Node Representation Learning for Directed Graphs

Khosla, Megha; Leonhardt, Jurek; Nejdl, Wolfgang; Anand, Avishek

doi:10.1007/978-3-030-46150-8_24

Cited by 30 publications

(43 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NERD [28]: for two nodes u and v with roles r and r 2 , respectively, NERD tries to find representations f r 1 (u) and f r 2 (v) by utilizing ASGD [53] to maximize the following objective function:…”

Section: Discussionmentioning

confidence: 99%

“…The training process is a two-player game where the adversarial samples are generated to maximize the model loss while the embedding vectors are optimized against them by utilizing stochastic gradient descent (SGD) [47]. NERD [28]: it mainly considers two different roles, a source and a target, for any nodes in the graph and maintains separate embedding spaces for the two distinct roles; based on this consideration, it exploits two distinct neighborhoods for each node and tries to maximize the likelihood of preserving both neighborhoods in their corresponding embedding spaces at the learning process.…”

Section: Graph Embedding Methodsmentioning

confidence: 99%

“…Graph embedding methods (in short, embedding methods), also known as feature representation learning methods, exploit the graph structure to represent each node in the graph as a low-dimensional vector in which neighborhood similarity, semantic information, and community structure among nodes in the graph are captured [22][23][24][25]. The obtained vector representations can be utilized by a wide range of tasks such as link prediction [22,24,[26][27][28], node classification [22,23,[25][26][27][28][29][30], recommendations [27], word analogy detection [25], and document classification [25]. Embedding methods, which are effective for extracting features from graph structured data, have broadly attracted significant attention in the literature and different embedding methods such as DeepWalk [23], Line [25], node2vec [26], graph-GAN [27], NetMF [29], ATP [24], BoostNE [30], DWNS [22], and NERD [28] have been proposed for homogeneous graphs.…”

Section: Introductionmentioning

confidence: 99%

“…The obtained vector representations can be utilized by a wide range of tasks such as link prediction [22,24,[26][27][28], node classification [22,23,[25][26][27][28][29][30], recommendations [27], word analogy detection [25], and document classification [25]. Embedding methods, which are effective for extracting features from graph structured data, have broadly attracted significant attention in the literature and different embedding methods such as DeepWalk [23], Line [25], node2vec [26], graph-GAN [27], NetMF [29], ATP [24], BoostNE [30], DWNS [22], and NERD [28] have been proposed for homogeneous graphs. In addition, some embedding methods have been proposed that target the heterogeneous graphs such as HeGAN [31], RTN [32], and HAN [33].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On Investigating Both Effectiveness and Efficiency of Embedding Methods in Task of Similarity Computation of Nodes in Graphs

Hamedani

Kim

2020

Applied Sciences

View full text Add to dashboard Cite

One of the important tasks in a graph is to compute the similarity between two nodes; link-based similarity measures (in short, similarity measures) are well-known and conventional techniques for this task that exploit the relations between nodes (i.e., links) in the graph. Graph embedding methods (in short, embedding methods) convert nodes in a graph into vectors in a low-dimensional space by preserving social relations among nodes in the original graph. Instead of applying a similarity measure to the graph to compute the similarity between nodes a and b, we can consider the proximity between corresponding vectors of a and b obtained by an embedding method as the similarity between a and b. Although embedding methods have been analyzed in a wide range of machine learning tasks such as link prediction and node classification, they are not investigated in terms of similarity computation of nodes. In this paper, we investigate both effectiveness and efficiency of embedding methods in the task of similarity computation of nodes by comparing them with those of similarity measures. To the best of our knowledge, this is the first work that examines the application of embedding methods in this special task. Based on the results of our extensive experiments with five well-known and publicly available datasets, we found the following observations for embedding methods: (1) with all datasets, they show less effectiveness than similarity measures except for one dataset, (2) they underperform similarity measures with all datasets in terms of efficiency except for one dataset, (3) they have more parameters than similarity measures, thereby leading to a time-consuming parameter tuning process, (4) increasing the number of dimensions does not necessarily improve their effectiveness in computing the similarity of nodes.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Graph Embedding Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Investigating Both Effectiveness and Efficiency of Embedding Methods in Task of Similarity Computation of Nodes in Graphs

Hamedani

Kim

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The tasks of vertex representation learning and vertex collocation profiling (VCP) for the purpose of topological link analysis and prediction were introduced in [106,107], respectively. Comprehensive information on the surrounding local structure of embedded pairs of vertices v x and v y in terms of their common membership in all possible subgraphs of n vertices over a set of r relations is available from their VCP, written as VCP n,r…”

Section: Learning-based Methodsmentioning

confidence: 99%

Review on Learning and Extracting Graph Features for Link Prediction

Mutlu

Oghaz

Rajabi

et al. 2020

MAKE

View full text Add to dashboard Cite

Link prediction in complex networks has attracted considerable attention from interdisciplinary research communities, due to its ubiquitous applications in biological networks, social networks, transportation networks, telecommunication networks, and, recently, knowledge graphs. Numerous studies utilized link prediction approaches in order sto find missing links or predict the likelihood of future links as well as employed for reconstruction networks, recommender systems, privacy control, etc. This work presents an extensive review of state-of-art methods and algorithms proposed on this subject and categorizes them into four main categories: similarity-based methods, probabilistic methods, relational models, and learning-based methods. Additionally, a collection of network data sets has been presented in this paper, which can be used in order to study link prediction. We conclude this study with a discussion of recent developments and future research directions.

show abstract

metanetwork: A R package dedicated to handling and representing trophic metanetworks

Ohlmann,

Garnier,

Vuillon

2023

Ecology and Evolution

View full text Add to dashboard Cite

Trophic networks describe interactions between species at a given location and time. Due to environmental changes, anthropogenic perturbations or sampling effects, trophic networks may vary in space and time. The collection of network time series or networks in different sites thus constitutes a metanetwork. We present here the R package metanetwork, which will ease the representation, the exploration and analysis of trophic metanetwork data sets that are increasingly available. Our main methodological advance consists in suitable layout algorithm for trophic networks, which is based on trophic levels and dimension reduction in a graph diffusion kernel. In particular, it highlights relevant features of trophic networks (trophic levels, energetic channels). In addition, we developed tools to handle, compare visually and quantitatively and aggregate those networks. Static and dynamic visualisation functions have been developed to represent large networks. We apply our package workflow to several trophic network data sets.

show abstract

Node Representation Learning for Directed Graphs

Cited by 30 publications

References 19 publications

On Investigating Both Effectiveness and Efficiency of Embedding Methods in Task of Similarity Computation of Nodes in Graphs

On Investigating Both Effectiveness and Efficiency of Embedding Methods in Task of Similarity Computation of Nodes in Graphs

Review on Learning and Extracting Graph Features for Link Prediction

metanetwork: A R package dedicated to handling and representing trophic metanetworks

Contact Info

Product

Resources

About