Attention augmented differentiable forest for tabular data
This work addresses the need for efficient and accurate models for tabular data, offering a memory-efficient alternative to gradient boosted decision trees, though it appears incremental as it builds on existing differentiable forest frameworks.
The authors tackled the problem of improving differentiable forests for tabular data by introducing a tree attention block to learn tree importance and adjust weights, resulting in comparable or higher accuracy than state-of-the-art gradient boosted decision trees on some datasets and lower memory usage on larger datasets.
Differentiable forest is an ensemble of decision trees with full differentiability. Its simple tree structure is easy to use and explain. With full differentiability, it would be trained in the end-to-end learning framework with gradient-based optimization method. In this paper, we propose tree attention block(TAB) in the framework of differentiable forest. TAB block has two operations, squeeze and regulate. The squeeze operation would extract the characteristic of each tree. The regulate operation would learn nonlinear relations between these trees. So TAB block would learn the importance of each tree and adjust its weight to improve accuracy. Our experiment on large tabular dataset shows attention augmented differentiable forest would get comparable accuracy with gradient boosted decision trees(GBDT), which is the state-of-the-art algorithm for tabular datasets. And on some datasets, our model has higher accuracy than best GBDT libs (LightGBM, Catboost, and XGBoost). Differentiable forest model supports batch training and batch size is much smaller than the size of training set. So on larger data sets, its memory usage is much lower than GBDT model. The source codes are available at https://github.com/closest-git/QuantumForest.