Clustering-based Domain-Incremental Learning
- URL: http://arxiv.org/abs/2309.12078v1
- Date: Thu, 21 Sep 2023 13:49:05 GMT
- Title: Clustering-based Domain-Incremental Learning
- Authors: Christiaan Lamers, Rene Vidal, Nabil Belbachir, Niki van Stein, Thomas
Baeck, Paris Giampouras
- Abstract summary: Key challenge in continual learning is the so-called "catastrophic forgetting problem"
We propose an online clustering-based approach on a dynamically updated finite pool of samples or gradients.
We demonstrate the effectiveness of the proposed strategy and its promising performance compared to state-of-the-art methods.
- Score: 4.835091081509403
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We consider the problem of learning multiple tasks in a continual learning
setting in which data from different tasks is presented to the learner in a
streaming fashion. A key challenge in this setting is the so-called
"catastrophic forgetting problem", in which the performance of the learner in
an "old task" decreases when subsequently trained on a "new task". Existing
continual learning methods, such as Averaged Gradient Episodic Memory (A-GEM)
and Orthogonal Gradient Descent (OGD), address catastrophic forgetting by
minimizing the loss for the current task without increasing the loss for
previous tasks. However, these methods assume the learner knows when the task
changes, which is unrealistic in practice. In this paper, we alleviate the need
to provide the algorithm with information about task changes by using an online
clustering-based approach on a dynamically updated finite pool of samples or
gradients. We thereby successfully counteract catastrophic forgetting in one of
the hardest settings, namely: domain-incremental learning, a setting for which
the problem was previously unsolved. We showcase the benefits of our approach
by applying these ideas to projection-based methods, such as A-GEM and OGD,
which lead to task-agnostic versions of them. Experiments on real datasets
demonstrate the effectiveness of the proposed strategy and its promising
performance compared to state-of-the-art methods.
Related papers
- An Effective Dynamic Gradient Calibration Method for Continual Learning [11.555822066922508]
Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks.
Due to the memory limit, we cannot store all the historical data, and therefore confront the catastrophic forgetting'' problem.
We develop an effective algorithm to calibrate the gradient in each updating step of the model.
arXiv Detail & Related papers (2024-07-30T16:30:09Z) - Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
A common problem in continual learning is the classification layer's bias towards the most recent task.
We name our approach Adaptive Retention & Correction (ARC)
ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
arXiv Detail & Related papers (2024-05-23T08:43:09Z) - Data-CUBE: Data Curriculum for Instruction-based Sentence Representation
Learning [85.66907881270785]
We propose a data curriculum method, namely Data-CUBE, that arranges the orders of all the multi-task data for training.
In the task level, we aim to find the optimal task order to minimize the total cross-task interference risk.
In the instance level, we measure the difficulty of all instances per task, then divide them into the easy-to-difficult mini-batches for training.
arXiv Detail & Related papers (2024-01-07T18:12:20Z) - Fine-Grained Knowledge Selection and Restoration for Non-Exemplar Class
Incremental Learning [64.14254712331116]
Non-exemplar class incremental learning aims to learn both the new and old tasks without accessing any training data from the past.
We propose a novel framework of fine-grained knowledge selection and restoration.
arXiv Detail & Related papers (2023-12-20T02:34:11Z) - Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization [51.34904967046097]
Continual learning seeks to overcome the challenge of catastrophic forgetting, where a model forgets previously learnt information.
We introduce a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting.
Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments.
arXiv Detail & Related papers (2023-09-15T17:10:51Z) - Class-Incremental Learning via Knowledge Amalgamation [14.513858688486701]
Catastrophic forgetting has been a significant problem hindering the deployment of deep learning algorithms in the continual learning setting.
We put forward an alternative strategy to handle the catastrophic forgetting with knowledge amalgamation (CFA)
CFA learns a student network from multiple heterogeneous teacher models specializing in previous tasks and can be applied to current offline methods.
arXiv Detail & Related papers (2022-09-05T19:49:01Z) - Center Loss Regularization for Continual Learning [0.0]
In general, neural networks lack the ability to learn different tasks sequentially.
Our approach remembers old tasks by projecting the representations of new tasks close to that of old tasks.
We demonstrate that our approach is scalable, effective, and gives competitive performance compared to state-of-the-art continual learning methods.
arXiv Detail & Related papers (2021-10-21T17:46:44Z) - TAG: Task-based Accumulated Gradients for Lifelong learning [21.779858050277475]
We propose a task-aware system that adapts the learning rate based on the relatedness among tasks.
We empirically show that our proposed adaptive learning rate not only accounts for catastrophic forgetting but also allows positive backward transfer.
arXiv Detail & Related papers (2021-05-11T16:10:32Z) - Incremental Object Detection via Meta-Learning [77.55310507917012]
We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared.
In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
arXiv Detail & Related papers (2020-03-17T13:40:00Z) - Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding
Meta-Amortization Error [50.83356836818667]
We develop a novel meta-regularization objective using it cyclical annealing schedule and it maximum mean discrepancy (MMD) criterion.
The experimental results show that our approach substantially outperforms standard meta-learning algorithms.
arXiv Detail & Related papers (2020-03-04T04:43:16Z)
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.