Robust Spatial Filtering With Graph Convolutional Neural Networks
| العنوان: | Robust Spatial Filtering With Graph Convolutional Neural Networks |
|---|---|
| المؤلفون: | Raymond Ptucha, Andrew M. Michael, Chao Zhang, Shagan Sah, Miguel Dominguez, Felipe Petroski Such, Nathan D. Cahill, Suhas Pillai |
| المصدر: | IEEE Journal of Selected Topics in Signal Processing. 11:884-896 |
| بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2017. |
| سنة النشر: | 2017 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Theoretical computer science, Artificial neural network, Spatial filter, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, 02 engineering and technology, Filter (signal processing), 010501 environmental sciences, 01 natural sciences, Convolutional neural network, Vertex (geometry), Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, Preprocessor, 020201 artificial intelligence & image processing, Adjacency matrix, Electrical and Electronic Engineering, Spectral method, 0105 earth and related environmental sciences |
| الوصف: | 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. |
| تدمد: | 1941-0484 1932-4553 |
| DOI: | 10.1109/jstsp.2017.2726981 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::588d479dcf29e5585d979669f0d07255 https://doi.org/10.1109/jstsp.2017.2726981 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....588d479dcf29e5585d979669f0d07255 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 19410484 19324553 |
|---|---|
| DOI: | 10.1109/jstsp.2017.2726981 |