Understanding Continual Learning Settings with Data Distribution Drift Analysis

Abstract

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.

References in corpus (25)

• Distilling the Knowledge in a Neural Network
• Overcoming catastrophic forgetting in neural networks
• Deep Visual Domain Adaptation: A Survey
• Continual Learning Through Synaptic Intelligence
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Efficient Lifelong Learning with A-GEM
• Three scenarios for continual learning
• A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
• Invariant Risk Minimization
• Progress & Compress: A scalable framework for continual learning
• Out-of-Distribution Generalization via Risk Extrapolation (REx)
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• Online Learning: A Comprehensive Survey
• Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
• Dive into Deep Learning
• Selfless Sequential Learning
• Task Agnostic Continual Learning via Meta Learning
• Online Learned Continual Compression with Adaptive Quantization Modules
• DisCoRL: Continual Reinforcement Learning via Policy Distillation
• Optimal Continual Learning has Perfect Memory and is NP-hard
• Invariant Risk Minimization Games
• Meta Continual Learning
• Regularization Shortcomings for Continual Learning
• Continuum: Simple Management of Complex Continual Learning Scenarios
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes

Cited by in corpus (3)

• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
• Continual Learning in Deep Networks: an Analysis of the Last Layer