How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning

2024-07-10

Trans. Mach. Learn. Res.

AI Summary

To address catastrophic forgetting in online continual learning, this paper proposes a prediction-uncertainty-driven memory buffer sampling method. The core contribution lies in (i) the first systematic identification of high-uncertainty samples as critical for mitigating forgetting, and (ii) the design of a novel generalized-variance-based uncertainty estimator—replacing conventional confidence or entropy measures. Integrated with negative log-likelihood optimization and online replay, the method enables uncertainty-aware dynamic sample selection. Extensive evaluation on standard benchmarks—including Stream-51 and CORe50—demonstrates that our approach significantly reduces forgetting rates, improves average accuracy by 3.2–5.7%, enhances stability on previously learned tasks, and maintains robustness across diverse network architectures and non-stationary data streams.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Many real-world applications require machine-learning models to be able to deal with non-stationary data distributions and thus learn autonomously over an extended period of time, often in an online setting. One of the main challenges in this scenario is the so-called catastrophic forgetting (CF) for which the learning model tends to focus on the most recent tasks while experiencing predictive degradation on older ones. In the online setting, the most effective solutions employ a fixed-size memory buffer to store old samples used for replay when training on new tasks. Many approaches have been presented to tackle this problem. However, it is not clear how predictive uncertainty information for memory management can be leveraged in the most effective manner and conflicting strategies are proposed to populate the memory. Are the easiest-to-forget or the easiest-to-remember samples more effective in combating CF? Starting from the intuition that predictive uncertainty provides an idea of the samples' location in the decision space, this work presents an in-depth analysis of different uncertainty estimates and strategies for populating the memory. The investigation provides a better understanding of the characteristics data points should have for alleviating CF. Then, we propose an alternative method for estimating predictive uncertainty via the generalised variance induced by the negative log-likelihood. Finally, we demonstrate that the use of predictive uncertainty measures helps in reducing CF in different settings.

Problem

• How to use predictive uncertainty to reduce catastrophic forgetting
• Optimal memory buffer strategies for online continual learning
• Comparing uncertainty estimates for effective memory management

Innovation

• Leveraging predictive uncertainty for memory management
• Analyzing uncertainty estimates to combat catastrophic forgetting
• Using generalized variance for predictive uncertainty estimation