A Distinct Unsupervised Reference Model From The Environment Helps Continual Learning

TL;DR

This paper introduces OSSCL, a semi-supervised continual learning framework that effectively utilizes out-of-distribution unlabeled data by employing a reference network for general knowledge and a learner network for task-specific learning.

Contribution

It proposes a novel OSSCL setting with out-of-distribution unlabeled data and a dual-network architecture to improve continual learning performance in realistic environments.

Findings

Outperforms existing methods in semi-supervised continual learning tasks.

Effectively segregates in-distribution and out-of-distribution unlabeled data.

Demonstrates the importance of a reference network for general-purpose knowledge.

Abstract

The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised continual learning (SSCL) settings in which the unlabeled data are available, but it is only from the same distribution as the labeled data. This assumption is still not general enough for real-world applications and restricts the utilization of unsupervised data. In this work, we introduce Open-Set Semi-Supervised Continual Learning (OSSCL), a more realistic semi-supervised continual learning setting in which out-of-distribution (OoD) unlabeled samples in the environment are assumed to coexist with the in-distribution ones. Under this configuration, we present a model with two distinct parts: (i) the reference network captures general-purpose and task-agnostic knowledge in the environment by using a broad spectrum of unlabeled samples, (ii) the learner network is designed to learn task-specific representations by exploiting supervised samples. The reference model both provides a pivotal representation space and also segregates unlabeled data to exploit them more efficiently. By performing a diverse range of experiments, we show the superior performance of our model compared with other competitors and prove the effectiveness of each component of the proposed model.