Loading...
Search for:
dynamic-graphs
0.006 seconds
Representation Learning for Dynamic Graphs
, M.Sc. Thesis Sharif University of Technology ; Fazli, Mohammad Amin (Supervisor)
Abstract
Representation learning methods on graphs have enabled using machine learning methods on graphs' discrete structure by transferring them to a continuous domain. As graphs' structures are not always static and may evolve through time, dynamic representation learning methods have recently gained scholars' attention. Several methods have been proposed to enable the model to update the embeddings graph changes, or new interactions happen between nodes. These online methods could significantly reduce the learning time by refreshing the model as the changes occur, so we don't need to retrain the model with the complete graph information. Moreover, by using the temporal information of interactions,...
Dynamic k-graphs: an algorithm for dynamic graph learning and temporal graph signal clustering
, Article 28th European Signal Processing Conference, EUSIPCO 2020, 24 August 2020 through 28 August 2020 ; Volume 2021-January , 2021 , Pages 2195-2199 ; 22195491 (ISSN); 9789082797053 (ISBN) ; Babaie Zadeh, M ; Achard, S ; Sharif University of Technology
European Signal Processing Conference, EUSIPCO
2021
Abstract
Graph signal processing (GSP) have found many applications in different domains. The underlying graph may not be available in all applications, and it should be learned from the data. There exist complicated data, where the graph changes over time. Hence, it is necessary to estimate the dynamic graph. In this paper, a new dynamic graph learning algorithm, called dynamic K-graphs, is proposed. This algorithm is capable of both estimating the time-varying graph and clustering the temporal graph signals. Numerical experiments demonstrate the high performance of this algorithm compared with other algorithms. © 2021 European Signal Processing Conference, EUSIPCO. All rights reserved
Dynamic Functional Connectivity in Autism Spectrum Disorder Using Resting-State fMRI
, M.Sc. Thesis Sharif University of Technology ; Fatemizadeh, Emadeddin (Supervisor)
Abstract
Autism Spectrum Disorder (ASD) is a group of neurodevelopmental disorders that cause repetitive behaviors and social and communication skills abnormalities. Autistic Disorder(AD) is one of the disorders in ASD that is being investigated in this study. There has been an increase in research about AD in recent years due to the increasing AD prevalence and the high autistic living costs. The dynamic functional connectivity between healthy and autistic groups has been analyzed by using graph theory. The brain is modeled as a dynamic graph using resting-state fMRI. The graph theory metric is calculated in the dynamic graph of each subject, and the distinction of the two groups is checked using...
Link Prediction using Dynamic Graph Neural Network with Application to Call Data
, M.Sc. Thesis Sharif University of Technology ; Jafari Siavoshani, Mahdi (Supervisor)
Abstract
In network science, link prediction is one of the essential tasks that has been neglected. One important application of link prediction in telecommunication networks is analyzing the user's consumption pattern to provide better service. This project aims to predict future links with applications to call data using the users' call history. In previous research, there are two main approaches: 1) heuristic-based approach, and 2) deep-learning-based approach, such as graph neural networks. These methods are mainly used for processing static graphs, and therefore, we cannot generalize them to dynamic graphs. But there are many graphs which are dynamic in nature. For instance, call data records...