Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning

• URL: http://arxiv.org/abs/2503.15924v1
• Date: Thu, 20 Mar 2025 08:00:41 GMT
• Title: Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning
• Authors: Peiyi Lin, Fukai Zhang, Kai Niu, Hao Fu,
• Abstract summary: Continual instruction tuning enables large language models to learn incrementally while retaining past knowledge.<n>Our framework dynamically filters incoming data, which identify and reduce redundant data across successive updates.<n>It reduces computational costs by 66.7% and improved model performance, and achieved autonomous updates.
• Score: 8.95038939248447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to learn. In domain-specific contexts, maintaining data quality and managing system constraints remain key challenges. To address these issues, we propose an automated continual instruction tuning framework that dynamically filters incoming data, which identify and reduce redundant data across successive updates. Our approach utilizes a small proxy model for efficient perplexity-based filtering, and updates the proxy to ensure that the filtering criteria remain aligned with the evolving state of the deployed model. Compared to existing static data selection methods, our framework can effectively handle incrementally acquired data and shifting distributions. Additionally, it addresses practical deployment challenges by enabling seamless model updates, supporting version rollback and incorporating automatic checkpoint evaluation. We evaluated the system in real-world medical scenarios. It reduced computational costs by 66.7% and improved model performance, and achieved autonomous updates, thus demonstrating its effectiveness for automatic continual instruction tuning.

Related papers

• Pull-Based Query Scheduling for Goal-Oriented Semantic Communication [14.787190731074322]
  This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems.<n>We introduce a grade of effectiveness (GoE) metric and integrate cumulative perspective theory (CPT) into the long-term effectiveness analysis.<n>We propose a model-based solution based on dynamic programming and model-free solutions employing state-of-the-art deep reinforcement learning (DRL) algorithms.
  arXiv  Detail & Related papers  (2025-03-09T18:51:14Z)
• 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.<n>Most existing methods rely on replay, focusing on enhancing memory retention through regularization or distillation.<n>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)
• 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.<n>We name our approach Adaptive Retention & Correction (ARC)<n>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)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• 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)
• iSAGE: An Incremental Version of SAGE for Online Explanation on Data Streams [8.49072000414555]
  iSAGE is a time- and memory-efficient incrementalization of SAGE. We show that iSAGE adheres to similar theoretical properties as SAGE.
  arXiv  Detail & Related papers  (2023-03-02T11:51:54Z)
• Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data [101.6195176510611]
  "Online" continual learning enables evaluating both information retention and online learning efficacy. In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online. We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts.
  arXiv  Detail & Related papers  (2021-08-20T06:17:20Z)
• Online Constrained Model-based Reinforcement Learning [13.362455603441552]
  Key requirement is the ability to handle continuous state and action spaces while remaining within a limited time and resource budget. We propose a model based approach that combines Gaussian Process regression and Receding Horizon Control. We test our approach on a cart pole swing-up environment and demonstrate the benefits of online learning on an autonomous racing task.
  arXiv  Detail & Related papers  (2020-04-07T15:51:34Z)
• Tracking Performance of Online Stochastic Learners [57.14673504239551]
  Online algorithms are popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches. When a constant step-size is used, these algorithms also have the ability to adapt to drifts in problem parameters, such as data or model properties, and track the optimal solution with reasonable accuracy. We establish a link between steady-state performance derived under stationarity assumptions and the tracking performance of online learners under random walk models.
  arXiv  Detail & Related papers  (2020-04-04T14:16:27Z)

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.