Haphazard Inputs as Images in Online Learning
This addresses the challenge of model-dependent solutions for haphazard inputs, making it applicable in fields requiring scalable and robust online learning.
The paper tackles the problem of varying feature spaces in online learning by transforming haphazard inputs into fixed-dimension images, enabling the use of vision-based models like ResNet and ViT, and demonstrates efficacy on four public datasets.
The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages.