Explainable Lifelong Stream Learning Based on "Glocal" Pairwise Fusion

TL;DR

The paper introduces ExLL, an explainable lifelong learning model for real-time on-device applications that learns from streaming data, maintains interpretability, and outperforms existing algorithms in accuracy across various datasets.

Contribution

ExLL is a novel lifelong learning framework combining self-organizing prototypes, explainability, and pairwise fusion for improved accuracy and interpretability in resource-constrained environments.

Findings

ExLL outperforms contemporary algorithms in accuracy across multiple datasets.

ExLL maintains interpretability through rule-based explanations.

ExLL demonstrates scalability and efficiency in real-time streaming scenarios.

Abstract

Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. Such devices have limited processing and memory storage capabilities, whereas continual learning acquires data over a long period of time. By necessity, lifelong learning algorithms have to be able to operate under such constraints while delivering good performance. This study presents the Explainable Lifelong Learning (ExLL) model, which incorporates several important traits: 1) learning to learn, in a single pass, from streaming data with scarce examples and resources; 2) a self-organizing prototype-based architecture that expands as needed and clusters streaming data into separable groups by similarity and preserves data against catastrophic forgetting; 3) an interpretable architecture to convert the clusters into explainable IF-THEN rules as well as to justify model predictions in terms of what is similar and dissimilar to the inference; and 4) inferences at the global and local level using a pairwise decision fusion process to enhance the accuracy of the inference, hence ``Glocal Pairwise Fusion.'' We compare ExLL against contemporary online learning algorithms for image recognition, using OpenLoris, F-SIOL-310, and Places datasets to evaluate several continual learning scenarios for video streams, low-sample learning, ability to scale, and imbalanced data streams. The algorithms are evaluated for their performance in accuracy, number of parameters, and experiment runtime requirements. ExLL outperforms all algorithms for accuracy in the majority of the tested scenarios.