Formalizing the Generalization-Forgetting Trade-off in Continual Learning

By Krishnan Raghavan, Prasanna Balaprakash. 2021

41 citations recorded by the source corpus.

We formulate the continual learning (CL) problem via dynamic programming and model the trade-off between catastrophic forgetting and generalization as a two-player sequential game. In this approach, player 1 maximizes the cost due to lack of generalization whereas player 2 minimizes the cost due to catastrophic forgetting. We show theoretically that a balance point between the two players exists for each task and that this point is stable (once the balance is achieved, the two players stay at the balance point). Next, we introduce balanced continual learning (BCL), which is designed to attain balance between generalization and forgetting and empirically demonstrate that BCL is comparable to or better than the state of the art.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Task-Free Continual Learning via Online Discrepancy Distance Learning (2022, neutral): “Recent attempts have provided the theoretical analysis for CL from different perspectives including the risk bound [46, 51], NP-hard problem [17], Teacher-Student framework [23, 58] and game theory [37].”
Continual Variational Autoencoder Learning via Online Cooperative Memorization (2022, background): “In recent years, some studies have provided the theoretical analysis for continual learning from different perspectives including the NP-hard problem [27], risk bound [58,64], Teacher-Student framework [34,57] and game theory [43].”
How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition (2022, background): “Similarly, Raghavan and Balaprakash (2021) found theoretically that the balance between generalization and forgetting, viewed as a two-player zero-sum game, is stable and corresponds to a saddle point, and developed an algorithm that searches for this saddle point by playing the two-player game.”