On the Stability-Plasticity Dilemma of Class-Incremental Learning
- URL: http://arxiv.org/abs/2304.01663v1
- Date: Tue, 4 Apr 2023 09:34:14 GMT
- Title: On the Stability-Plasticity Dilemma of Class-Incremental Learning
- Authors: Dongwan Kim and Bohyung Han
- Abstract summary: A primary goal of class-incremental learning is to strike a balance between stability and plasticity.
This paper aims to shed light on how effectively recent class-incremental learning algorithms address the stability-plasticity trade-off.
- Score: 50.863180812727244
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: A primary goal of class-incremental learning is to strike a balance between
stability and plasticity, where models should be both stable enough to retain
knowledge learned from previously seen classes, and plastic enough to learn
concepts from new classes. While previous works demonstrate strong performance
on class-incremental benchmarks, it is not clear whether their success comes
from the models being stable, plastic, or a mixture of both. This paper aims to
shed light on how effectively recent class-incremental learning algorithms
address the stability-plasticity trade-off. We establish analytical tools that
measure the stability and plasticity of feature representations, and employ
such tools to investigate models trained with various algorithms on large-scale
class-incremental benchmarks. Surprisingly, we find that the majority of
class-incremental learning algorithms heavily favor stability over plasticity,
to the extent that the feature extractor of a model trained on the initial set
of classes is no less effective than that of the final incremental model. Our
observations not only inspire two simple algorithms that highlight the
importance of feature representation analysis, but also suggest that
class-incremental learning approaches, in general, should strive for better
feature representation learning.
Related papers
- Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences [6.067007470552307]
We propose a methodology for finding sequences of machine learning models that are stable across retraining iterations.
We develop a mixed-integer optimization formulation that is guaranteed to recover optimal models.
Our method shows stronger stability than greedily trained models with a small, controllable sacrifice in predictive power.
arXiv Detail & Related papers (2024-03-28T22:45:38Z) - Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning [33.560003528712414]
Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data.
This poses a challenge in striking a balance between stability and plasticity when adapting to new information.
We propose Branch-tuning, an efficient and straightforward method that achieves a balance between stability and plasticity in continual SSL.
arXiv Detail & Related papers (2024-03-27T05:38:48Z) - Towards Plastic and Stable Exemplar-Free Incremental Learning: A Dual-Learner Framework with Cumulative Parameter Averaging [12.168402195820649]
We propose a Dual-Learner framework with Cumulative.
Averaging (DLCPA)
We show that DLCPA outperforms several state-of-the-art exemplar-free baselines in both Task-IL and Class-IL settings.
arXiv Detail & Related papers (2023-10-28T08:48:44Z) - Robust Learning with Progressive Data Expansion Against Spurious
Correlation [65.83104529677234]
We study the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features.
Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process.
We propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.
arXiv Detail & Related papers (2023-06-08T05:44:06Z) - SRIL: Selective Regularization for Class-Incremental Learning [5.810252620242912]
Class-Incremental Learning aims to create an integrated model that balances plasticity and stability to overcome this challenge.
We propose a selective regularization method that accepts new knowledge while maintaining previous knowledge.
We validate the effectiveness of the proposed method through extensive experimental protocols using CIFAR-100, ImageNet-Subset, and ImageNet-Full.
arXiv Detail & Related papers (2023-05-09T05:04:35Z) - PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning [49.0417577439298]
Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge.
We propose a method which has similar number of parameters but distributes them differently to find a better balance between plasticity and stability.
arXiv Detail & Related papers (2022-09-14T12:53:00Z) - Towards Diverse Evaluation of Class Incremental Learning: A Representation Learning Perspective [67.45111837188685]
Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data.
We experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning.
arXiv Detail & Related papers (2022-06-16T11:44:11Z) - Self-Supervised Class Incremental Learning [51.62542103481908]
Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels.
When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new.
In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
arXiv Detail & Related papers (2021-11-18T06:58:19Z) - Towards Better Plasticity-Stability Trade-off in Incremental Learning: A
simple Linear Connector [8.13916229438606]
Plasticity-stability dilemma is a main problem for incremental learning.
We show that a simple averaging of two independently optimized optima of networks, null-space projection for past tasks and simple SGD for the current task, can attain a meaningful balance between preserving already learned knowledge and granting sufficient flexibility for learning a new task.
arXiv Detail & Related papers (2021-10-15T07:37:20Z) - Model-Augmented Actor-Critic: Backpropagating through Paths [81.86992776864729]
Current model-based reinforcement learning approaches use the model simply as a learned black-box simulator.
We show how to make more effective use of the model by exploiting its differentiability.
arXiv Detail & Related papers (2020-05-16T19:18:10Z)
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.