PALM: Machine Learning Explanations For Iterative Debugging
PALM: Machine Learning Explanations For Iterative Debugging
复制标题
PALM：迭代调试的机器学习解释
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Eugene Wu
中科院分区：
文献类型：
--
作者：
S. Krishnan;Eugene Wu
当深度神经网络做出错误预测时，开发人员可能很难理解原因。虽然在预测特征方面有许多可解释性的模型，但分离出对预测有最大影响的一小部分训练示例可能更自然。然而，通常的情况是，每个训练样本都以某种方式对预测做出贡献，但责任程度各不相同。我们提出了分区感知本地模型(Partition Aware Local Model，Palm)，它是一个学习和总结这种责任结构的工具，以帮助机器学习调试。Palm使用两部分代理模型来逼近复杂模型(例如，深度神经网络)：分割训练数据的元模型和逼近每个分割内的模式的一组子模型。这些子模型可以任意复杂，以捕捉复杂的局部模式。然而，元模型被约束为决策树。这样，用户可以检查元模型的结构，确定规则是否与直觉匹配，并将有问题的测试实例有效地链接到负责任的训练数据。对Palm的查询比最近邻查询识别相关数据的速度快近30倍，这是交互式应用程序的关键特性。
When a Deep Neural Network makes a misprediction, it can be challenging for a developer to understand why. While there are many models for interpretability in terms of predictive features, it may be more natural to isolate a small set of training examples that have the greatest influence on the prediction. However, it is often the case that every training example contributes to a prediction in some way but with varying degrees of responsibility. We present Partition Aware Local Model (PALM), which is a tool that learns and summarizes this responsibility structure to aide machine learning debugging. PALM approximates a complex model (e.g., a deep neural network) using a two-part surrogate model: a meta-model that partitions the training data, and a set of sub-models that approximate the patterns within each partition. These sub-models can be arbitrarily complex to capture intricate local patterns. However, the meta-model is constrained to be a decision tree. This way the user can examine the structure of the meta-model, determine whether the rules match intuition, and link problematic test examples to responsible training data efficiently. Queries to PALM are nearly 30x faster than nearest neighbor queries for identifying relevant data, which is a key property for interactive applications.