Tensor Polynomial Additive Model

TL;DR

The paper introduces the Tensor Polynomial Additive Model (TPAM), which preserves data structure in high-order inputs, improves accuracy and compression, and maintains interpretability for transparent machine learning.

Contribution

It proposes a novel tensor-based additive model that captures complex feature interactions with fewer parameters while retaining interpretability.

Findings

Enhances accuracy by up to 30% on various datasets.

Achieves up to 5x data compression.

Maintains interpretability of high-order features.

Abstract

Additive models can be used for interpretable machine learning for their clarity and simplicity. However, In the classical models for high-order data, the vectorization operation disrupts the data structure, which may lead to degenerated accuracy and increased computational complexity. To deal with these problems, we propose the tensor polynomial addition model (TPAM). It retains the multidimensional structure information of high-order inputs with tensor representation. The model parameter compression is achieved using a hierarchical and low-order symmetric tensor approximation. In this way, complex high-order feature interactions can be captured with fewer parameters. Moreover, The TPAM preserves the inherent interpretability of additive models, facilitating transparent decision-making and the extraction of meaningful feature values. Additionally, leveraging TPAM's transparency and ability to handle higher-order features, it is used as a post-processing module for other interpretation models by introducing two variants for class activation maps. Experimental results on a series of datasets demonstrate that TPAM can enhance accuracy by up to 30\%, and compression rate by up to 5 times, while maintaining a good interpretability.