Ex-Model: Continual Learning from a Stream of Trained Models

TL;DR

This paper introduces Ex-Model Continual Learning, a new paradigm where agents learn from trained models rather than raw data, enhancing efficiency, privacy, and scalability in non-stationary environments.

Contribution

The paper formalizes the ex-model continual learning paradigm, proposes three algorithms, and provides an extensive empirical evaluation across multiple datasets and scenarios.

Findings

Ex-Model algorithms perform well across diverse scenarios.

Learning from trained models improves privacy and efficiency.

The paradigm offers new research directions in continual learning.

Abstract

Learning continually from non-stationary data streams is a challenging research topic of growing popularity in the last few years. Being able to learn, adapt, and generalize continually in an efficient, effective, and scalable way is fundamental for a sustainable development of Artificial Intelligent systems. However, an agent-centric view of continual learning requires learning directly from raw data, which limits the interaction between independent agents, the efficiency, and the privacy of current approaches. Instead, we argue that continual learning systems should exploit the availability of compressed information in the form of trained models. In this paper, we introduce and formalize a new paradigm named "Ex-Model Continual Learning" (ExML), where an agent learns from a sequence of previously trained models instead of raw data. We further contribute with three ex-model continual learning algorithms and an empirical setting comprising three datasets (MNIST, CIFAR-10 and CORe50), and eight scenarios, where the proposed algorithms are extensively tested. Finally, we highlight the peculiarities of the ex-model paradigm and we point out interesting future research directions.