关于解释图形神经网络的必要性和充分性的概率:一个下限优化方法
Ruichu Cai1, Yuxuan Zhu2, Xuexin Chen2
1School of Computer Science, Guangdong University of Technology, Guangzhou 510006, China; Peng Cheng Laboratory, Shenzhen 518066, China.
本研究引入了解释图形神经网络 (GNN) 的新框架,确保解释既必要又足够. 拟议的方法优化了必要性和充分性的概率 (PNS) 的下界,以获得更可靠的GNN解释性.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 图形神经网络的神经网络
背景情况:
- 图形神经网络 (GNN) 的解释性至关重要,但具有挑战性.
- 现有的方法往往侧重于必要性或充分性,而不是同时进行两者.
- 必要性和充分性的概率 (PNS) 提供了一个理论的理想,但很难计算.
研究的目的:
- 制定一个框架,为GNN提供必要和充分的解释.
- 解决与计算PNS相关的计算挑战.
- 提高GNN模型解释的可靠性和可信度.
主要方法:
- 提出了GNN (NSEG) 框架的必要和充分解释.
- 将GNN建模为结构因果模型 (SCM),以估计反事实概率.
- 优化了使用连续面具和采样策略来实现可扩展性的PNS下界.
主要成果:
- NSEG框架始终产生了既必要又足够的解释.
- 经验结果表明,NSEG的表现优于现有的最先进的GNN解释方法.
- 该方法提高了获得必要和充分解释的可扩展性.
结论:
- 该NSEG框架为实现真正可解释的GNNs提供了一个强大的解决方案.
- 通过优化PNS的下界,该框架克服了以前的计算障碍.
- 这项工作推进了复杂的基于图形的模型的可解释AI领域.
更多相关视频
11:18Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
10:44Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Reducing Line Loss
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
Routh-Hurwitz Criterion I
To apply the Routh-Hurwitz criterion, a Routh table is constructed. The table's rows are labeled with powers of the complex frequency variable s, starting from the...
Probability in Statistics
An example of a simple event is a coin toss. The result of a coin toss is either a head or a tail. Here, head and tail are two simple events. These two simple events make up the sample space. Further, the probability of an event occurring falls within the range of 0 to 1. The probability of an...
Expected Frequencies in Goodness-of-Fit Tests
Accuracy, limits, and approximation
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
