Interpretation of multi-label classification models using shapley values
This provides interpretability for multi-label classification, which is incremental as it applies an existing method to a new task.
The paper tackled the problem of interpreting multi-label classification models by extending SHAP methodology to this task, demonstrating its usefulness through comprehensive comparisons on well-known datasets.
Multi-label classification is a type of classification task, it is used when there are two or more classes, and the data point we want to predict may belong to none of the classes or all of them at the same time. In the real world, many applications are actually multi-label involved, including information retrieval, multimedia content annotation, web mining, and so on. A game theory-based framework known as SHapley Additive exPlanations (SHAP) has been applied to explain various supervised learning models without being aware of the exact model. Herein, this work further extends the explanation of multi-label classification task by using the SHAP methodology. The experiment demonstrates a comprehensive comparision of different algorithms on well known multi-label datasets and shows the usefulness of the interpretation.