DLBacktrace让任何深度学习模型决策过程可解释，无需修改模型结构。
DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
- 基于输入扰动分析，不依赖模型内部结构生成解释
- 在多种模型（如BERT、ResNet）上效果优于SHAP和GradCAM
- 支持PyTorch/TensorFlow，适合需要可信AI的科研与工业场景
人工智能的快速发展催生了更复杂的深度学习模型，这些模型常作为难以理解的“黑箱”，其决策过程缺乏透明性。这种不可解释性在高风险应用中尤为突出，影响信任与责任归属。本文强调可解释性对建立信任、确保问责与负责任部署的重要性。为此，我们提出DLBacktrace——一种全新的、与模型无关的可解释性方法，适用于多种架构（如MLP、CNN、Transformer-based LLM），涵盖BERT、ResNet、U-Net及自定义DNN。通过与SHAP、LIME、GradCAM等现有方法对比，实验表明，DLBacktrace能有效提升对模型行为的理解。该工具支持PyTorch与TensorFlow，代码已开源于https://github.com/AryaXAI/DLBacktrace。
原文摘要 · Abstract (English)
The rapid growth of AI has led to more complex deep learning models, often operating as opaque "black boxes" with limited transparency in their decision-making. This lack of interpretability poses challenges, especially in high-stakes applications where understanding model output is crucial. This work highlights the importance of interpretability in fostering trust, accountability, and responsible deployment. To address these challenges, we introduce DLBacktrace, a novel, model-agnostic technique designed to provide clear insights into deep learning model decisions across a wide range of domains and architectures, including MLPs, CNNs, and Transformer-based LLM models. We present a comprehensive overview of DLBacktrace and benchmark its performance against established interpretability methods such as SHAP, LIME, and GradCAM. Our results demonstrate that DLBacktrace effectively enhances understanding of model behavior across diverse tasks. DLBacktrace is compatible with models developed in both PyTorch and TensorFlow, supporting architectures such as BERT, ResNet, U-Net, and custom DNNs for tabular data. The library is open-sourced and available at https://github.com/AryaXAI/DLBacktrace .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。