Causal Analysis for Robust Interpretability of Neural Networks
用因果分析增强神经网络解释的稳健性AI 解读 ↓
← 返回论文列表与筛选
阅读说明
本页整理公开书目信息，不生成学术质量评分。AI 解读根据题名及所注明的摘要或原文片段生成，未完成全文核验，可能有误；具体假设、证明与结论请核对原文。摘要保留来源文本，未经模型改写。
DOI 首次登记不等于接收或发表日期。部分更正、评论等条目没有独立摘要；缺少可靠材料时保留待补状态。
本页为预印本版本；arXiv 收录、作者填写的期刊信息以及作者既有发表经历，都不单独证明本篇已接收。作者发表记录按 OpenAlex 身份与完整姓名、本站覆盖期刊 ISSN 及正式卷期核对，只展示已核实例，档案仍可能误合并。
引用量采用 OpenAlex 单条关联记录，不合计多个记录；关联记录可能包含正式发表版本，不等于此版本单独引用。缺失不视为零，引用指标不代表论文质量。
关注作者按书目中的完整姓名匹配，同名和姓名变体需人工辨别。相关论文先按共享细分方向和具体方法排列，再参考通用方法与发表日期。
分类依据与纠错
AI 根据所提供的论文材料归类：摘要研究神经网络隐藏层的计算机制与图像分类解释，未直接涉及经济处理效应或单位间干扰，现有细分依据不足。
反馈分类问题
正在核对关联版本…
代码、数据与补充材料
正在核对对应版本的资源…
用因果分析增强神经网络解释的稳健性
- 研究问题
- 如何识别预训练神经网络内部对预测有作用的机制，减少相关性归因受噪声、虚假关联与训练偏差影响造成的不稳定？
- 方法与思路
- 作者对隐藏层实施路径干预，提取与预测相关且必要的信息，构造针对任务的因果解释图，并在图像分类模型中评估。
- 材料陈述的贡献
- 摘要称，方法较标准归因方法产生更稳定且忠实的解释，所得图还能揭示网络内部交互，为行为审查和模型修复提供线索。
- 阅读关注点
- 应核对路径干预的具体定义、必要信息的判定标准，以及解释忠实性与稳定性指标是否确实反映内部预测机制。
- 阅读边界
- 这是 arXiv 预印本，同行评审及期刊接收未经核实；摘要未给出实验数值，网络内部干预结论也不能直接解释现实世界因果关系。
原文摘要
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to individual examples. However, these measures are susceptible to noise and spurious correlations encoded in the model during the training phase (e.g., biased inputs, model overfitting, or misspecification). Moreover, this process has proven to result in noisy and unstable attributions that prevent any transparent understanding of the model's behavior. In this paper, we develop a robust interventional-based method grounded by causal analysis to capture cause-effect mechanisms in pre-trained neural networks and their relation to the prediction. Our novel approach relies on path interventions to infer the causal mechanisms within hidden layers and isolate relevant and necessary information (to model prediction), avoiding noisy ones. The result is task-specific causal explanatory graphs that can audit model behavior and express the actual causes underlying its performance. We apply our method to vision models trained on classification tasks. On image classification tasks, we provide extensive quantitative experiments to show that our approach can capture more stable and faithful explanations than standard attribution-based methods. Furthermore, the underlying causal graphs reveal the neural interactions in the model, making it a valuable tool in other applications (e.g., model repair).