Online Continual Learning Without the Storage Constraint
- URL: http://arxiv.org/abs/2305.09253v2
- Date: Thu, 2 Nov 2023 06:06:50 GMT
- Title: Online Continual Learning Without the Storage Constraint
- Authors: Ameya Prabhu, Zhipeng Cai, Puneet Dokania, Philip Torr, Vladlen
Koltun, Ozan Sener
- Abstract summary: We contribute a simple algorithm, which updates a kNN classifier continually along with a fixed, pretrained feature extractor.
It can adapt to rapidly changing streams, has zero stability gap, operates within tiny computational budgets, has low storage requirements by only storing features.
It can outperform existing methods by over 20% in accuracy on two large-scale online continual learning datasets.
- Score: 67.66235695269839
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Traditional online continual learning (OCL) research has primarily focused on
mitigating catastrophic forgetting with fixed and limited storage allocation
throughout an agent's lifetime. However, a broad range of real-world
applications are primarily constrained by computational costs rather than
storage limitations. In this paper, we target such applications, investigating
the online continual learning problem under relaxed storage constraints and
limited computational budgets. We contribute a simple algorithm, which updates
a kNN classifier continually along with a fixed, pretrained feature extractor.
We selected this algorithm due to its exceptional suitability for online
continual learning. It can adapt to rapidly changing streams, has zero
stability gap, operates within tiny computational budgets, has low storage
requirements by only storing features, and has a consistency property: It never
forgets previously seen data. These attributes yield significant improvements,
allowing our proposed algorithm to outperform existing methods by over 20% in
accuracy on two large-scale OCL datasets: Continual LOCalization (CLOC) with
39M images and 712 classes and Continual Google Landmarks V2 (CGLM) with 580K
images and 10,788 classes, even when existing methods retain all previously
seen images. Furthermore, we achieve this superior performance with
considerably reduced computational and storage expenses. We provide code to
reproduce our results at github.com/drimpossible/ACM.
Related papers
- Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling [19.447914903112366]
We propose to use floating point operations and total memory size in Byte as a metric for computational and memory budgets.
To improve a CL method in a limited total budget, we propose adaptive layer freezing that does not update the layers for less informative batches.
In addition, we propose a memory retrieval method that allows the model to learn the same amount of knowledge as using random retrieval in fewer iterations.
arXiv Detail & Related papers (2024-10-19T16:00:00Z) - 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) - OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning [57.43911113915546]
Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which the problem space expands with limited data.
FSCIL methods inherently face the challenge of catastrophic forgetting as data arrives incrementally.
We propose the OrCo framework built on two core principles: features' orthogonality in the representation space, and contrastive learning.
arXiv Detail & Related papers (2024-03-27T13:30:48Z) - Action-Quantized Offline Reinforcement Learning for Robotic Skill
Learning [68.16998247593209]
offline reinforcement learning (RL) paradigm provides recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data.
In this paper, we propose an adaptive scheme for action quantization.
We show that several state-of-the-art offline RL methods such as IQL, CQL, and BRAC improve in performance on benchmarks when combined with our proposed discretization scheme.
arXiv Detail & Related papers (2023-10-18T06:07:10Z) - Computationally Budgeted Continual Learning: What Does Matter? [128.0827987414154]
Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data.
Current CL literature focuses on restricted access to previously seen data, while imposing no constraints on the computational budget for training.
We revisit this problem with a large-scale benchmark and analyze the performance of traditional CL approaches in a compute-constrained setting.
arXiv Detail & Related papers (2023-03-20T14:50:27Z) - Improving information retention in large scale online continual learning [99.73847522194549]
Online continual learning aims to adapt efficiently to new data while retaining existing knowledge.
Recent work suggests that information retention remains a problem in large scale OCL even when the replay buffer is unlimited.
We propose using a moving average family of methods to improve optimization for non-stationary objectives.
arXiv Detail & Related papers (2022-10-12T16:59:43Z) - Online Continual Learning under Extreme Memory Constraints [40.80045285324969]
We introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL)
MC-OCL imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting.
We propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach.
arXiv Detail & Related papers (2020-08-04T13:25:26Z)
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.