Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning

• URL: http://arxiv.org/abs/2511.09871v1
• Date: Fri, 14 Nov 2025 01:14:29 GMT
• Title: Expandable and Differentiable Dual Memories with Orthogonal Regularization for Exemplar-free Continual Learning
• Abstract summary: Continual learning methods force neural networks to process sequential tasks in isolation, preventing them from leveraging useful inter-task relationships.<n>We propose a fully differentiable, exemplar-free expandable method composed of two complementary memories.<n> Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that the proposed method outperforms 14 state-of-the-art methods for class-incremental learning.
• Score: 9.626869344059456
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning methods used to force neural networks to process sequential tasks in isolation, preventing them from leveraging useful inter-task relationships and causing them to repeatedly relearn similar features or overly differentiate them. To address this problem, we propose a fully differentiable, exemplar-free expandable method composed of two complementary memories: One learns common features that can be used across all tasks, and the other combines the shared features to learn discriminative characteristics unique to each sample. Both memories are differentiable so that the network can autonomously learn latent representations for each sample. For each task, the memory adjustment module adaptively prunes critical slots and minimally expands capacity to accommodate new concepts, and orthogonal regularization enforces geometric separation between preserved and newly learned memory components to prevent interference. Experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that the proposed method outperforms 14 state-of-the-art methods for class-incremental learning, achieving final accuracies of 55.13\%, 37.24\%, and 30.11\%, respectively. Additional analysis confirms that, through effective integration and utilization of knowledge, the proposed method can increase average performance across sequential tasks, and it produces feature extraction results closest to the upper bound, thus establishing a new milestone in continual learning.

Related papers

• CLARE: Scalable Class-Incremental Continual Learning via a Sparsity-Based Framework [42.31039781559425]
  Continual learning must balance the learning of new knowledge with the retention of previously learned knowledge.<n>Existing methods exhibit a scalability bottleneck when trained sequentially on many tasks.<n>Inspired by evidence that sparse fine-tuning achieves performance comparable to full fine-tuning, this paper presents a novel sparsity-driven continual learning framework.
  arXiv  Detail & Related papers  (2026-09-15T11:33:44Z)
• Divergent Ensemble Networks: Enhancing Uncertainty Estimation with Shared Representations and Independent Branching [0.9963916732353794]
  Divergent Ensemble Network (DEN) is a novel architecture that combines shared representation learning with independent branching.<n>DEN employs a shared input layer to capture common features across all branches, followed by divergent, independently trainable layers that form an ensemble.<n>This shared-to-branching structure reduces parameter redundancy while maintaining ensemble diversity, enabling efficient and scalable learning.
  arXiv  Detail & Related papers  (2024-12-02T06:52:45Z)
• 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)
• Multi-Task Learning with Prior Information [5.770309971945476]
  We propose a multi-task learning framework, where we utilize prior knowledge about the relations between features. We also impose a penalty on the coefficients changing for each specific feature to ensure related tasks have similar coefficients on common features shared among them.
  arXiv  Detail & Related papers  (2023-01-04T12:48:05Z)
• Neural Architecture for Online Ensemble Continual Learning [6.241435193861262]
  We present a fully differentiable ensemble method that allows us to efficiently train an ensemble of neural networks in the end-to-end regime. The proposed technique achieves SOTA results without a memory buffer and clearly outperforms the reference methods.
  arXiv  Detail & Related papers  (2022-11-27T23:17:08Z)
• Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning [53.17258888552998]
  This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation. We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
  arXiv  Detail & Related papers  (2022-06-01T23:26:51Z)
• Generative Kernel Continual learning [117.79080100313722]
  We introduce generative kernel continual learning, which exploits the synergies between generative models and kernels for continual learning. The generative model is able to produce representative samples for kernel learning, which removes the dependence on memory in kernel continual learning. We conduct extensive experiments on three widely-used continual learning benchmarks that demonstrate the abilities and benefits of our contributions.
  arXiv  Detail & Related papers  (2021-12-26T16:02:10Z)
• Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search [65.51181219410763]
  One-step methods have been developed to handle pedestrian detection and identification sub-tasks using a single network. There are two major challenges in the current one-step approaches. We propose a decoupled and memory-reinforced network (DMRNet) to overcome these problems.
  arXiv  Detail & Related papers  (2021-02-22T06:19:45Z)
• Incremental Embedding Learning via Zero-Shot Translation [65.94349068508863]
  Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks. We propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI) In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks.
  arXiv  Detail & Related papers  (2020-12-31T08:21:37Z)
• Multi-task Supervised Learning via Cross-learning [102.64082402388192]
  We consider a problem known as multi-task learning, consisting of fitting a set of regression functions intended for solving different tasks. In our novel formulation, we couple the parameters of these functions, so that they learn in their task specific domains while staying close to each other. This facilitates cross-fertilization in which data collected across different domains help improving the learning performance at each other task.
  arXiv  Detail & Related papers  (2020-10-24T21:35:57Z)
• ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification [49.87503122462432]
  We introduce a novel neural network termed Relation-and-Margin learning Network (ReMarNet) Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples.
  arXiv  Detail & Related papers  (2020-06-27T13:50:20Z)

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.