paper-with-me

홈 › Papers

Understanding Continual Learning Settings with Data Distribution Drift Analysis

2021-04-04 · Timothée Lesort, Massimo Caccia, Irina Rish

Classical machine learning algorithms often assume that the data are drawn i.i.d. from a stationary probability distribution. Recently, continual learning emerged as a rapidly growing area of machine learning where this assumption is relaxed, i.e. where the data distribution is non-stationary and changes over time. This paper represents the state of data distribution by a context variable $c$. A drift in $c$ leads to a data distribution drift. A context drift may change the target distribution, the input distribution, or both. Moreover, distribution drifts might be abrupt or gradual. In continual learning, context drifts may interfere with the learning process and erase previously learned knowledge; thus, continual learning algorithms must include specialized mechanisms to deal with such drifts. In this paper, we aim to identify and categorize different types of context drifts and potential assumptions about them, to better characterize various continual-learning scenarios. Moreover, we propose to use the distribution drift framework to provide more precise definitions of several terms commonly used in the continual learning field.

📄 PDF Abstract BibTeX arXiv:2104.01678

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningContinual Learning

Similar Papers 제목 키워드 기반

Continuum: Simple Management of Complex Continual Learning Scenarios

2021-02-11 · Arthur Douillard, Timothée Lesort

Continual learning is a machine learning sub-field specialized in settings with non-iid data. Hence, the training data distribution is not static and drifts through time. Those drifts might cause interferences in the tra…

Continual LearningManagement

Efficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring

2026-08-28 · Sjoerd van Straten, Marwan Hassani arxiv

Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online co…

Continual Learning

Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset

2024-11-06 · Alexandre Galashov, Michalis K. Titsias, András György, Clare Lyle 외

Neural networks are traditionally trained under the assumption that data come from a stationary distribution. However, settings which violate this assumption are becoming more popular; examples include supervised learnin…

Continual LearningMulti-Armed Banditsreinforcement-learningReinforcement Learning

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

2024-07-11 · Alex Gomez-Villa, Dipam Goswami, Kai Wang, Andrew D. Bagdanov 외

Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small first task presents a significant challenge for continual representation learning. Prototype-based approaches, when…

class-incremental learningClass Incremental LearningContinual LearningExemplar-Free+2

Continual Learning in Deep Networks: an Analysis of the Last Layer

2021-06-03 · Timothée Lesort, Thomas George, Irina Rish

We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause catastrophic forgetting in the output l…

Continual Learning