PVBF: A Framework for Mitigating Parameter Variation Imbalance in Online Continual Learning
Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training. However, these methods face challenges of prediction bias, stemming from deviations in parameter update directions during task transitions. This paper identifies parameter variation imbalance as a critical factor contributing to prediction bias in ER-based OCL. Specifically, using the proposed parameter variation evaluation method, we highlight two types of imbalance: correlation-induced imbalance, where certain parameters are disproportionately updated across tasks, and layer-wise imbalance, where output layer parameters update faster than those in preceding layers. To mitigate the above imbalances, we propose the Parameter Variation Balancing Framework (PVBF), which incorporates: 1) a novel method to compute parameter correlations with previous tasks based on parameter variations, 2) an encourage-and-consolidate (E&C) method utilizing parameter correlations to perform gradient adjustments across all parameters during training, 3) a dual-layer copy weights with reinit (D-CWR) strategy to slowly update output layer parameters for frequently occuring sample categories. Experiments on short and long task sequences demonstrate that PVBF significantly reduces prediction bias and improves OCL performance, achieving up to 47\% higher accuracy compared to existing ER-based methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Mitigating Sample-Level Imbalance via Probabilistic Separation for Adaptive Multimodal Fusion
Multimodal learning faces modality imbalance, where dominant modalities suppress weaker ones due to inconsistent convergence rates. Existing static or heuristic methods overlook sample-level variations in prediction bias…
Mitigating Data Imbalance in Automated Speaking Assessment
Automated Speaking Assessment (ASA) plays a crucial role in evaluating second-language (L2) learners proficiency. However, ASA models often suffer from class imbalance, leading to biased predictions. To address this, we …
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially r…
On how to avoid exacerbating spurious correlations when models are overparameterized
Overparameterized models fail to generalize well in the presence of data imbalance even when combined with traditional techniques for mitigating imbalances. This paper focuses on imbalanced classification datasets, in wh…
Generalization Boundsimbalanced classificationOn the Data-Driven Modeling of Price-Responsive Flexible Loads: Formulation and Algorithm
The flexible loads in power systems, such as interruptible and transferable loads, are critical flexibility resources for mitigating power imbalances. Despite their potential, accurate modeling of these loads is a challe…
Bayesian Optimizationparameter estimation