Schedule-Robust Online Continual Learning
- URL: http://arxiv.org/abs/2210.05561v1
- Date: Tue, 11 Oct 2022 15:55:06 GMT
- Title: Schedule-Robust Online Continual Learning
- Authors: Ruohan Wang, Marco Ciccone, Giulia Luise, Massimiliano Pontil, Andrew
Yapp, Carlo Ciliberto
- Abstract summary: A continual learning algorithm learns from a non-stationary data stream.
A key challenge in CL is to design methods robust against arbitrary schedules over the same underlying data.
We present a new perspective on CL, as the process of learning a schedule-robust predictor, followed by adapting the predictor using only replay data.
- Score: 45.325658404913945
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: A continual learning (CL) algorithm learns from a non-stationary data stream.
The non-stationarity is modeled by some schedule that determines how data is
presented over time. Most current methods make strong assumptions on the
schedule and have unpredictable performance when such requirements are not met.
A key challenge in CL is thus to design methods robust against arbitrary
schedules over the same underlying data, since in real-world scenarios
schedules are often unknown and dynamic. In this work, we introduce the notion
of schedule-robustness for CL and a novel approach satisfying this desirable
property in the challenging online class-incremental setting. We also present a
new perspective on CL, as the process of learning a schedule-robust predictor,
followed by adapting the predictor using only replay data. Empirically, we
demonstrate that our approach outperforms existing methods on CL benchmarks for
image classification by a large margin.
Related papers
- TS-ACL: A Time Series Analytic Continual Learning Framework for Privacy-Preserving and Class-Incremental Pattern Recognition [14.108911377558242]
TS-ACL is a novel framework for privacy-preserving and class-incremental pattern recognition.
It transforms each update of the model into a gradient-free analytical learning process with a closed-form solution.
It simultaneously achieves non-forgetting, privacy preservation, and lightweight consumption, making it widely suitable for various applications.
arXiv Detail & Related papers (2024-10-21T12:34:02Z) - Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation [123.4883806344334]
We study a realistic Continual Learning setting where learning algorithms are granted a restricted computational budget per time step while training.
We apply this setting to large-scale semi-supervised Continual Learning scenarios with sparse label rates.
Our extensive analysis and ablations demonstrate that DietCL is stable under a full spectrum of label sparsity, computational budget, and various other ablations.
arXiv Detail & Related papers (2024-04-19T10:10:39Z) - Mitigating Catastrophic Forgetting in Task-Incremental Continual
Learning with Adaptive Classification Criterion [50.03041373044267]
We propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning.
Experiments show that CFL achieves state-of-the-art performance and has a stronger ability to overcome compared with the classification baselines.
arXiv Detail & Related papers (2023-05-20T19:22:40Z) - Real-Time Evaluation in Online Continual Learning: A New Hope [104.53052316526546]
We evaluate current Continual Learning (CL) methods with respect to their computational costs.
A simple baseline outperforms state-of-the-art CL methods under this evaluation.
This surprisingly suggests that the majority of existing CL literature is tailored to a specific class of streams that is not practical.
arXiv Detail & Related papers (2023-02-02T12:21:10Z) - Do Pre-trained Models Benefit Equally in Continual Learning? [25.959813589169176]
Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch.
Despite their encouraging performance on contrived benchmarks, these algorithms show dramatic performance drops in real-world scenarios.
This paper advocates the systematic introduction of pre-training to CL.
arXiv Detail & Related papers (2022-10-27T18:03:37Z) - A Study of Continual Learning Methods for Q-Learning [78.6363825307044]
We present an empirical study on the use of continual learning (CL) methods in a reinforcement learning (RL) scenario.
Our results show that dedicated CL methods can significantly improve learning when compared to the baseline technique of "experience replay"
arXiv Detail & Related papers (2022-06-08T14:51:52Z) - The CLEAR Benchmark: Continual LEArning on Real-World Imagery [77.98377088698984]
Continual learning (CL) is widely regarded as crucial challenge for lifelong AI.
We introduce CLEAR, the first continual image classification benchmark dataset with a natural temporal evolution of visual concepts.
We find that a simple unsupervised pre-training step can already boost state-of-the-art CL algorithms.
arXiv Detail & Related papers (2022-01-17T09:09:09Z) - Weakly Supervised Continual Learning [17.90483695137098]
This work explores Weakly Supervised Continual Learning (WSCL)
We show that not only our proposals exhibit higher flexibility when supervised information is scarce, but also that less than 25% labels can be enough to reach or even outperform SOTA methods trained under full supervision.
In doing so, we show that not only our proposals exhibit higher flexibility when supervised information is scarce, but also that less than 25% labels can be enough to reach or even outperform SOTA methods trained under full supervision.
arXiv Detail & Related papers (2021-08-14T14:38:20Z) - Continual Learning for Recurrent Neural Networks: a Review and Empirical
Evaluation [12.27992745065497]
Continual Learning with recurrent neural networks could pave the way to a large number of applications where incoming data is non stationary.
We organize the literature on CL for sequential data processing by providing a categorization of the contributions and a review of the benchmarks.
We propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real-world applications.
arXiv Detail & Related papers (2021-03-12T19:25:28Z)
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.