BECAME: BayEsian Continual Learning with Adaptive Model MErging

• URL: http://arxiv.org/abs/2504.02666v1
• Date: Thu, 03 Apr 2025 15:07:28 GMT
• Title: BECAME: BayEsian Continual Learning with Adaptive Model MErging
• Authors: Mei Li, Yuxiang Lu, Qinyan Dai, Suizhi Huang, Yue Ding, Hongtao Lu,
• Abstract summary: We introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging.<n>Our approach outperforms state-of-the-art CL methods and existing merging strategies.
• Score: 21.642774366793997
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Learning (CL) strives to learn incrementally across tasks while mitigating catastrophic forgetting. A key challenge in CL is balancing stability (retaining prior knowledge) and plasticity (learning new tasks). While representative gradient projection methods ensure stability, they often limit plasticity. Model merging techniques offer promising solutions, but prior methods typically rely on empirical assumptions and carefully selected hyperparameters. In this paper, we explore the potential of model merging to enhance the stability-plasticity trade-off, providing theoretical insights that underscore its benefits. Specifically, we reformulate the merging mechanism using Bayesian continual learning principles and derive a closed-form solution for the optimal merging coefficient that adapts to the diverse characteristics of tasks. To validate our approach, we introduce a two-stage framework named BECAME, which synergizes the expertise of gradient projection and adaptive merging. Extensive experiments show that our approach outperforms state-of-the-art CL methods and existing merging strategies.

Related papers

• Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off [25.33978152436581]
  We propose a novel framework that reformulates the stability-plasticity trade-off in continual learning.<n>ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity.
  arXiv  Detail & Related papers  (2025-03-30T10:38:36Z)
• Feature Calibration enhanced Parameter Synthesis for CLIP-based Class-incremental Learning [10.253058594622017]
  Class-Incremental Learning (CIL) enables models to continuously learn new class knowledge while retaining previous classes. Traditional CIL methods rely primarily on visual features, which limits their effectiveness in complex, multimodal scenarios. We propose a Feature Enhanced Synthesis (FCPS) framework that mitigates catastrophic generalization while preserving the model's intrinsic generalization capability.
  arXiv  Detail & Related papers  (2025-03-24T13:44:12Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• TSVD: Bridging Theory and Practice in Continual Learning with Pre-trained Models [103.45785408116146]
  Continual learning (CL) aims to train a model that can solve multiple tasks presented sequentially.<n>Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks.<n>However, such methods lack theoretical guarantees, making them prone to unexpected failures.<n>We aim to bridge this gap by designing a simple CL method that is theoretically sound and highly performant.
  arXiv  Detail & Related papers  (2024-10-01T12:58:37Z)
• ReconBoost: Boosting Can Achieve Modality Reconcilement [89.4377895465204]
  We study the modality-alternating learning paradigm to achieve reconcilement. We propose a new method called ReconBoost to update a fixed modality each time. We show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others.
  arXiv  Detail & Related papers  (2024-05-15T13:22:39Z)
• FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing [3.533544633664583]
  Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting. Traditional EFCIL approaches typically skew towards either model plasticity through successive fine-tuning or stability. This paper builds upon the foundational FeTrIL framework to examine the efficacy of various oversampling techniques and dynamic optimization strategies.
  arXiv  Detail & Related papers  (2024-03-12T08:34:05Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)
• Class-Incremental Mixture of Gaussians for Deep Continual Learning [15.49323098362628]
  We propose end-to-end incorporation of the mixture of Gaussians model into the continual learning framework. We show that our model can effectively learn in memory-free scenarios with fixed extractors.
  arXiv  Detail & Related papers  (2023-07-09T04:33:19Z)
• Revisiting GANs by Best-Response Constraint: Perspective, Methodology, and Application [49.66088514485446]
  Best-Response Constraint (BRC) is a general learning framework to explicitly formulate the potential dependency of the generator on the discriminator. We show that even with different motivations and formulations, a variety of existing GANs ALL can be uniformly improved by our flexible BRC methodology.
  arXiv  Detail & Related papers  (2022-05-20T12:42:41Z)
• Training Generative Adversarial Networks by Solving Ordinary Differential Equations [54.23691425062034]
  We study the continuous-time dynamics induced by GAN training. From this perspective, we hypothesise that instabilities in training GANs arise from the integration error. We experimentally verify that well-known ODE solvers (such as Runge-Kutta) can stabilise training.
  arXiv  Detail & Related papers  (2020-10-28T15:23:49Z)
• Efficient Empowerment Estimation for Unsupervised Stabilization [75.32013242448151]
  empowerment principle enables unsupervised stabilization of dynamical systems at upright positions. We propose an alternative solution based on a trainable representation of a dynamical system as a Gaussian channel. We show that our method has a lower sample complexity, is more stable in training, possesses the essential properties of the empowerment function, and allows estimation of empowerment from images.
  arXiv  Detail & Related papers  (2020-07-14T21:10:16Z)

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.