Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization

• URL: http://arxiv.org/abs/2412.18177v1
• Date: Tue, 24 Dec 2024 05:25:21 GMT
• Title: Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
• Authors: Sihao Liu, Yibo Yang, Xiaojie Li, David A. Clifton, Bernard Ghanem,
• Abstract summary: Online continual learning (OCL) seeks to learn new tasks from data streams that appear only once, while retaining knowledge of previously learned tasks. Most existing methods rely on replay, focusing on enhancing memory retention through regularization or distillation. We introduce a plug-and-play module, S6MOD, which can be integrated into most existing methods and directly improve adaptability.
• Score: 72.81319836138347
• License:
• Abstract: Online continual learning (OCL) seeks to learn new tasks from data streams that appear only once, while retaining knowledge of previously learned tasks. Most existing methods rely on replay, focusing on enhancing memory retention through regularization or distillation. However, they often overlook the adaptability of the model, limiting the ability to learn generalizable and discriminative features incrementally from online training data. To address this, we introduce a plug-and-play module, S6MOD, which can be integrated into most existing methods and directly improve adaptability. Specifically, S6MOD introduces an extra branch after the backbone, where a mixture of discretization selectively adjusts parameters in a selective state space model, enriching selective scan patterns such that the model can adaptively select the most sensitive discretization method for current dynamics. We further design a class-conditional routing algorithm for dynamic, uncertainty-based adjustment and implement a contrastive discretization loss to optimize it. Extensive experiments combining our module with various models demonstrate that S6MOD significantly enhances model adaptability, leading to substantial performance gains and achieving the state-of-the-art results.

Related papers

• Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging [75.93960998357812]
  Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their capabilities across different tasks and domains. Current model merging techniques focus on merging all available models simultaneously, with weight matrices-based methods being the predominant approaches. We propose a training-free projection-based continual merging method that processes models sequentially.
  arXiv  Detail & Related papers  (2025-01-16T13:17:24Z)
• Recursive Learning of Asymptotic Variational Objectives [49.69399307452126]
  General state-space models (SSMs) are widely used in statistical machine learning and are among the most classical generative models for sequential time-series data. Online sequential IWAE (OSIWAE) allows for online learning of both model parameters and a Markovian recognition model for inferring latent states. This approach is more theoretically well-founded than recently proposed online variational SMC methods.
  arXiv  Detail & Related papers  (2024-11-04T16:12:37Z)
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning [113.89327264634984]
  Few-shot class-incremental learning (FSCIL) confronts the challenge of integrating new classes into a model with minimal training samples. Traditional methods widely adopt static adaptation relying on a fixed parameter space to learn from data that arrive sequentially. We propose a dual selective SSM projector that dynamically adjusts the projection parameters based on the intermediate features for dynamic adaptation.
  arXiv  Detail & Related papers  (2024-07-08T17:09:39Z)
• Dynamic Feature Learning and Matching for Class-Incremental Learning [20.432575325147894]
  Class-incremental learning (CIL) has emerged as a means to learn new classes without catastrophic forgetting of previous classes. We propose the Dynamic Feature Learning and Matching (DFLM) model in this paper. Our proposed model achieves significant performance improvements over existing methods.
  arXiv  Detail & Related papers  (2024-05-14T12:17:19Z)
• Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters [65.15700861265432]
  We present a parameter-efficient continual learning framework to alleviate long-term forgetting in incremental learning with vision-language models. Our approach involves the dynamic expansion of a pre-trained CLIP model, through the integration of Mixture-of-Experts (MoE) adapters. To preserve the zero-shot recognition capability of vision-language models, we introduce a Distribution Discriminative Auto-Selector.
  arXiv  Detail & Related papers  (2024-03-18T08:00:23Z)
• Learning an evolved mixture model for task-free continual learning [11.540150938141034]
  We address the Task-Free Continual Learning (TFCL) in which a model is trained on non-stationary data streams with no explicit task information. We introduce two simple dropout mechanisms to selectively remove stored examples in order to avoid memory overload.
  arXiv  Detail & Related papers  (2022-07-11T16:01:27Z)
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [137.39196753245105]
  We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization. We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
  arXiv  Detail & Related papers  (2020-10-26T03:20:42Z)

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.