scholarly journals Node Embedding over Temporal Graphs

2019 ◽  
Author(s):  
Uriel Singer ◽  
Ido Guy ◽  
Kira Radinsky
Keyword(s):  
Link Prediction ◽  
Clustering Coefficient ◽  
Joint Optimization ◽  
Performance Improvements ◽  
Label Node ◽  
Node Classification ◽  
Temporal Graphs ◽  
The Given ◽  
Over Time ◽  
Node Embeddings

In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that creates a temporal embedding of a node by learning to combine its historical temporal embeddings, such that it optimizes per given task (e.g., link prediction). The algorithm is initialized using static node embeddings, which are then aligned over the representations of a node at different time points, and eventually adapted for the given task in a joint optimization. We evaluate the effectiveness of our approach over a variety of temporal graphs for the two fundamental tasks of temporal link prediction and multi-label node classification, comparing to competitive baselines and algorithmic alternatives. Our algorithm shows performance improvements across many of the datasets and baselines and is found particularly effective for graphs that are less cohesive, with a lower clustering coefficient.

scholarly journals Structural Hierarchy-Enhanced Network Representation Learning

2020 ◽  
Vol 10 (20) ◽  
pp. 7214
Author(s):  
Cheng-Te Li ◽  
Hong-Yu Lin
Keyword(s):  
Network Topology ◽  
Link Prediction ◽  
Main Idea ◽  
Representation Learning ◽  
Coarse Grained ◽  
Community Knowledge ◽  
Structural Hierarchy ◽  
Network Representation ◽  
Node Classification ◽  
Node Embeddings

Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding space, nor model coarse-grained community knowledge hidden behind the network topology. In this paper, we propose a novel NRL framework, Structural Hierarchy Enhancement (SHE), to deal with such two issues. The main idea is to construct a structural hierarchy from the network based on community detection, and to utilize such a hierarchy to perform level-wise NRL. In addition, lower-level node embeddings are passed to higher-level ones so that community knowledge can be aware of in NRL. Experiments conducted on benchmark network datasets show that SHE can significantly boost the performance of NRL in both tasks of NC and LP, compared to other hierarchical NRL methods.

scholarly journals Discovering latent node Information by graph attention network

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Weiwei Gu ◽  
Fei Gao ◽  
Xiaodan Lou ◽  
Jiang Zhang
Keyword(s):  
Supervised Learning ◽  
Link Prediction ◽  
Learning Algorithm ◽  
Network Visualization ◽  
Graph Structure ◽  
High Quality ◽  
Node Centrality ◽  
Influential Nodes ◽  
Node Classification ◽  
Highly Cited

AbstractIn this paper, we propose graph attention based network representation (GANR) which utilizes the graph attention architecture and takes graph structure as the supervised learning information. Compared with node classification based representations, GANR can be used to learn representation for any given graph. GANR is not only capable of learning high quality node representations that achieve a competitive performance on link prediction, network visualization and node classification but it can also extract meaningful attention weights that can be applied in node centrality measuring task. GANR can identify the leading venture capital investors, discover highly cited papers and find the most influential nodes in Susceptible Infected Recovered Model. We conclude that link structures in graphs are not limited on predicting linkage itself, it is capable of revealing latent node information in an unsupervised way once a appropriate learning algorithm, like GANR, is provided.

scholarly journals MultiVERSE: a multiplex and multiplex-heterogeneous network embedding approach

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Léo Pio-Lopez ◽  
Alberto Valdeolivas ◽  
Laurent Tichit ◽  
Élisabeth Remy ◽  
Anaïs Baudot
Keyword(s):  
Heterogeneous Networks ◽  
Heterogeneous Network ◽  
Link Prediction ◽  
Network Embedding ◽  
Multiplex Networks ◽  
Multiplex Network ◽  
Gene Associations ◽  
Different Types ◽  
Embedding Methods ◽  
Node Embeddings

