Online Continual Learning with Dynamic Label Hierarchies

TL;DR

This paper introduces DHOCL, a new online continual learning setting with evolving hierarchical labels, and proposes HALO, a method that adapts to hierarchical changes to improve learning stability and accuracy.

Contribution

The paper defines the DHOCL problem, identifies key challenges with hierarchical label evolution, and proposes HALO, a novel approach with organized prototypes for better hierarchical learning.

Findings

HALO outperforms existing methods on multiple benchmarks.

It improves hierarchical accuracy and reduces mistake severity.

HALO enhances continual performance stability.

Abstract

Online Continual Learning (OCL) aims to learn from endless non\text{-}stationary data streams, yet most existing methods assume a flat label space and overlook the hierarchical organization of real\text{-}world concepts that evolves both horizontally (sibling classes) and vertically (coarse or fine categories). To better reflect this context, we introduce a new problem setting, DHOCL (Online Continual Learning from Dynamic Hierarchies), where taxonomies evolve across granularities and each sample provides supervision at a single hierarchical level. In this setting, we find two fundamental issues: (i) partial supervision under mixed granularities provides only point-wise signals over an evolving path-wise hierarchy, which constrains plasticity and undermines cross-level semantic consistency, and (ii) the dynamically evolving hierarchies induce granularity-dependent interference, destabilizing popular replay and regularization mechanisms and thereby exacerbating catastrophic forgetting. To tackle these issues, we propose HALO (Hierarchical Adaptive Learning with Organized Prototypes), which adaptively combines complementary classification heads, regularized by organized learnable hierarchical prototypes, enabling rapid adaptation, hierarchical consistency, and structured knowledge consolidation as the taxonomy evolves. Extensive experiments on multiple benchmarks demonstrate that HALO consistently outperforms existing methods across hierarchical accuracy, mistake severity, and continual performance.