强大的分布式学习对抗分布式转移和拜占庭式攻击
IEEE transactions on neural networks and learning systems
|August 23, 2024
概括
这项研究引入了分布式学习的新算法,增强了对数据分布转移和拜占庭式攻击的模型稳定性. 这项研究揭示了基于规范的选 (NBS) 算法在1/3的拜占庭节点的关键融合断点.
科学领域:
- 分布式学习系统 分布式学习系统
- 机器学习的稳定性 机器学习的稳定性
- 优化理论 优化理论
背景情况:
- 分布式学习面临来自分布式转移的威胁,导致样本之外的表现不佳.
- 对工作节点的拜占庭式攻击可以使分布式学习结果无效.
- 解决分布变化和拜占庭袭击同时提出了重大挑战.
研究的目的:
- 提出一个新的研究方向,共同解决分布式转移和分布式学习中的拜占庭式攻击.
- 设计一种新的算法,既能提供分布稳定性,又能提供拜占庭式稳定性.
- 分析拟议算法的收性质和稳定性.
主要方法:
- 该研究将分布稳定优化 (DRO) 与基于规范的选 (NBS) 结合在一起,这是一个强大的聚合方案.
- 对于非凸,凸和强烈凸的学习模型,提供了收证明.
- 理论分析调查了NBS在拜占庭节点百分比方面的局限性.
主要成果:
- 开发了一种新的算法,在分布式学习中实现了分布式和拜占庭式的稳定性.
- 对各种模型类型分析了对汇聚行为和对拜占庭袭击的耐用性.
- 证明了基于NBS的算法,包括提出的算法,当拜占庭节点构成总节点的1/3或更多时,无法融合,这与1/2的常见信念相反.
结论:
- 拟议的算法有效地解决了分布式学习中的分布式转移和拜占庭式攻击.
- 这些发现澄清了NBS算法的趋同断点,建立了新的理论理解.
- 这项工作是第一个同时解决分布式转移和分布式学习系统中拜占庭式攻击的问题.
更多相关视频
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
7.5K
05:48Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
1.4K
相关概念视频
Distribution Reliability and Automation
107
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
107
Associative Learning
318
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
318
Observational Learning
154
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
154
Secondary Distribution
82
Secondary distribution systems provide electrical energy at the utilization voltage levels from distribution transformers to customer meters. Typical secondary voltages in the United States include 120/240 V for residential use, 208Y/120 V for residential and commercial use, and 480Y/277 V for industrial and high-rise commercial use.
In residential areas, 120/240 V single-phase, three-wire service is commonly used for lighting, outlets, and large appliances. Urban areas with high-density loads...
In residential areas, 120/240 V single-phase, three-wire service is commonly used for lighting, outlets, and large appliances. Urban areas with high-density loads...
82
Distribution and Dispersion
21.6K
To understand intra-specific interactions in populations, scientists measure the spatial arrangement of species individuals. This geographic arrangement is known as the species distribution or dispersion. Highly territorial species exhibit a uniform distribution pattern, in which individuals are spaced at relatively equal distances from one another. Species that are highly tied to particular resources, such as food or shelter, tend to concentrate around those resources, and thus exhibit a...
21.6K
Probability Distributions
6.8K
The probability of a random variable x is the likelihood of its occurrence. A probability distribution represents the probabilities of a random variable using a formula, graph, or table. There are two types of probability distribution– discrete probability distribution and continuous probability distribution.
A discrete probability distribution is a probability distribution of discrete random variables. It can be categorized into binomial probability distribution and Poisson...
A discrete probability distribution is a probability distribution of discrete random variables. It can be categorized into binomial probability distribution and Poisson...
6.8K
