A Theoretical Study on Solving Continual Learning

by   Gyuhak Kim, et al.

Continual learning (CL) learns a sequence of tasks incrementally. There are two popular CL settings, class incremental learning (CIL) and task incremental learning (TIL). A major challenge of CL is catastrophic forgetting (CF). While a number of techniques are already available to effectively overcome CF for TIL, CIL remains to be highly challenging. So far, little theoretical study has been done to provide a principled guidance on how to solve the CIL problem. This paper performs such a study. It first shows that probabilistically, the CIL problem can be decomposed into two sub-problems: Within-task Prediction (WP) and Task-id Prediction (TP). It further proves that TP is correlated with out-of-distribution (OOD) detection, which connects CIL and OOD detection. The key conclusion of this study is that regardless of whether WP and TP or OOD detection are defined explicitly or implicitly by a CIL algorithm, good WP and good TP or OOD detection are necessary and sufficient for good CIL performances. Additionally, TIL is simply WP. Based on the theoretical result, new CIL methods are also designed, which outperform strong baselines in both CIL and TIL settings by a large margin.


page 1

page 2

page 3

page 4


Open-World Continual Learning: Unifying Novelty Detection and Continual Learning

As AI agents are increasingly used in the real open world with unknowns ...

Continual Learning Based on OOD Detection and Task Masking

Existing continual learning techniques focus on either task incremental ...

Continual Feature Selection: Spurious Features in Continual Learning

Continual Learning (CL) is the research field addressing learning settin...

Learnability and Algorithm for Continual Learning

This paper studies the challenging continual learning (CL) setting of Cl...

Class-Incremental Learning based on Label Generation

Despite the great success of pre-trained language models, it is still a ...

A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials

There have been emerging a number of benchmarks and techniques for the d...

Please sign up or login with your details

Forgot password? Click here to reset