Local-Aggregation Graph Networks
- 8 May 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. PP (01628828) , 1
Abstract
Convolutional neural networks (CNNs) provide a dramatically powerful class of models, but are subject to traditional convolution that can merely aggregate permutation-ordered and dimension-equal local inputs. It causes that CNNs are allowed to only manage signals on Euclidean or grid-like domains (e.g., images), not ones on non-Euclidean or graph domains (e.g., traffic networks). To eliminate this limitation, we develop a local-aggregation function, a sharable nonlinear operation, to aggregate permutation-unordered and dimension-unequal local inputs on non-Euclidean domains. In the context of the function approximation theory, the local-aggregation function is parameterized with a group of orthonormal polynomials in an effective and efficient manner. By replacing the traditional convolution in CNNs with the parameterized local-aggregation function, Local-Aggregation Graph Networks (LAGNs) are readily established, which enable to fit nonlinear functions without activation functions and can be expediently trained with the standard back-propagation. Extensive experiments on various datasets strongly demonstrate the effectiveness and efficiency of LAGNs, leading to superior performance on numerous pattern recognition and machine learning tasks, including text categorization, molecular activity detection, taxi flow prediction, and image classification.Keywords
Funding Information
- National Natural Science Foundation of China (61573352, 61773377, 91646207)
- Natural Science Foundation of Beijing Municipality (L172053)
This publication has 26 references indexed in Scilit:
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- Advances in natural language processingScience, 2015
- Region-Based Convolutional Networks for Accurate Object Detection and SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Global Contrast Based Salient Region DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- The Stanford CoreNLP Natural Language Processing Toolkit2014
- Good Practice in Large-Scale Learning for Image ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Wavelets on graphs via spectral graph theoryApplied and Computational Harmonic Analysis, 2011
- A new model for learning in graph domains2006
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998