深度神经网络的归因解释:一个理论视角
IEEE transactions on pattern analysis and machine intelligence
|February 24, 2026
概括
本调查回顾了对深度神经网络 (DNN) 归因解释的进展,重点关注理论框架,以确保方法忠实地反映了DNN逻辑. 它解决了统一,推理和评估的挑战,以实现可靠的AI解释.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 可解释的人工智能 (XAI)
背景情况:
- 归因解释方法旨在量化输入变量对深度神经网络 (DNN) 预测的贡献.
- 一个根本的挑战是缺乏忠诚,质疑这些方法是否真正反映了DNN决策逻辑.
研究的目的:
- 提供对DNN的归因方法最近的理论进步进行全面的审查.
- 解决归因方法理论统一,合理性和原则性评估的核心挑战.
主要方法:
- 审查有关归因方法的理论研究.
- 专注于三个方向:理论统一,理论理由和理论评估.
- 分析共同点,差异,数学理由和忠诚原则.
主要成果:
- 确定了理论上统一的归因方法的关键进展.
- 澄清了现有方法的数学和概念上的理由.
- 建立了评估归因忠实性的原则方法.
结论:
- 理论研究对于理解和改进归因方法至关重要.
- 提供了基于理论发现的方法设计,选择和使用的实际建议.
- 在归因解释中讨论了开放的问题和未来的研究方向.
相关概念视频
Attribution
340
In social interactions, individuals frequently seek to understand the motivations and causes behind others' behaviors. This fundamental aspect of social perception, known as attribution, plays a crucial role in shaping interpersonal relationships and guiding future actions. Attribution refers to the cognitive process through which people infer the reasons behind others' behaviors, allowing them to assess character traits, intentions, and situational influences.Attribution Theory and Its...
340
Fundamental Attribution Error
13.9K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
13.9K
Theory of Attribution I: Correspondent Inference Theory
663
Correspondent inference theory, proposed by Jones and Davis in 1965, seeks to explain how individuals infer stable personality traits from observed behaviors. It suggests that people attribute actions to underlying dispositions rather than external circumstances, particularly when the behavior appears intentional and socially significant.Voluntary Behavior and Dispositional AttributionAccording to this theory, individuals are more likely to attribute behavior to personal traits when it appears...
663
Theory of Attribution II: Kelley's Covariation Theory
743
Attribution theory plays a crucial role in social psychology, helping to explain how individuals interpret the causes of behavior. One prominent model within this field is Harold Kelley's covariation theory, which provides a systematic approach to determining whether internal traits or external circumstances drive a person's actions. The model posits that individuals rely on three key types of information—consensus, consistency, and distinctiveness—to make these judgments.Consensus:...
743
Attribution Theory
13.9K
Behavior is a product of both the situation (e.g., cultural influences, social roles, and the presence of bystanders) and of the person (e.g., personality characteristics). Subfields of psychology tend to focus on one influence or behavior over others. Situationism is the view that our behavior and actions are determined by our immediate environment and surroundings. In contrast, dispositionism holds that our behavior is determined by internal factors (Heider, 1958).
13.9K
Actor-Observer Effect
439
The actor-observer effect, a cognitive bias closely linked to the fundamental attribution error, refers to the tendency for individuals to attribute their behavior to external, situational factors while explaining others’ behavior in terms of internal, dispositional traits. This asymmetry in attribution significantly influences social perception and judgment.Cognitive Mechanisms Behind the EffectTwo primary psychological mechanisms contribute to the actor-observer effect: differences in...
439


