Unifying Perplexing Behaviors in Modified BP Attributions through Alignment Perspective
원문 초록
Attributions aim to identify input pixels that are relevant to the decision-making process. A popular approach involves using modified backpropagation (BP) rules to reverse decisions, which improves interpretability compared to the original gradients. However, these methods lack a solid theoretical foundation and exhibit perplexing behaviors, such as reduced sensitivity to parameter randomization, raising concerns about their reliability and highlighting the need for theoretical justification. In this work, we present a unified theoretical framework for methods like GBP, RectGrad, LRP, and DTD, demonstrating that they achieve input alignment by combining the weights of activated neurons. This alignment improves the visualization quality and reduces sensitivity to weight randomization. Our contributions include: (1) Providing a unified explanation for multiple behaviors, rather than focusing on just one. (2) Accurately predicting novel behaviors. (3) Offering insights into decision-making processes, including layer-wise information changes and the relationship between attributions and model decisions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Graph-Structured Data Analysis of Component Failure in Autonomous Cargo Ships Based on Feature Fusion
Guiding LLM Decision-Making with Fairness Reward Models
Generative Latent Kernel Modeling for Blind Motion Deblurring
InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior
VERITAS: Verification and Explanation of Realness in Images for Transparency in AI Systems
Enhancing LLM Agent Safety via Causal Influence Prompting
토론
이 논문과 연결된 포럼 글이 아직 없습니다.