The Experts below are selected from a list of 3 Experts worldwide ranked by ideXlab platform
Bishal Thapa - One of the best experts on this subject based on the ideXlab platform.
-
network signatures from Image representation of adjacency matrices deep transfer learning for Subgraph classification
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Kshiteesh Hegde, Malik Magdonismail, Ram Ramanathan, Bishal ThapaAbstract:We propose a novel Subgraph Image representation for classification of network fragments with the targets being their parent networks. The graph Image representation is based on 2D Image embeddings of adjacency matrices. We use this Image representation in two modes. First, as the input to a machine learning algorithm. Second, as the input to a pure transfer learner. Our conclusions from several datasets are that (a) deep learning using our structured Image features performs the best compared to benchmark graph kernel and classical features based methods; and, (b) pure transfer learning works effectively with minimum interference from the user and is robust against small data.
Kshiteesh Hegde - One of the best experts on this subject based on the ideXlab platform.
-
network signatures from Image representation of adjacency matrices deep transfer learning for Subgraph classification
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Kshiteesh Hegde, Malik Magdonismail, Ram Ramanathan, Bishal ThapaAbstract:We propose a novel Subgraph Image representation for classification of network fragments with the targets being their parent networks. The graph Image representation is based on 2D Image embeddings of adjacency matrices. We use this Image representation in two modes. First, as the input to a machine learning algorithm. Second, as the input to a pure transfer learner. Our conclusions from several datasets are that (a) deep learning using our structured Image features performs the best compared to benchmark graph kernel and classical features based methods; and, (b) pure transfer learning works effectively with minimum interference from the user and is robust against small data.
Malik Magdonismail - One of the best experts on this subject based on the ideXlab platform.
-
network signatures from Image representation of adjacency matrices deep transfer learning for Subgraph classification
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Kshiteesh Hegde, Malik Magdonismail, Ram Ramanathan, Bishal ThapaAbstract:We propose a novel Subgraph Image representation for classification of network fragments with the targets being their parent networks. The graph Image representation is based on 2D Image embeddings of adjacency matrices. We use this Image representation in two modes. First, as the input to a machine learning algorithm. Second, as the input to a pure transfer learner. Our conclusions from several datasets are that (a) deep learning using our structured Image features performs the best compared to benchmark graph kernel and classical features based methods; and, (b) pure transfer learning works effectively with minimum interference from the user and is robust against small data.
Ram Ramanathan - One of the best experts on this subject based on the ideXlab platform.
-
network signatures from Image representation of adjacency matrices deep transfer learning for Subgraph classification
arXiv: Computer Vision and Pattern Recognition, 2018Co-Authors: Kshiteesh Hegde, Malik Magdonismail, Ram Ramanathan, Bishal ThapaAbstract:We propose a novel Subgraph Image representation for classification of network fragments with the targets being their parent networks. The graph Image representation is based on 2D Image embeddings of adjacency matrices. We use this Image representation in two modes. First, as the input to a machine learning algorithm. Second, as the input to a pure transfer learner. Our conclusions from several datasets are that (a) deep learning using our structured Image features performs the best compared to benchmark graph kernel and classical features based methods; and, (b) pure transfer learning works effectively with minimum interference from the user and is robust against small data.
