Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning

• URL: http://arxiv.org/abs/2412.00776v3
• Date: Sun, 09 Mar 2025 02:19:22 GMT
• Title: Learning Mamba as a Continual Learner: Meta-learning Selective State Space Models for Efficient Continual Learning
• Authors: Chongyang Zhao, Dong Gong,
• Abstract summary: Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples.<n>We focus on meta-learning sequence-prediction-based continual learners without retaining all past representations.<n>Given Mamba's strong sequence modeling performance and attention-free nature, we explore a key question: Can attention-free models like Mamba perform well on meta-continual learning.
• Score: 12.697915176594314
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) aims to efficiently learn from a non-stationary data stream, without storing or recomputing all seen samples. CL enables prediction on new tasks by incorporating sequential training samples. Building on this connection between CL and sequential modeling, meta-continual learning (MCL) aims to meta-learn an efficient continual learner as a sequence prediction model, with advanced sequence models like Transformers being natural choices. However, despite decent performance, Transformers rely on a linearly growing cache to store all past representations, conflicting with CL's objective of not storing all seen samples and limiting efficiency. In this paper, we focus on meta-learning sequence-prediction-based continual learners without retaining all past representations. While attention-free models with fixed-size hidden states (e.g., Linear Transformers) align with CL's essential goal and efficiency needs, they have shown limited effectiveness in MCL in previous literature. Given Mamba's strong sequence modeling performance and attention-free nature, we explore a key question: Can attention-free models like Mamba perform well on MCL? By formulating Mamba and the SSM for MCL tasks, we propose MambaCL, a meta-learned continual learner. To enhance MambaCL's training, we introduce selectivity regularization, leveraging the connection between Mamba and Transformers to guide its behavior over sequences. Furthermore, we study how Mamba and other models perform across various MCL scenarios through extensive and well-designed experiments. Our results highlight the promising performance and strong generalization of Mamba and attention-free models in MCL, demonstrating its potential for efficient continual learning and adaptation.

Related papers

• Repetitive Contrastive Learning Enhances Mamba's Selectivity in Time Series Prediction [1.6590638305972631]
  We introduce Repetitive Contrastive Learning (RCL), a token-level contrastive pretraining framework aimed at enhancing Mamba's selective capabilities. RCL pretrains a single Mamba block to strengthen its selective abilities and then transfers these pretrained parameters to initialize Mamba blocks in various backbone models. Extensive experiments show that RCL consistently boosts the performance of backbone models, surpassing existing methods and achieving state-of-the-art results.
  arXiv  Detail & Related papers  (2025-04-12T11:57:27Z)
• Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization [72.81319836138347]
  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.
  arXiv  Detail & Related papers  (2024-12-24T05:25:21Z)
• Mamba-CL: Optimizing Selective State Space Model in Null Space for Continual Learning [54.19222454702032]
  Continual Learning aims to equip AI models with the ability to learn a sequence of tasks over time, without forgetting previously learned knowledge. State Space Models (SSMs) have achieved notable success in computer vision. We introduce Mamba-CL, a framework that continuously fine-tunes the core SSMs of the large-scale Mamba foundation model.
  arXiv  Detail & Related papers  (2024-11-23T06:36:16Z)
• ReMamba: Equip Mamba with Effective Long-Sequence Modeling [50.530839868893786]
  We propose ReMamba, which enhances Mamba's ability to comprehend long contexts. ReMamba incorporates selective compression and adaptation techniques within a two-stage re-forward process.
  arXiv  Detail & Related papers  (2024-08-28T02:47:27Z)
• 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)
• Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks [25.092302463435523]
  State-space models (SSMs) have been proposed as alternatives to Transformer networks in language modeling. In this study, we evaluate the ICL performance of SSMs, focusing on Mamba, against Transformer models across various tasks.
  arXiv  Detail & Related papers  (2024-02-06T18:56:35Z)
• Is Mamba Capable of In-Context Learning? [63.682741783013306]
  State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL) This work provides empirical evidence that Mamba, a newly proposed state space model, has similar ICL capabilities.
  arXiv  Detail & Related papers  (2024-02-05T16:39:12Z)
• Recasting Continual Learning as Sequence Modeling [44.437160324905726]
  We propose to formulate continual learning as a sequence modeling problem. By adopting the meta-continual learning (MCL) framework, we can train the sequence model at the meta-level. Our experiments on seven benchmarks, covering both classification and regression, show that sequence models can be an attractive solution for general MCL.
  arXiv  Detail & Related papers  (2023-10-18T13:26:52Z)
• Pre-training Language Model as a Multi-perspective Course Learner [103.17674402415582]
  This study proposes a multi-perspective course learning (MCL) method for sample-efficient pre-training. In this study, three self-supervision courses are designed to alleviate inherent flaws of "tug-of-war" dynamics. Our method significantly improves ELECTRA's average performance by 2.8% and 3.2% absolute points respectively on GLUE and SQuAD 2.0 benchmarks.
  arXiv  Detail & Related papers  (2023-05-06T09:02:10Z)
• CLIPood: Generalizing CLIP to Out-of-Distributions [73.86353105017076]
  Contrastive language-image pre-training (CLIP) models have shown impressive zero-shot ability, but the further adaptation of CLIP on downstream tasks undesirably degrades OOD performances. We propose CLIPood, a fine-tuning method that can adapt CLIP models to OOD situations where both domain shifts and open classes may occur on unseen test data. Experiments on diverse datasets with different OOD scenarios show that CLIPood consistently outperforms existing generalization techniques.
  arXiv  Detail & Related papers  (2023-02-02T04:27:54Z)

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.