User-friendly Foundation Model Adapters for Multivariate Time Series Classification

• URL: http://arxiv.org/abs/2409.12264v1
• Date: Wed, 18 Sep 2024 18:50:20 GMT
• Title: User-friendly Foundation Model Adapters for Multivariate Time Series Classification
• Authors: Vasilii Feofanov, Romain Ilbert, Malik Tiomoko, Themis Palpanas, Ievgen Redko,
• Abstract summary: 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 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.
• Score: 16.94369040048502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content [62.816876067499415]
  We propose LiveXiv: a scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models true abilities.
  arXiv  Detail & Related papers  (2024-10-14T17:51:23Z)
• MSTAR: Multi-Scale Backbone Architecture Search for Timeseries Classification [0.41185655356953593]
  We propose a novel multi-scale search space and a framework for Neural architecture search (NAS) We show that our model can serve as a backbone to employ a powerful Transformer module with both untrained and pre-trained weights. Our search space reaches the state-of-the-art performance on four datasets on four different domains.
  arXiv  Detail & Related papers  (2024-02-21T13:59:55Z)
• Low-resource finetuning of foundation models beats state-of-the-art in histopathology [3.4577420145036375]
  We benchmark the most popular vision foundation models as feature extractors for histopathology data. By finetuning a foundation model on a single GPU for only two hours or three days depending on the dataset, we can match or outperform state-of-the-art feature extractors. This is a considerable shift from the current state, where only few institutions with large amounts of resources and datasets are able to train a feature extractor.
  arXiv  Detail & Related papers  (2024-01-09T18:46:59Z)
• ZooPFL: Exploring Black-box Foundation Models for Personalized Federated Learning [95.64041188351393]
  This paper endeavors to solve both the challenges of limited resources and personalization. We propose a method named ZOOPFL that uses Zeroth-Order Optimization for Personalized Federated Learning. To reduce the computation costs and enhance personalization, we propose input surgery to incorporate an auto-encoder with low-dimensional and client-specific embeddings.
  arXiv  Detail & Related papers  (2023-10-08T12:26:13Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• Deep Generative model with Hierarchical Latent Factors for Time Series Anomaly Detection [40.21502451136054]
  This work presents DGHL, a new family of generative models for time series anomaly detection. A top-down Convolution Network maps a novel hierarchical latent space to time series windows, exploiting temporal dynamics to encode information efficiently. Our method outperformed current state-of-the-art models on four popular benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-15T17:19:44Z)
• Data Summarization via Bilevel Optimization [48.89977988203108]
  A simple yet powerful approach is to operate on small subsets of data. In this work, we propose a generic coreset framework that formulates the coreset selection as a cardinality-constrained bilevel optimization problem.
  arXiv  Detail & Related papers  (2021-09-26T09:08:38Z)
• STAR: Sparse Transformer-based Action Recognition [61.490243467748314]
  This work proposes a novel skeleton-based human action recognition model with sparse attention on the spatial dimension and segmented linear attention on the temporal dimension of data. Experiments show that our model can achieve comparable performance while utilizing much less trainable parameters and achieve high speed in training and inference.
  arXiv  Detail & Related papers  (2021-07-15T02:53:11Z)
• Top-KAST: Top-K Always Sparse Training [50.05611544535801]
  We propose Top-KAST, a method that preserves constant sparsity throughout training. We show that it performs comparably to or better than previous works when training models on the established ImageNet benchmark. In addition to our ImageNet results, we also demonstrate our approach in the domain of language modeling.
  arXiv  Detail & Related papers  (2021-06-07T11:13:05Z)
• Do We Really Need Deep Learning Models for Time Series Forecasting? [4.2698418800007865]
  Time series forecasting is a crucial task in machine learning, as it has a wide range of applications. Deep learning and matrix factorization models have been recently proposed to tackle the same problem with more competitive performance. In this paper, we try to answer whether these highly complex deep learning models are without alternative.
  arXiv  Detail & Related papers  (2021-01-06T16:18:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.