Learnable Heterogeneous Convolution: Learning both topology and strength

2023-01-13 · Rongzhen Zhao, Zhenzhi Wu, Qikun Zhang

Existing convolution techniques in artificial neural networks suffer from huge computation complexity, while the biological neural network works in a much more powerful yet efficient way. Inspired by the biological plasticity of dendritic topology and synaptic strength, our method, Learnable Heterogeneous Convolution, realizes joint learning of kernel shape and weights, which unifies existing handcrafted convolution techniques in a data-driven way. A model based on our method can converge with structural sparse weights and then be accelerated by devices of high parallelism. In the experiments, our method either reduces VGG16/19 and ResNet34/50 computation by nearly 5x on CIFAR10 and 2x on ImageNet without harming the performance, where the weights are compressed by 10x and 4x respectively; or improves the accuracy by up to 1.0% on CIFAR10 and 0.5% on ImageNet with slightly higher efficiency. The code will be available on www.github.com/Genera1Z/LearnableHeterogeneousConvolution.

📄 PDF Abstract BibTeX arXiv:2301.05440

Code (1)

genera1z/learnableheterogeneousconvolution 공식 구현 tf

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Robust Spatial Filtering with Graph Convolutional Neural Networks

2017-03-02 · Felipe Petroski Such, Shagan Sah, Miguel Dominguez, Suhas Pillai 외

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 contrib…

General Classification

BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks

2020-10-23 · Di Jin, Xiangchen Song, Zhizhi Yu, Ziyang Liu 외

Graph convolutional networks (GCNs), aiming to integrate high-order neighborhood information through stacked graph convolution layers, have demonstrated remarkable power in many network analysis tasks. However, topologic…

Topology Adaptive Graph Convolutional Networks

2017-10-28 · ICLR 2018 1 · Jian Du, Shanghang Zhang, Guanhang Wu, Jose M. F. Moura 외

Spectral graph convolutional neural networks (CNNs) require approximation to the convolution to alleviate the computational complexity, resulting in performance loss. This paper proposes the topology adaptive graph convo…

Leap: Inductive Link Prediction via Learnable TopologyAugmentation

2025-03-05 · Ahmed E. Samy, Zekarias T. Kefato, Sarunas Girdzijauskas

Link prediction is a crucial task in many downstream applications of graph machine learning. To this end, Graph Neural Network (GNN) is a widely used technique for link prediction, mainly in transductive settings, where …

Graph Neural Network Inductive Bias Inductive Link Prediction Link Prediction+1

Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning

2022-11-16 · Zhaoliang Chen, Lele Fu, Jie Yao, Wenzhong Guo 외

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning d…

MULTI-VIEW LEARNING