Skip to content
Back to skills

Your Network May Need To Be Rewritten Network Adversarial Based On Highdimensional Function Graph Decomposition

ASecurity

**arXiv ID:** 2405.03712 **Authors:** Xiaoyan Su, Yinghao Zhu, Run Li **Published:** 2024-05-04T11:22:30Z **Abstract:** In the past, research on a single low dimensional activation function in networks has led to internal covariate shift and gradient deviation problems. A relatively small research area is how to use function combinations to provide property completion for a single activation function application. We propose a network adversarial method to address the aforementioned challenges...

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 11, 2026
tools

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill your-network-may-need-to-be-rewritten-network-adversarial-based-on-highdimensional-function-graph-decomposition --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Your Network May Need To Be Rewritten Network Adversarial Based On Highdimensional Function Graph Decomposition?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Your Network May Need To Be Rewritten Network Adversarial Based On Highdimensional Function Graph Decomposition
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-your-network-may-need-to-be-rewritten-network-adve/badge)](https://www.skillsdirectory.com/skills/hiyenwong-your-network-may-need-to-be-rewritten-network-adve)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Your Network May Need to Be Rewritten: Network Adversarial Based on High-Dimensional Function Graph Decomposition

**arXiv ID:** 2405.03712
**Authors:** Xiaoyan Su, Yinghao Zhu, Run Li
**Published:** 2024-05-04T11:22:30Z
**Abstract:**
In the past, research on a single low dimensional activation function in networks has led to internal covariate shift and gradient deviation problems. A relatively small research area is how to use function combinations to provide property completion for a single activation function application. We propose a network adversarial method to address the aforementioned challenges. This is the first method to use different activation functions in a network. Based on the existing activation functions in the current network, an adversarial function with opposite derivative image properties is constructed, and the two are alternately used as activation functions for different network layers. For complex situations, we propose a method of high-dimensional function graph decomposition(HD-FGD), which divides it into different parts and then passes through a linear layer. After integrating the inverse of the partial derivatives of each decomposed term, we obtain its adversarial function by referring to the computational rules of the decomposition process. The use of network adversarial methods or the use of HD-FGD alone can effectively replace the traditional MLP+activation function mode. Through the above methods, we have achieved a substantial improvement over standard activation functions regarding both training efficiency and predictive accuracy. The article addresses the adversarial issues associated with several prevalent activation functions, presenting alternatives that can be seamlessly integrated into existing models without any adverse effects. We will release the code as open source after the conference review process is completed.

## Skill Description

This skill is generated from the arXiv paper: Your Network May Need to Be Rewritten: Network Adversarial Based on High-Dimensional Function Graph Decomposition (2405.03712).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2405.03712](http://arxiv.org/abs/2405.03712v1)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.