Timezone: »

 
Poster
Structure-Aware Convolutional Neural Networks
Jianlong Chang · Jie Gu · Lingfeng Wang · GAOFENG MENG · SHIMING XIANG · Chunhong Pan

Tue Dec 04 07:45 AM -- 09:45 AM (PST) @ Room 517 AB #121

Convolutional neural networks (CNNs) are inherently subject to invariable filters that can only aggregate local inputs with the same topological structures. It causes that CNNs are allowed to manage data with Euclidean or grid-like structures (e.g., images), not ones with non-Euclidean or graph structures (e.g., traffic networks). To broaden the reach of CNNs, we develop structure-aware convolution to eliminate the invariance, yielding a unified mechanism of dealing with both Euclidean and non-Euclidean structured data. Technically, filters in the structure-aware convolution are generalized to univariate functions, which are capable of aggregating local inputs with diverse topological structures. Since infinite parameters are required to determine a univariate function, we parameterize these filters with numbered learnable parameters in the context of the function approximation theory. By replacing the classical convolution in CNNs with the structure-aware convolution, Structure-Aware Convolutional Neural Networks (SACNNs) are readily established. Extensive experiments on eleven datasets strongly evidence that SACNNs outperform current models on various machine learning tasks, including image classification and clustering, text categorization, skeleton-based action recognition, molecular activity detection, and taxi flow prediction.

Author Information

Jianlong Chang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)
Jie Gu (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences)
Lingfeng Wang (Institute of Automation, Chinese Academy of Sciences)
GAOFENG MENG (Institute of Automation, Chinese Academy of Sciences)
SHIMING XIANG (Chinese Academy of Sciences, China)
Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)

More from the Same Authors