Composing continual learning mechanisms lifts long-horizon retention from 1.2% to 34.9%

mdredze · x · 2026-09-09

The paper "Continual Learning Mechanisms Compose for Long-Horizon Memorization" tackles long-horizon memorization: learning many tasks sequentially, catastrophic forgetting in sequential fine-tuning loses about 98.8% of knowledge after 100 tasks.

The authors combine four existing mechanisms — generative replay, self-distillation, weight regularization, and merged LoRA — each preserving complementary forms of prior information.

Together they reach 34.9% final retention, with replay + merged LoRA showing super-additive benefits. The finding: composing existing mechanisms is a very strong yet simple recipe.

Related event: JHU Research: Composing Continual Learning Mechanisms Boosts Long-Horizon Memory(4 posts)→

Original post →

More from Research

Research channel →