How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models

• URL: http://arxiv.org/abs/2409.18664v1
• Date: Fri, 27 Sep 2024 11:50:10 GMT
• Title: How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
• Authors: Tomaso Trinci, Simone Magistri, Roberto Verdecchia, Andrew D. Bagdanov,
• Abstract summary: We aim to gain a systematic understanding of the energy efficiency of continual learning algorithms. We performed experiments on three standard datasets: CIFAR-100, ImageNet-R, and DomainNet. We propose a novel metric, the Energy NetScore, which we use measure the algorithm efficiency in terms of energy-accuracy trade-off.
• Score: 10.192658261639549
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the ever-growing adoption of AI, its impact on the environment is no longer negligible. Despite the potential that continual learning could have towards Green AI, its environmental sustainability remains relatively uncharted. In this work we aim to gain a systematic understanding of the energy efficiency of continual learning algorithms. To that end, we conducted an extensive set of empirical experiments comparing the energy consumption of recent representation-, prompt-, and exemplar-based continual learning algorithms and two standard baseline (fine tuning and joint training) when used to continually adapt a pre-trained ViT-B/16 foundation model. We performed our experiments on three standard datasets: CIFAR-100, ImageNet-R, and DomainNet. Additionally, we propose a novel metric, the Energy NetScore, which we use measure the algorithm efficiency in terms of energy-accuracy trade-off. Through numerous evaluations varying the number and size of the incremental learning steps, our experiments demonstrate that different types of continual learning algorithms have very different impacts on energy consumption during both training and inference. Although often overlooked in the continual learning literature, we found that the energy consumed during the inference phase is crucial for evaluating the environmental sustainability of continual learning models.

Related papers

• Watt For What: Rethinking Deep Learning's Energy-Performance Relationship [13.505163099299025]
  We study the trade-off between model accuracy and electricity consumption of deep learning models. By evaluating accuracy per unit of electricity consumed, we demonstrate how smaller, more energy-efficient models can significantly expedite research. This research contributes to a more equitable research landscape, where smaller entities can compete effectively with larger counterparts.
  arXiv  Detail & Related papers  (2023-10-10T11:08:31Z)
• How to use model architecture and training environment to estimate the energy consumption of DL training [5.190998244098203]
  This study aims to leverage the relationship between energy consumption and two relevant design decisions in Deep Learning training. We study the training's power consumption behavior and propose four new energy estimation methods. Our results show that selecting the proper model architecture and training environment can reduce energy consumption dramatically.
  arXiv  Detail & Related papers  (2023-07-07T12:07:59Z)
• A Comparative Study of Machine Learning Algorithms for Anomaly Detection in Industrial Environments: Performance and Environmental Impact [62.997667081978825]
  This study seeks to address the demands of high-performance machine learning models with environmental sustainability. Traditional machine learning algorithms, such as Decision Trees and Random Forests, demonstrate robust efficiency and performance. However, superior outcomes were obtained with optimised configurations, albeit with a commensurate increase in resource consumption.
  arXiv  Detail & Related papers  (2023-07-01T15:18:00Z)
• Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI [8.025202812165412]
  We consider energy consumption as a metric of equal importance to accuracy and to reduce any irrelevant tasks or energy usage. We examine the training stage of the deep learning pipeline from a sustainability perspective. We highlight innovative and promising energy-efficient practices for training deep learning models.
  arXiv  Detail & Related papers  (2023-03-24T12:48:21Z)
• Energy Efficiency of Training Neural Network Architectures: An Empirical Study [11.325530936177493]
  The evaluation of Deep Learning models has traditionally focused on criteria such as accuracy, F1 score, and related measures. The computations needed to train such models entail a large carbon footprint. We study the relations between DL model architectures and their environmental impact in terms of energy consumed and CO$$ emissions produced during training.
  arXiv  Detail & Related papers  (2023-02-02T09:20:54Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• An Energy and Carbon Footprint Analysis of Distributed and Federated Learning [42.37180749113699]
  Classical and centralized Artificial Intelligence (AI) methods require moving data from producers (sensors, machines) to energy hungry data centers. Emerging alternatives to mitigate such high energy costs propose to efficiently distribute, or federate, the learning tasks across devices. This paper proposes a novel framework for the analysis of energy and carbon footprints in distributed and federated learning.
  arXiv  Detail & Related papers  (2022-06-21T13:28:49Z)
• Energy-based Latent Aligner for Incremental Learning [83.0135278697976]
  Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new tasks may not align well with the updates suitable for older tasks. We propose ELI: Energy-based Latent Aligner for Incremental Learning.
  arXiv  Detail & Related papers  (2022-03-28T17:57:25Z)
• Learning to Continuously Optimize Wireless Resource in a Dynamic Environment: A Bilevel Optimization Perspective [52.497514255040514]
  This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment. We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes. Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2021-05-03T07:23:39Z)
• Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment [55.91291559442884]
  This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. We propose to build the notion of continual learning into the modeling process of learning wireless systems. Our design is based on a novel min-max formulation which ensures certain fairness" across different data samples.
  arXiv  Detail & Related papers  (2020-11-16T08:24:34Z)
• Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning [68.37641996188133]
  We introduce a framework for tracking realtime energy consumption and carbon emissions. We create a leaderboard for energy efficient reinforcement learning algorithms. We propose strategies for mitigation of carbon emissions and reduction of energy consumption.
  arXiv  Detail & Related papers  (2020-01-31T05:12:59Z)

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.