Gekko Budiutama

Fixed transforms such as the discrete Fourier transform and discrete cosine transform are widely used in machine learning to extract features, but choosing among them usually requires knowing the dataset's properties, and the approach weakens when that knowledge is missing. The Adaptive Interpolating Transform (AIT) turns the transform itself into learnable parameters, learning data-driven mappings tailored to the dataset and task. On ImageNet-2012 and the General Language Understanding Evaluation tasks, AIT-enhanced models outperform fixed-transform baselines under both from-scratch and fine-tuning workflows, adding only nine parameters to vision models and three per encoder layer to language models.

Fixed transforms such as the discrete Fourier transform and discrete cosine transform are widely used in machine learning to extract features, but choosing among them usually requires knowing the dataset's properties, and the approach weakens when that knowledge is missing. The Adaptive Interpolating Transform (AIT) turns the transform itself into learnable parameters, learning data-driven mappings tailored to the dataset and task. On ImageNet-2012 and the General Language Understanding Evaluation tasks, AIT-enhanced models outperform fixed-transform baselines under both from-scratch and fine-tuning workflows, adding only nine parameters to vision models and three per encoder layer to language models.