Diffusion Boosted Trees
This work addresses supervised learning problems, particularly for tabular data applications like fraud detection, though it appears incremental as it hybridizes existing methods.
The paper tackled supervised learning by introducing Diffusion Boosted Trees (DBT), combining denoising diffusion models and gradient boosting to model conditional distributions without parametric assumptions, and demonstrated its advantages over deep neural network-based diffusion models and competence in real-world regression and fraud detection tasks.
Combining the merits of both denoising diffusion probabilistic models and gradient boosting, the diffusion boosting paradigm is introduced for tackling supervised learning problems. We develop Diffusion Boosted Trees (DBT), which can be viewed as both a new denoising diffusion generative model parameterized by decision trees (one single tree for each diffusion timestep), and a new boosting algorithm that combines the weak learners into a strong learner of conditional distributions without making explicit parametric assumptions on their density forms. We demonstrate through experiments the advantages of DBT over deep neural network-based diffusion models as well as the competence of DBT on real-world regression tasks, and present a business application (fraud detection) of DBT for classification on tabular data with the ability of learning to defer.