# Learnable Heterogeneous Convolution: Learning both topology and strength

Source: [Learnable Heterogeneous Convolution: Learning both topology and strength](<https://www.sota2.com/research/paper/68fa6e591e209131cea3f42b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:56.866Z

Authors: Rongzhen Zhao, Zhenzhi Wu, Qikun Zhang

Published: 2023-01-13T08:48:12.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.05440>)

[PDF](<https://arxiv.org/pdf/2301.05440.pdf>)