AbstractNetwork embedding approaches are gaining momentum to analyse a large variety of networks. Indeed, these approaches have demonstrated their effectiveness in tasks such as community detection, node classification, and link prediction. However, very few network embedding methods have been specifically designed to handle multiplex networks, i.e. networks composed of different layers sharing the same set of nodes but having different types of edges. Moreover, to our knowledge, existing approaches cannot embed multiple nodes from multiplex-heterogeneous networks, i.e. networks composed of several multiplex networks containing both different types of nodes and edges. In this study, we propose MultiVERSE, an extension of the VERSE framework using Random Walks with Restart on Multiplex (RWR-M) and Multiplex-Heterogeneous (RWR-MH) networks. MultiVERSE is a fast and scalable method to learn node embeddings from multiplex and multiplex-heterogeneous networks. We evaluate MultiVERSE on several biological and social networks and demonstrate its performance. MultiVERSE indeed outperforms most of the other methods in the tasks of link prediction and network reconstruction for multiplex network embedding, and is also efficient in link prediction for multiplex-heterogeneous network embedding. Finally, we apply MultiVERSE to study rare disease-gene associations using link prediction and clustering. MultiVERSE is freely available on github at https://github.com/Lpiol/MultiVERSE.

scholarly journals “Golden Prague”, “a Promised South” and the rest...? Regional and settlement preferences of the inhabitants of Czechia

Geografie ◽  
2014 ◽  
Vol 119 (3) ◽  
pp. 218-239 ◽  
Author(s):  
Marie Štefánková ◽  
Dušan Drbohlav
Keyword(s):  
Theoretical Framework ◽  
Representative Survey ◽  
Residential Preferences ◽  
Czech Population ◽  
Research Activities ◽  
Current State ◽  
The Given ◽  
Coherent Picture ◽  
Over Time

The article deals with regional and residential preferences of the Czech population. Regional and settlement preferences represent an interdisciplinary issue, which is relevant mostly to geography and sociology. In this article, the given issue is presented under the umbrella of a broader theoretical framework in the context of Czech and foreign studies. Selected important outputs of previous research activities in the field of regional and settlement preferences are discussed within this study, which enables it to draw a coherent picture of the given issues in Czechia and their developments over time. The main analysis is devoted to the current state of preferences of the Czech population. It is based on a representative survey, which was carried out in December 2010. The aim of the article is not only to make a comparison of regional and residential preferences over a period of almost 40 years, but also to juxtapose the patterns of regional preferences with real migration movements of the Czech population.

scholarly journals A novel similarity measure for missing link prediction in social networks

2020 ◽  
Vol 19 (2) ◽  
pp. 1071
Author(s):  
Gogulamudi Naga Chandrika ◽  
E. Srinivasa Reddy
Keyword(s):  
Social Networks ◽  
Complex Networks ◽  
Similarity Measure ◽  
Network Theory ◽  
Link Prediction ◽  
Prediction Methods ◽  
Missing Link ◽  
The Social ◽  
Hidden Patterns ◽  
Over Time

<p><span>Social Networks progress over time by the addition of new nodes and links, form associations with one community to the other community. Over a few decades, the fast expansion of Social Networks has attracted many researchers to pay more attention towards complex networks, the collection of social data, understand the social behaviors of complex networks and predict future conflicts. Thus, Link prediction is imperative to do research with social networks and network theory. The objective of this research is to find the hidden patterns and uncovered missing links over complex networks. Here, we developed a new similarity measure to predict missing links over social networks. The new method is computed on common neighbors with node-to-node distance to get better accuracy of missing link prediction. </span><span>We tested the proposed measure on a variety of real-world linked datasets which are formed from various linked social networks. The proposed approach performance is compared with contemporary link prediction methods. Our measure makes very effective and intuitive in predicting disappeared links in linked social networks.</span></p>

Finding Minimal Infrequent Elements in Multi-Dimensional Data Defined over Partially Ordered Sets and its Applications

2010 ◽  
pp. 98-116
Author(s):  
Khaled M. Elbassioni
Keyword(s):  
Association Rules ◽  
Partially Ordered Set ◽  
Quantitative Data ◽  
Partially Ordered Sets ◽  
Threshold Value ◽  
Ordered Sets ◽  
Time Intervals ◽  
Partially Ordered ◽  
The Given ◽  
Over Time

