General Transform: A Unified Framework for Adaptive Transform to Enhance Representations

TL;DR

This paper introduces General Transform (GT), an adaptive, data-driven transform framework that learns optimal representations for machine learning tasks, outperforming traditional fixed transforms in vision and NLP applications.

Contribution

The paper proposes a novel adaptive transform framework that automatically learns suitable data representations, reducing reliance on prior domain knowledge.

Findings

GT outperforms conventional transforms in vision tasks

GT improves NLP task performance

Models with GT achieve higher accuracy

Abstract

Discrete transforms, such as the discrete Fourier transform, are widely used in machine learning to improve model performance by extracting meaningful features. However, with numerous transforms available, selecting an appropriate one often depends on understanding the dataset's properties, making the approach less effective when such knowledge is unavailable. In this work, we propose General Transform (GT), an adaptive transform-based representation designed for machine learning applications. Unlike conventional transforms, GT learns data-driven mapping tailored to the dataset and task of interest. Here, we demonstrate that models incorporating GT outperform conventional transform-based approaches across computer vision and natural language processing tasks, highlighting its effectiveness in diverse learning scenarios.