进化神经架构搜索的图形嵌入比较器用同态多比较搜索
Xiaolei Zhang1, Yu Xue1, Ferrante Neri2,3
1School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, P. R. China.
International journal of neural systems
|January 25, 2026
概括
本研究介绍了图形嵌入比较器与同态多比较 (GEC-IMC),这是一个新的神经架构搜索 (NAS) 框架. GEC-IMC通过从图形结构学习架构表示来增强深度学习模型设计,以实现更强大,更有效的性能预测.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 深度学习 (Deep Learning) 是一种深度学习.
- 计算机科学 计算机科学
背景情况:
- 设计有效的神经网络架构是深度学习的一个关键挑战.
- 自动神经架构搜索 (NAS) 方法通常依赖于不充分的描述符或预测符,限制它们捕捉网络复杂性的能力并提供可靠的指导.
- 现有的NAS方法难以应对候选网络的结构复杂性,导致最佳搜索结果不足.
研究的目的:
- 介绍一个新的进化NAS框架,图形嵌入比较器与同态多比较 (GEC-IMC).
- 开发一种方法,直接从它们的图形结构中学习架构表示.
- 通过提高性能预测准确度来提高NAS的稳定性和效率.
主要方法:
- 利用图形卷积网络将神经架构编码为嵌入式.
- 采用对比式学习策略,在嵌入空间中更靠近地绘制具有类似准确性的架构.
- 开发了一个用于精确对对性能估计的比较器,并纳入了一个异形多比较机制,用于强大的排名.
主要成果:
- 在标准NAS基准指标上,GEC-IMC实现了最先进的性能.
- 与现有的业绩预测指标相比,该框架表现出了更好的稳定性.
- 废除研究证实了嵌入学习和多重比较在提高搜索效率方面的有效性.
结论:
- 通过利用图形结构表示,GEC-IMC为NAS提供了更有效的方法.
- 学习嵌入和多重比较的组合显著提高了搜索的稳定性和效率.
- 这一框架在自动化复杂神经架构设计方面取得了重大进展.
相关概念视频
02:54Evolutionary Relationships through Genome Comparisons
6.9K
Genome comparison is one of the excellent ways to interpret the evolutionary relationships between organisms. The basic principle of genome comparison is that if two species share a common feature, it is likely encoded by the DNA sequence conserved between both species. The advent of genome sequencing technologies in the late 20th century enabled scientists to understand the concept of conservation of domains between species and helped them to deduce evolutionary relationships across diverse...
6.9K
02:35What is Evolutionary History?
43.0K
Scientists record evolutionary history by analyzing fossil, morphological, and genetic data. The fossil record documents the history of life on Earth and provides evidence for evolution. However, both fossil and living organisms offer evidence that outlines Earth’s evolutionary history.
43.0K
02:57The Sense of Self: Reflected Self-Appraisal and Social Comparison
55.6K
According to Charles Cooley, we base our image on what we think other people see (Cooley 1902). We imagine how we must appear to others, then react to this speculation. We don certain clothes, prepare our hair in a particular manner, wear makeup, use cologne, and the like—all with the notion that our presentation of ourselves is going to affect how others perceive us. We expect a certain reaction, and, if lucky, we get the one we desire and feel good about it. But more than that, Cooley...
55.6K
01:20Evolutionary Psychology
976
Evolutionary psychology explores the origins of human behavior and mental processes by framing them within the context of natural selection, a theory famously propounded by Charles Darwin. This field asserts that many behaviors common across human societies — ranging from instinctive fear reactions to complex social interactions — arose as evolutionary adaptations. These adaptations enhanced the survival and reproductive success of our ancestors, thereby becoming embedded in the...
976
01:07Ogive Graph
6.7K
An ogive graph is sometimes called a cumulative frequency polygon. It is one type of frequency polygon that shows cumulative frequency. In other words, the cumulative percentages are added to the graph from left to right. An ogive graph plots cumulative frequency on the vertical y-axis and class boundaries along the horizontal x-axis. It’s very similar to a histogram; only instead of rectangles, an ogive displays a single point where the top right of the rectangle would be. Creating this...
6.7K
01:30Graphing Antiderivatives
52
The concept of an antiderivative is fundamental in calculus, describing how a function's values accumulate over time. This process is closely related to physical motion, such as the movement of a rolling ball. As the ball progresses, its position changes in response to variations in velocity, just as an antiderivative graph reflects the cumulative effect of the original function's values.Graphing an antiderivative requires interpreting how a function's values influence the shape of its...
52