Loading...
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 52406 (05)
- University: Sharif University of Technology
- Department: Electrical Engineering
- Advisor(s): Salehkaleybar, Saber; Hashemi, Matin
- Abstract:
- Nowadays, thanks to improvement of processing hardware and plenty of data available, artificial intelligence and specifically Deep Learning are being one of the powerful tools for solving different problems. Also graph is one of the powerful tools for modeling different data structures. Graph matching is one of the problems in the field of graph problems.In this thesis we consider the problem of graph matching in Erdos-Renyi graphs. The graph matching problem refers to recovering the node-to-node correspondence between two correlated graphs. Previous works theoretically showed that recovering is feasible in sparse Erdos-R´enyi graphs if and only if the probability of having an edge between a pair of nodes in one of the graphs and also between the corresponding nodes in the other graph is in the order of Ω(log(n)/n), where n is the number of nodes. In this thesis, we propose two seedless graph matching algorithms which one of them uses the structural information in matching nodes and the other is based on deep neural networks. We experimentally evaluate both proposed algorithm on Erdos-R´enyi graphs in both Θ(log(n)/n) and Θ(log2(n)/n) regions. The proposed algorithms outperform previous methods in both regions
- Keywords:
- Graphs ; Graph Matching ; Deep Neural Networks ; Deep Convolutional Neural Networks ; Learning Algorithm
- محتواي کتاب
- view