Continual Learning via Online Leverage Score Sampling
In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills. As such, the key challenge is to transfer and generalize the knowledge learned from one task to other tasks, avoiding forgetting and interference of previous knowledge and improving the overall performance. In this paper, within the continual learning paradigm, we introduce a method that effectively forgets the less useful data samples continuously and allows beneficial information to be kept for training of the subsequent tasks, in an online manner. The method uses statistical leverage score information to measure the importance of the data samples in every task and adopts frequent directions approach to enable a continual or life-long learning property. This effectively maintains a constant training size across all tasks. We first provide mathematical intuition for the method and then demonstrate its effectiveness in avoiding catastrophic forgetting and computational efficiency on continual learning of classification tasks when compared with the existing state-of-the-art techniques.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencyContinual LearningSimilar Papers 제목 키워드 기반
Lifelong Learning via Online Leverage Score Sampling
In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for life-long learning, effectively utilizing the previously acquired sk…
Continual LearningLifelong learningImportance Sampling for Nonlinear Models
While norm-based and leverage-score-based methods have been extensively studied for identifying "important" data points in linear models, analogous tools for nonlinear models remain significantly underdeveloped. By intro…
Outlier DetectionOptimal Sampling Designs for Multi-dimensional Streaming Time Series with Application to Power Grid Sensor Data
The Internet of Things (IoT) system generates massive high-speed temporally correlated streaming data and is often connected with online inference tasks under computational or energy constraints. Online analysis of these…
Computational EfficiencyTime SeriesTime Series AnalysisAn Efficient Conditional Score-based Filter for High Dimensional Nonlinear Filtering Problems
In many engineering and applied science domains, high-dimensional nonlinear filtering is still a challenging problem. Recent advances in score-based diffusion models offer a promising alternative for posterior sampling b…
Online Continual Learning of End-to-End Speech Recognition Models
Continual Learning, also known as Lifelong Learning, aims to continually learn from new data as it becomes available. While prior research on continual learning in automatic speech recognition has focused on the adaptati…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Continual LearningLifelong learning+3