This repository curates a comprehensive collection of research papers focusing on decision, classification, and regression trees. It aims to provide researchers and practitioners with a centralized resource for advancements in tree-based learning methods. The papers cover various aspects, including new algorithms, theoretical analyses, and practical applications, often accompanied by code implementations. The repository includes papers from leading conferences such as AAAI, ICML, and ICLR, alongside other prominent academic venues.
The collection highlights recent advancements in areas like explainable AI, fairness, and robustness of decision trees. Many papers focus on improving the efficiency and scalability of tree-based models, addressing limitations such as computational complexity and handling large datasets. The repository includes work on novel algorithms for handling missing values, adversarial examples, and frequentist approaches to feature selection, demonstrating a deep exploration of relevant challenges and solutions.
- Algorithms: Explores novel decision tree algorithms, including modifications for handling specific data types, incorporating external knowledge, and improving performance on various tasks.- Explainability: Presents techniques for making decision tree models more understandable and transparent, offering insights into model behavior and decision-making processes.- Robustness: Investigates methods to enhance the robustness of decision trees against noise, outliers, and adversarial attacks.- Scalability: Focuses on addressing the scalability challenges of decision tree algorithms, enabling their application to large datasets.- Applications: Covers various applications of decision trees in fields like medical diagnosis, finance, and natural language processing.
The repository is actively maintained with new papers added regularly. The majority of the papers are from recent years (2021-2022), indicating ongoing research activity in the field. The inclusion of code links for many papers suggests a focus on reproducibility and practical implementation.
This repository is a valuable resource for anyone interested in the latest research in decision, classification, and regression trees. It benefits researchers looking for inspiration, practitioners seeking new techniques, and students exploring machine learning algorithms. The curated collection streamlines research efforts by providing access to a wide range of impactful papers, all focused on advancing the field of tree-based modeling.