DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning
- URL: http://arxiv.org/abs/2411.19154v1
- Date: Thu, 28 Nov 2024 13:54:01 GMT
- Title: DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning
- Authors: Haiyang Guo, Fei Zhu, Fanhu Zeng, Bing Liu, Xu-Yao Zhang,
- Abstract summary: Continual learning aims to equip models with the ability to retain previously learned knowledge like a human.
Existing methods usually overlook the issue of information leakage caused by the fact that the experiment data have been used in pre-trained models.
In this paper, we propose a new LoRA-based rehearsal-free method named DESIRE.
- Score: 23.878495627964146
- License:
- Abstract: Continual learning aims to equip models with the ability to retain previously learned knowledge like a human. Recent work incorporating Parameter-Efficient Fine-Tuning has revitalized the field by introducing lightweight extension modules. However, existing methods usually overlook the issue of information leakage caused by the fact that the experiment data have been used in pre-trained models. Once these duplicate data are removed in the pre-training phase, their performance can be severely affected. In this paper, we propose a new LoRA-based rehearsal-free method named DESIRE. Our method avoids imposing additional constraints during training to mitigate catastrophic forgetting, thereby maximizing the learning of new classes. To integrate knowledge from old and new tasks, we propose two efficient post-processing modules. On the one hand, we retain only two sets of LoRA parameters for merging and propose dynamic representation consolidation to calibrate the merged feature representation. On the other hand, we propose decision boundary refinement to address classifier bias when training solely on new class data. Extensive experiments demonstrate that our method achieves state-of-the-art performance on multiple datasets and strikes an effective balance between stability and plasticity. Our code will be publicly available.
Related papers
- How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM? [55.33467849079774]
Low-rank adaptation (LoRA) is a popular and efficient training technique for updating or domain-specific adaptation of Large Language Models.
We investigate how new facts can be incorporated into the LLM using LoRA without compromising the previously learned knowledge.
arXiv Detail & Related papers (2025-02-20T12:31:03Z) - CSTA: Spatial-Temporal Causal Adaptive Learning for Exemplar-Free Video Class-Incremental Learning [62.69917996026769]
A class-incremental learning task requires learning and preserving both spatial appearance and temporal action involvement.
We propose a framework that equips separate adapters to learn new class patterns, accommodating the incremental information requirements unique to each class.
A causal compensation mechanism is proposed to reduce the conflicts during increment and memorization for between different types of information.
arXiv Detail & Related papers (2025-01-13T11:34:55Z) - Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion [10.322832012497722]
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time.
With the advancement of vision-language pre-trained models such as CLIP, they demonstrate good generalization ability.
However, further adaptation to downstream tasks by simply fine-tuning the model leads to severe forgetting.
Most existing works with pre-trained models assume that the forgetting of old classes is uniform when the model acquires new knowledge.
arXiv Detail & Related papers (2024-07-19T09:20:33Z) - Beyond Prompt Learning: Continual Adapter for Efficient Rehearsal-Free Continual Learning [22.13331870720021]
We propose a beyond prompt learning approach to the RFCL task, called Continual Adapter (C-ADA)
C-ADA flexibly extends specific weights in CAL to learn new knowledge for each task and freezes old weights to preserve prior knowledge.
Our approach achieves significantly improved performance and training speed, outperforming the current state-of-the-art (SOTA) method.
arXiv Detail & Related papers (2024-07-14T17:40:40Z) - Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approach [87.8330887605381]
We show how to adapt a pre-trained Vision Transformer to downstream recognition tasks with only a few learnable parameters.
We synthesize a task-specific query with a learnable and lightweight module, which is independent of the pre-trained model.
Our method achieves state-of-the-art performance under memory constraints, showcasing its applicability in real-world situations.
arXiv Detail & Related papers (2024-07-09T15:45:04Z) - Adaptive Retention & Correction: Test-Time Training 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) - DUEL: Duplicate Elimination on Active Memory for Self-Supervised
Class-Imbalanced Learning [19.717868805172323]
We propose an active data filtering process during self-supervised pre-training in our novel framework, Duplicate Elimination (DUEL)
This framework integrates an active memory inspired by human working memory and introduces distinctiveness information, which measures the diversity of the data in the memory.
The DUEL policy, which replaces the most duplicated data with new samples, aims to enhance the distinctiveness information in the memory and thereby mitigate class imbalances.
arXiv Detail & Related papers (2024-02-14T06:09:36Z) - 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) - Federated Unlearning via Active Forgetting [24.060724751342047]
We propose a novel federated unlearning framework based on incremental learning.
Our framework differs from existing federated unlearning methods that rely on approximate retraining or data influence estimation.
arXiv Detail & Related papers (2023-07-07T03:07:26Z) - Complementary Learning Subnetworks for Parameter-Efficient
Class-Incremental Learning [40.13416912075668]
We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks.
Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
arXiv Detail & Related papers (2023-06-21T01:43:25Z) - Adaptive Cross Batch Normalization for Metric Learning [75.91093210956116]
Metric learning is a fundamental problem in computer vision.
We show that it is equally important to ensure that the accumulated embeddings are up to date.
In particular, it is necessary to circumvent the representational drift between the accumulated embeddings and the feature embeddings at the current training iteration.
arXiv Detail & Related papers (2023-03-30T03:22:52Z)
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.