Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams

Matthias De Lange, Tinne Tuytelaars

Keywords: continual learning, prototypical learning, online learning, incremental learning, deep learning, representation learning, catastrophic forgetting, concept drift

Abstract: Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streams of data proves a challenging endeavor as they rapidly become outdated, caused by an ever-changing parameter space in the learning process. Additionally, continual learning assumes a non-stationary nature of the data stream, typically resulting in catastrophic forgetting of previous knowledge. As a first, we introduce a system addressing both problems, where prototypes evolve continually in a shared latent space, enabling learning and prediction at any point in time. In contrast to the major body of work in continual learning, data streams are processed in an online fashion, without additional task-information, and an efficient memory scheme provides robustness to imbalanced data streams. Besides nearest neighbor based prediction, learning is facilitated by a novel objective function, encouraging cluster density about the class prototype and increased inter-class variance. Furthermore, the latent space quality is elevated by pseudo-prototypes in each batch, constituted by replay of exemplars from memory. We generalize the existing paradigms in continual learning to incorporate data incremental learning from data streams by formalizing a two-agent learner-evaluator framework, and obtain state-of-the-art performance by a significant margin on eight benchmarks, including three highly imbalanced data streams.

One-sentence Summary: Continual Prototype Evolution (CoPE) establishes online adaptation of class-representative prototypes in non-stationary data streams, exploiting latent space representations in a novel loss to enhance the state-of-the-art in continual learning.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=95swpzM9Qt