# Continual Rare-Class Recognition with Emerging Novel Subclasses

## TL;DR

RaRecognize is a novel continual learning framework that effectively identifies and adapts to emerging rare subclasses in streaming data, outperforming existing methods on real-world datasets.

## Contribution

The paper introduces RaRecognize, a new method that learns a general decision boundary and recognizes both known and emerging rare subclasses in streaming data.

## Key findings

- RaRecognize outperforms state-of-the-art baselines on three real-world datasets.
- It effectively recognizes recurrent and emerging rare subclasses.
- The model size grows moderately over time, maintaining efficiency.

## Abstract

Given a labeled dataset that contains a rare (or minority) class of of-interest instances, as well as a large class of instances that are not of interest, how can we learn to recognize future of-interest instances over a continuous stream? We introduce RaRecognize, which (i) estimates a general decision boundary between the rare and the majority class, (ii) learns to recognize individual rare subclasses that exist within the training data, as well as (iii) flags instances from previously unseen rare subclasses as newly emerging. The learner in (i) is general in the sense that by construction it is dissimilar to the specialized learners in (ii), thus distinguishes minority from the majority without overly tuning to what is seen in the training data. Thanks to this generality, RaRecognize ignores all future instances that it labels as majority and recognizes the recurrent as well as emerging rare subclasses only. This saves effort at test time as well as ensures that the model size grows moderately over time as it only maintains specialized minority learners. Through extensive experiments, we show that RaRecognize outperforms state-of-the art baselines on three real-world datasets that contain corporate-risk and disaster documents as rare classes.