SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.12986 · 2022

Extracting Effective Subnetworks with Gumbel-Softmax

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large and performant neural networks are often overparameterized and can be drastically reduced in size and complexity thanks to pruning. Pruning is a group of methods, which seeks to remove redundant or unnecessary weights or groups of weights in a network. These techniques allow the creation of lightweight networks, which are particularly critical in embedded or mobile applications. In this paper, we devise an alternative pruning method that allows extracting effective subnetworks from larger untrained ones. Our method is stochastic and extracts subnetworks by exploring different topologies which are sampled using Gumbel Softmax. The latter is also used to train probability distributions which measure the relevance of weights in the sampled topologies. The resulting subnetworks are further enhanced using a highly efficient rescaling mechanism that reduces training time and improves performance. Extensive experiments conducted on CIFAR show the outperformance of our subnetwork extraction method against the related work.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2202.12986")
get_code_for_paper("2202.12986")
have("2202.12986")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2202.12986.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2202.12986.svg)](https://syntology.ai/paper/2202.12986)

Connect an agent — have() is free.