Joint Node-Edge Network Embedding for Link Prediction

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

doi:10.1007/978-3-030-11027-7_3

Cited by 23 publications

(7 citation statements)

References 38 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

“…Stacking convolutional layers allows information to propagate not only from the local neighborhood but also from the distant neighbor nodes. In addition, methods for joint node and edge embedding allow to train semi-supervised [20], [21] and self-supervised [22] models for certain sparse graphs.…”

Section: Related Workmentioning

confidence: 99%

Fast Approximate Convex Hull Construction in Networks via Node Embedding

Gavrilev

Makarov²

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Geodesic convexity in networks is an intrinsic property of graphs. It aids in distinguishing between real-world networks and random graphs. One possible application is recommending new connections in a collaborative network by searching for them in the so-called convex hull, which is a minimal subgraph containing all the shortest paths between its nodes. However, the existing algorithms for constructing convex hulls from subsets of nodes involve extensive search over subgraphs and have poor scalability. Thus, they become inapplicable to large graphs such as social networks. In this paper, we propose a new approach for fast convex hull construction for a subset of nodes on a network using graph embeddings. We apply the well-known convexity concept in embedding space to a similar problem for geometric learning on a graph, optimizing the process of finding all the shortest paths in the induced subgraph. To preserve the metric characteristics of a network, we train a graph neural network with an L1-distance loss. As a result, the trained model enables us to approximately verify the convexity of subgraphs in linear time, contrary to the previous approaches, which have cubic complexity.

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

Joint Node-Edge Network Embedding for Link Prediction

Cited by 23 publications

References 38 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

Fast Approximate Convex Hull Construction in Networks via Node Embedding

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

Contact Info

Product

Resources

About