Felipe Petroski Such
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Felipe Petroski Such has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Andrew Michael
Geisinger Health System, Autism and Developmental Medicine Institute, Danville, PA, USA
1 shared publicationChao Zhang
Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY, USA
1 shared publicationMiguel Alexander Dominguez
Department of Engineering, Rochester Institute of Technology, Rochester, NY, USA
1 shared publication- Nathan D. Cahill
Rochester Institute of Technology
1 shared publication Raymond Ptucha
Department of Computer Engineering, Rochester Institute of Technology, Rochester, NY, USA
1 shared publicationShagan Sah
Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, Rochester, NY, USA
1 shared publication
Latest Publications
- 13 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 11 (6) , 884-896
Robust Spatial Filtering With Graph Convolutional Neural Networks
Convolutional neural networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite-impulse response filters are learned on a hierarchy of layers, each contributing more abstract information than the previous layer. The simplicity and elegance of the convolutional filtering process makes them perfect for structured problems, such as image, video, or voice, where vertices are homogeneous in the sense of number, location, and strength of neighbors. The vast majority of classification problems, for example in the pharmaceutical, homeland security, and financial domains are unstructured. As these problems are formulated into unstructured graphs, the heterogeneity of these problems, such as number of vertices, number of connections per vertex, and edge strength, cannot be tackled with standard convolutional techniques. We propose a novel neural learning framework that is capable of handling both homogeneous and heterogeneous data while retaining the benefits of traditional CNN successes. Recently, researchers have proposed variations of CNNs that can handle graph data. In an effort to create learnable filter banks of graphs, these methods either induce constraints on the data or require preprocessing. As opposed to spectral methods, our framework, which we term Graph-CNNs, defines filters as polynomials of functions of the graph adjacency matrix. Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets. We perform experiments to validate the applicability of Graph-CNNs to a variety of structured and unstructured classification problems and demonstrate state-of-the-art results on document and molecule classification problems.
- 13 July 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 11 (6) , 884-896
Robust Spatial Filtering With Graph Convolutional Neural Networks
Convolutional neural networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite-impulse response filters are learned on a hierarchy of layers, each contributing more abstract information than the previous layer. The simplicity and elegance of the convolutional filtering process makes them perfect for structured problems, such as image, video, or voice, where vertices are homogeneous in the sense of number, location, and strength of neighbors. The vast majority of classification problems, for example in the pharmaceutical, homeland security, and financial domains are unstructured. As these problems are formulated into unstructured graphs, the heterogeneity of these problems, such as number of vertices, number of connections per vertex, and edge strength, cannot be tackled with standard convolutional techniques. We propose a novel neural learning framework that is capable of handling both homogeneous and heterogeneous data while retaining the benefits of traditional CNN successes. Recently, researchers have proposed variations of CNNs that can handle graph data. In an effort to create learnable filter banks of graphs, these methods either induce constraints on the data or require preprocessing. As opposed to spectral methods, our framework, which we term Graph-CNNs, defines filters as polynomials of functions of the graph adjacency matrix. Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets. We perform experiments to validate the applicability of Graph-CNNs to a variety of structured and unstructured classification problems and demonstrate state-of-the-art results on document and molecule classification problems.