Interpretable Pattern

Interpretable pattern discovery aims to identify meaningful and understandable structures within complex data, facilitating both scientific understanding and practical applications. Current research focuses on developing algorithms and models, such as pattern exploiting training (PET), symbolic pattern forests, and tensor decomposition, to uncover these patterns in diverse data types including time series, graphs, and sequential data. This work is crucial for improving the transparency and trustworthiness of machine learning models, enabling better decision-making in fields ranging from healthcare to social media analysis. The ultimate goal is to move beyond "black box" models, providing human-interpretable insights into the underlying data generating processes.