The authors consider databases in which each attribute takes values from a partially ordered set (poset). This allows one to model a number of interesting scenarios arising in different applications, including quantitative databases, taxonomies, and databases in which each attribute is an interval representing the duration of a certain event occurring over time. A natural problem that arises in such circumstances is the following: given a database D and a threshold value t, find all collections of “generalizations” of attributes which are “supported” by less than t transactions from D. They call such collections infrequent elements. Due to monotonicity, they can reduce the output size by considering only minimal infrequent elements. We study the complexity of finding all minimal infrequent elements for some interesting classes of posets. The authors show how this problem can be applied to mining association rules in different types of databases, and to finding “sparse regions” or “holes” in quantitative data or in databases recording the time intervals during which a re-occurring event appears over time. Their main focus will be on these applications rather than on the correctness or analysis of the given algorithms.

scholarly journals Unpacking Changing Multi-Actor and Multi-Level Actor Ties in Transformative Spaces: Insights from a Degraded Landscape, Machubeni, South Africa

Land ◽  
2020 ◽  
Vol 9 (7) ◽  
pp. 227
Author(s):  
Menelisi Falayi ◽  
James Gambiza ◽  
Michael Schoon
Keyword(s):  
South Africa ◽  
Collective Action ◽  
Land Degradation ◽  
Network Evolution ◽  
Clustering Coefficient ◽  
Edge Density ◽  
Policy Outcomes ◽  
Local Municipality ◽  
Multi Level ◽  
Over Time

The loss of ecosystem services through land degradation continues to be a significant concern for policymakers and land users around the world. Facilitating collective action among various actors is regarded as imperative in halting land degradation. Despite extensive research on collective action, there have been few studies that continuously map social ties and detect network evolution as a way of enabling longitudinal analysis of transformative spaces. This paper seeks to examine the changing dynamics of multi-actor and multi-level actor ties over a period of two years in Machubeni, South Africa. To do this, we used social network analysis to detect continuities and/or discontinuities of multi-actor and multi-level actor ties over time. Overall, edge density, clustering coefficient, and reciprocity scores steadily increased over the two years despite a decline in the number of active organisations within the network. Our results demonstrate that the proportion of strong ties gradually increased over time across three governance networks. However, multi-level linkages between the local municipality and the local organisations remained weak due to a lack of trust and collaborative fatigue. While the transformative space has succeeded in enhancing collaboration and knowledge sharing between local organisations and researchers, further long-term engagement with government agencies might be necessary for promoting institutional transformations and policy outcomes, and building network resilience in complex polycentric governance systems.

A computational functional genomics based self-limiting self-concentration mechanism of cell specialization as a biological role of jumping genes

2016 ◽  
Vol 8 (1) ◽  
pp. 91-103 ◽  
Author(s):  
Jörn Lötsch ◽  
Alfred Ultsch
Keyword(s):  
Functional Genomics ◽  
Biological Role ◽  
Active Line ◽  
Jumping Genes ◽  
The Given ◽  
Over Time ◽  
Cell Specialization

LINE-1 retrotransposition may result in silencing of genes. This is more likely with genes not carrying active LINE-1 as those are about 10 times more frequent in the given set of genes. Over time this leads to self-specialization of the cell toward processes associated with gene carrying active LINE-1, which then functionally prevail in the chronified situation.

scholarly journals Link Prediction and Node Classification Based on Multitask Graph Autoencoder

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shicong Chen ◽  
Deyu Yuan ◽  
Shuhua Huang ◽  
Yang Chen
Keyword(s):  
Loss Function ◽  
Link Prediction ◽  
Deep Level ◽  
Preferential Attachment ◽  
Similarity Index ◽  
Representation Learning ◽  
High Order ◽  
Fine Tuning ◽  
Common Neighbor ◽  
Node Classification

The goal of network representation learning is to extract deep-level abstraction from data features that can also be viewed as a process of transforming the high-dimensional data to low-dimensional features. Learning the mapping functions between two vector spaces is an essential problem. In this paper, we propose a new similarity index based on traditional machine learning, which integrates the concepts of common neighbor, local path, and preferential attachment. Furthermore, for applying the link prediction methods to the field of node classification, we have innovatively established an architecture named multitask graph autoencoder. Specifically, in the context of structural deep network embedding, the architecture designs a framework of high-order loss function by calculating the node similarity from multiple angles so that the model can make up for the deficiency of the second-order loss function. Through the parameter fine-tuning, the high-order loss function is introduced into the optimized autoencoder. Proved by the effective experiments, the framework is generally applicable to the majority of classical similarity indexes.

Sign in / Sign up

Export Citation Format

Share Document