Abstraction Augmented Continual Learning

Replace standard supervised fine-tuning loss with a dual-objective loss that jointly optimizes over both concrete instances and their abstract representations (entity-masked versions), eliminating need for replay buffers and improving cumulative accuracy by 2-5% on continual learning benchmarks. Use when streaming data contains latent relational structure, catastrophic forgetting is problematic, and you want to maintain structural understanding without memory overhead.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 075f0720c4

Frequently asked questions

npx get-skill add adu2021/abstraction-augmented-continual-learning