FingerLiu

# How(理论)

• 使用有自解释性的模型(WB)
• 基于模型不可知论的黑盒探测(BB)
• 深度学习/神经网络模型的可解释性

• 线性回归模型
• 逻辑回归
• 决策树

## 黑盒探测

• Partial Dependence Plot (PDP)
• Global Surrogate
• Local Surrogate Model-Agnostic Method(LIME)
• Anchors(If-Then-That)
• Shapley Values
• SHAP

### PDP

``````A partial dependence plot can show whether the relationship between the target and a feature is linear, monotonic or more complex.

Disadvantages:The assumption of independence is the biggest issue with PD plots.
``````

### Global Surrogate

``````A global surrogate model is an interpretable model that is trained to approximate the predictions of a black box model.

Advantages: flexible.Any interpretable models can be used.
Disadvantages:You have to be aware that you draw conclusions about the model and not about the data, since the surrogate model never sees the real outcome.
``````

### Local Surrogate Model-Agnostic Method(LIME)

``````Local surrogate models are interpretable models that are used to explain individual predictions of black box machine learning models.

Advantages: They make human-friendly explanations.LIME is one of the few methods that works for tabular data, text and images.
Disadvantages: The correct definition of the neighborhood differs./instability.
``````

### Anchor

``````A rule anchors a prediction if changes in other feature values do not affect the prediction.
Anchors utilizes reinforcement learning techniques in combination with a graph search algorithm to reduce the number of model calls (and hence the required runtime) to a minimum while still being able to recover from local optima.

Anchors are subsettable(shown as example).
Works for non-linear or complex in an instance’s neighborhood(reinforcement learning).
Can be parallelized.

many scenarios require discretization.
many calls to the ML model.
``````

### explore timeline

PDP(2001) --> LIME(2016) --> Anchors(2018)
Shapley Values(2014) --> SHAP(2016)

## 深度学习/神经网络模型

• Feature Visualization
• Network dissection

# When to use

• Your model makes significant impact.
• When the problem is not well studied, or explore in a very new area.

# In Action(实战)

python: sklearn、keras、alibi

R: iml

seldon 是一个模型生命周期管理的系统，有点类似于我们的 PAS 加一部分 DAG 的功能，他们基于上述 LIME 和 Anchor 等实现了一套模型解释和异常检测的框架并开源了，我们可以借鉴、探索下。

https://github.com/SeldonIO/a...

https://github.com/SeldonIO/a...

562 声望
28 粉丝
0 条评论