An Investigation of Replay-based Approaches for Continual Learning
- URL: http://arxiv.org/abs/2108.06758v1
- Date: Sun, 15 Aug 2021 15:05:02 GMT
- Title: An Investigation of Replay-based Approaches for Continual Learning
- Authors: Benedikt Bagus and Alexander Gepperth
- Abstract summary: Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF)
Several solution classes have been proposed, of which so-called replay-based approaches seem very promising due to their simplicity and robustness.
We empirically investigate replay-based approaches of continual learning and assess their potential for applications.
- Score: 79.0660895390689
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Continual learning (CL) is a major challenge of machine learning (ML) and
describes the ability to learn several tasks sequentially without catastrophic
forgetting (CF). Recent works indicate that CL is a complex topic, even more so
when real-world scenarios with multiple constraints are involved. Several
solution classes have been proposed, of which so-called replay-based approaches
seem very promising due to their simplicity and robustness. Such approaches
store a subset of past samples in a dedicated memory for later processing:
while this does not solve all problems, good results have been obtained. In
this article, we empirically investigate replay-based approaches of continual
learning and assess their potential for applications. Selected recent
approaches as well as own proposals are compared on a common set of benchmarks,
with a particular focus on assessing the performance of different sample
selection strategies. We find that the impact of sample selection increases
when a smaller number of samples is stored. Nevertheless, performance varies
strongly between different replay approaches. Surprisingly, we find that the
most naive rehearsal-based approaches that we propose here can outperform
recent state-of-the-art methods.
Related papers
- Watch Your Step: Optimal Retrieval for Continual Learning at Scale [1.7265013728931]
In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks.
One of the most widely used approaches in continual learning is referred to as replay.
We propose a framework for evaluating selective retrieval strategies, categorized by simple, independent class- and sample-selective primitives.
We propose a set of strategies to prevent duplicate replays and explore whether new samples with low loss values can be learned without replay.
arXiv Detail & Related papers (2024-04-16T17:35:35Z) - BECLR: Batch Enhanced Contrastive Few-Shot Learning [1.450405446885067]
Unsupervised few-shot learning aspires to bridge this gap by discarding the reliance on annotations at training time.
We propose a novel Dynamic Clustered mEmory (DyCE) module to promote a highly separable latent representation space.
We then tackle the, somehow overlooked yet critical, issue of sample bias at the few-shot inference stage.
arXiv Detail & Related papers (2024-02-04T10:52:43Z) - Enhancing Consistency and Mitigating Bias: A Data Replay Approach for
Incremental Learning [100.7407460674153]
Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks.
To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks.
However, it is not expected in practice considering the memory constraint or data privacy issue.
As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
arXiv Detail & Related papers (2024-01-12T12:51:12Z) - RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning [53.52699766206808]
We propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning.
We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches and learnable baselines.
arXiv Detail & Related papers (2023-05-23T20:15:56Z) - Active Learning Principles for In-Context Learning with Large Language
Models [65.09970281795769]
This paper investigates how Active Learning algorithms can serve as effective demonstration selection methods for in-context learning.
We show that in-context example selection through AL prioritizes high-quality examples that exhibit low uncertainty and bear similarity to the test examples.
arXiv Detail & Related papers (2023-05-23T17:16:04Z) - Transfer and Active Learning for Dissonance Detection: Addressing the
Rare-Class Challenge [7.61140479230184]
We propose and investigate transfer- and active learning solutions to the rare class problem of dissonance detection.
We perform experiments for a specific rare class problem: collecting language samples of cognitive dissonance from social media.
We find that probability-of-rare-class (PRC) is a simple and effective strategy to guide annotations and ultimately improve model accuracy.
arXiv Detail & Related papers (2023-05-03T23:29:05Z) - A baseline on continual learning methods for video action recognition [15.157938674002793]
Continual learning aims to solve long-standing limitations of classic supervisedly-trained models.
We present a benchmark of state-of-the-art continual learning methods on video action recognition.
arXiv Detail & Related papers (2023-04-20T14:20:43Z) - Fast Hierarchical Learning for Few-Shot Object Detection [57.024072600597464]
Transfer learning approaches have recently achieved promising results on the few-shot detection task.
These approaches suffer from catastrophic forgetting'' issue due to finetuning of base detector.
We tackle the aforementioned issues in this work.
arXiv Detail & Related papers (2022-10-10T20:31:19Z) - Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
Prototype-centered Attentive Learning (PAL) model composed of two novel components.
First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective.
Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
arXiv Detail & Related papers (2021-01-20T11:48:12Z)
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.