectors can later be used for downstream machine learning problems, such as node classification, link prediction and network visualization. Naturally, some networks have text information associated with them. For instance, in a citation network, each node is a scientific paper associated with its abstract or title; in a social network, all users may be viewed as nodes of a network and posts of each user as textual attributes. In this work, we explore how combining existing methods of text and network embeddings can increase accuracy for downstream tasks and propose modifications to popular architectures to better capture textual information in network embedding and fusion frameworks.

show abstract

Section: Methodsmentioning

confidence: 99%

Fusion of text and graph information for machine learning problems on networks

Makarov

Kiselev

2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Makarov et al (2019aMakarov et al ( , 2019bMakarov et al ( , 2019c authors show that two-level architecture can improve the recommendation results. Firstly it predicts the collaboration itself and further estimates its quantity/quality.…”

Section: Recommender Systemsmentioning

confidence: 99%

Survey on graph embeddings and their applications to machine learning problems on graphs

Makarov

Kiselev

Nikitinsky

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Dealing with relational data always required significant computational resources, domain expertise and task-dependent feature engineering to incorporate structural information into a predictive model. Nowadays, a family of automated graph feature engineering techniques has been proposed in different streams of literature. So-called graph embeddings provide a powerful tool to construct vectorized feature spaces for graphs and their components, such as nodes, edges and subgraphs under preserving inner graph properties. Using the constructed feature spaces, many machine learning problems on graphs can be solved via standard frameworks suitable for vectorized feature representation. Our survey aims to describe the core concepts of graph embeddings and provide several taxonomies for their description. First, we start with the methodological approach and extract three types of graph embedding models based on matrix factorization, random-walks and deep learning approaches. Next, we describe how different types of networks impact the ability of models to incorporate structural and attributed data into a unified embedding. Going further, we perform a thorough evaluation of graph embedding applications to machine learning problems on graphs, among which are node classification, link prediction, clustering, visualization, compression, and a family of the whole graph embedding algorithms suitable for graph classification, similarity and alignment problems. Finally, we overview the existing applications of graph embeddings to computer science domains, formulate open problems and provide experiment results, explaining how different networks properties result in graph embeddings quality in the four classic machine learning problems on graphs, such as node classification, link prediction, clustering and graph visualization. As a result, our survey covers a new rapidly growing field of network feature engineering, presents an in-depth analysis of models based on network types, and overviews a wide range of applications to machine learning problems on graphs.

show abstract

“…Recently, various studies on network embedding [27][28][29][30][31] have attempted to represent latent vectors from the structure of the network. Makarov et al [32] applied Node2Vec [30], which is an improved method for generating random walks to improve the accuracy of co-authors. To consider research interests of authors, Kong et al [33] proposed CCRec, a method of integrating the extracted features of the topic through Word2Vec [34] in the title of a paper written by the author into the random walk of the co-author network.…”

Section: Related Workmentioning

confidence: 99%

Discovering the role model of authors by embedding research history

Jeon

Jung

2021

Journal of Information Science

View full text Add to dashboard Cite

A role model that supports career planning is important for authors in the academic area to improve research abilities. In this study, we discovered a role model in bibliographic networks based on two perspectives: (1) high research performance to be exemplary and (2) a similar research history that can be easily followed by authors. We assume that the year-wise subgraphs in the dynamic bibliographic network signify the ‘research history’. We discovered role models of authors in three steps: (1) learning vector representations of research history in dynamic bibliographic networks, (2) measuring the similarity of authors according to the research history and (3) visualising role models. With this process, we can recommend a reasonable role model whose research path the authors can easily follow. In addition, we verified the effectiveness of the research history embeddings and the accuracy of the recommended role model in a real data set.

show abstract

Co-authorship Network Embedding and Recommending Collaborators via Network Embedding

Cited by 20 publications

References 6 publications

Fusion of text and graph information for machine learning problems on networks

Fusion of text and graph information for machine learning problems on networks

Survey on graph embeddings and their applications to machine learning problems on graphs

Discovering the role model of authors by embedding research history

Contact Info

Product

Resources

About