User-friendly Foundation Model Adapters for Multivariate Time Series Classification
This work addresses the problem of computational resource limitations for users running large pre-trained foundation models on multivariate time series classification, though it is incremental as it applies existing methods to this context.
The paper tackled the challenge of making resource-intensive foundation models more accessible by exploring dimensionality reduction techniques, achieving up to a 10x speedup and enabling 4.5x more datasets to fit on a single GPU without performance degradation.
Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dimensionality reduction techniques. Our goal is to enable users to run large pre-trained foundation models on standard GPUs without sacrificing performance. We investigate classical methods such as Principal Component Analysis alongside neural network-based adapters, aiming to reduce the dimensionality of multivariate time series data while preserving key features. Our experiments show up to a 10x speedup compared to the baseline model, without performance degradation, and enable up to 4.5x more datasets to fit on a single GPU, paving the way for more user-friendly and scalable foundation models.