大脑启发的混沌图反向传播用于组合优化
IEEE transactions on neural networks and learning systems
|January 12, 2026
概括
本研究介绍了混乱图反向传播 (CGBP),这是一种用于图形神经网络 (GNN) 的新型训练算法. 通过避免局部最小值,CGBP增强了用于组合优化问题 (COP) 的GNN,通过避免局部最小值,优于现有方法.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 计算科学 计算科学
背景情况:
- 图形神经网络 (GNN) 为组合优化问题 (COP) 提供高效的近似解决方案.
- 目前在GNN中的反向传播方法经常陷入局部最小值,限制了优化性能.
- 现有的方法在解决大规模的COP时难以与最先进的技术 (SOTA) 相匹配.
研究的目的:
- 为GNN开发一种新的训练算法,克服传统反向传播的局限性.
- 为了提高GNN的优化性能,用于解决复杂的组合优化问题.
- 引入一种受混乱动态启发的培训方法,以增强GNN学习.
主要方法:
- 介绍了混乱图反向传播 (CGBP),这是GNN的新训练算法.
- 在GNN训练过程中整合了局部损失函数,以诱导混乱的动态.
- 利用混乱动态的全球ergodicity和伪随机性进行有效的GNN学习.
主要成果:
- CGBP展示了解决COP的GNN的高效和全球学习.
- 将CGBP应用于最大独立集 (MIS),最大切割 (MC) 和图形色调 (GC) 问题.
- 在大型基准数据集上,与SOTA方法相比,实现了竞争性或优异的性能.
结论:
- CGBP有效地解决了GNN培训COP的本地最小问题.
- 在CGBP的混乱动态使高效和全球优化.
- CGBP作为一个通用插件模块,可以增强现有的学习方法,以提高搜索和性能.
相关概念视频
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
282
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
282
Sequence Networks of Rotating Machines
481
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
481
Combinatorial Gene Control
9.5K
Combinatorial gene control is the synergistic action of several transcriptional factors to regulate the expression of a single gene. The absence of one or more of these factors may lead to a significant difference in the level of gene expression or repression.
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
9.5K
Woodward–Hoffmann Selection Rules and Microscopic Reversibility
3.8K
Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...
3.8K
Ampere-Maxwell's Law: Problem-Solving
1.1K
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of the...
1.1K
Randomized Experiments
8.8K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...
8.8K

