重新审视以AUC为导向的对抗性训练与损失不可知障碍
IEEE transactions on pattern analysis and machine intelligence
|August 10, 2023
概括
这项研究增强了ROC曲线下的区域 (AUC) 分类的对抗性训练. 它引入了一种与现有方法兼容的新算法,确保长尾数据集的稳定性和概括性.
科学领域:
- 机器学习 机器学习
- 计算机视觉 计算机视觉
背景情况:
- 在ROC曲线下的面积 (AUC) 对于长尾鱼的分类至关重要.
- 现有的AUC优化方法缺乏对抗攻击的稳定性.
- AdAUC提供以AUC为导向的对抗性培训,但在实际应用方面存在局限性.
研究的目的:
- 开发一种更实用,更强大的以AUC为导向的对抗性训练方法.
- 解决 AdAUC.中全球扰动生成的局限性.
- 为AUC对抗训练的概括能力提供理论上的保证.
主要方法:
- 重构了最初的AUC对抗性训练目标函数.
- 提出了一种诱导算法,与基于得分和基于实例智能损失的扰动兼容.
- 开发了一个基于SVRG的快速梯度下降-上升算法来加速.
主要成果:
- 在温和条件下证明了AdAUC和分数/实例智能扰动之间的等价性.
- 建立了一个明确的错误,限制了以AUC为导向的对抗性训练,确保了通用化.
- 通过广泛的实验,在五个长尾数据集上实现了强大的性能和稳定性.
结论:
- 拟议的方法提高了AUC对抗训练的兼容性和稳定性.
- 建立了概括的理论保障.
- 该算法为长尾分类任务的性能和稳定性提供了显著的改进.
更多相关视频
03:14Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
Published on: December 6, 2024
622
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
287
相关概念视频
Avoidance Learning and Learned Helplessness
1.8K
Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
1.8K
Generalization, Discrimination, and Extinction
613
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
613
Associative Learning
444
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...
444
Survival Tree
110
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
110
Observational Learning
210
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...
210
Operant Conditioning Intervention
81
Operant conditioning serves as a foundational principle in therapeutic interventions aimed at modifying maladaptive behaviors. Central to this approach is the notion that behaviors, both adaptive and maladaptive, are learned through reinforcement. By analyzing the environmental factors that reinforce problematic behaviors, clinicians can design interventions to weaken these reinforcements and replace maladaptive behaviors with healthier alternatives.
In operant conditioning, behaviors that are...
In operant conditioning, behaviors that are...
81
