Formalizing the Generalization-Forgetting Trade-Off in Continual Learning

R. Krishnan; Prasanna Balaprakash

Formalizing the Generalization-Forgetting Trade-Off in Continual Learning

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

We formulate the continual learning 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 increased catastrophic forgetting. We show theoretically and experimentally 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 we empirically demonstrate that BCL is comparable to or better than the state of the art.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Publisher	Neural information processing systems foundation
Pages	17284-17297
Number of pages	14
ISBN (Electronic)	9781713845393
State	Published - 2021
Externally published	Yes
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: Dec 6 2021 → Dec 14 2021

Publication series

Name	Advances in Neural Information Processing Systems
Volume	21
ISSN (Print)	1049-5258

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	12/6/21 → 12/14/21

Funding

This work was supported by the U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research, under Contract DE-AC02-06CH11357 and by a DOE Early Career Research Program award. We are grateful for the computing resources from the Joint Laboratory for System Evaluation and Leadership Computing Facility at Argonne. We also are grateful to Dr. Vignesh Narayanan, assistant professor, University of South Carolina, and Dr. Marieme Ngom, Dr. Sami Khairy -postdoctoral appointees, Argonne National Laboratory, for their insights.

Cite this

Krishnan, R., & Balaprakash, P. (2021). Formalizing the Generalization-Forgetting Trade-Off in Continual Learning. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 17284-17297). (Advances in Neural Information Processing Systems; Vol. 21). Neural information processing systems foundation.

Krishnan, R. ; Balaprakash, Prasanna. / Formalizing the Generalization-Forgetting Trade-Off in Continual Learning. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. pp. 17284-17297 (Advances in Neural Information Processing Systems).

@inproceedings{6ee995de59d74c8f9b7cf7cce8aa5cc9,

title = "Formalizing the Generalization-Forgetting Trade-Off in Continual Learning",

abstract = "We formulate the continual learning 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 increased catastrophic forgetting. We show theoretically and experimentally 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 we empirically demonstrate that BCL is comparable to or better than the state of the art.",

author = "R. Krishnan and Prasanna Balaprakash",

note = "Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",

year = "2021",

language = "English",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "17284--17297",

editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, {Percy S.} and {Wortman Vaughan}, Jenn",

booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",

}

Krishnan, R & Balaprakash, P 2021, Formalizing the Generalization-Forgetting Trade-Off in Continual Learning. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 21, Neural information processing systems foundation, pp. 17284-17297, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 12/6/21.

Formalizing the Generalization-Forgetting Trade-Off in Continual Learning. / Krishnan, R.; Balaprakash, Prasanna.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. p. 17284-17297 (Advances in Neural Information Processing Systems; Vol. 21).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Formalizing the Generalization-Forgetting Trade-Off in Continual Learning

AU - Krishnan, R.

AU - Balaprakash, Prasanna

PY - 2021

Y1 - 2021

N2 - We formulate the continual learning 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 increased catastrophic forgetting. We show theoretically and experimentally 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 we empirically demonstrate that BCL is comparable to or better than the state of the art.

AB - We formulate the continual learning 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 increased catastrophic forgetting. We show theoretically and experimentally 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 we empirically demonstrate that BCL is comparable to or better than the state of the art.

UR - http://www.scopus.com/inward/record.url?scp=85131853334&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85131853334

T3 - Advances in Neural Information Processing Systems

SP - 17284

EP - 17297

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

PB - Neural information processing systems foundation

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

Y2 - 6 December 2021 through 14 December 2021

ER -

Krishnan R, Balaprakash P. Formalizing the Generalization-Forgetting Trade-Off in Continual Learning. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Neural information processing systems foundation. 2021. p. 17284-17297. (Advances in Neural Information Processing Systems).

Formalizing the Generalization-Forgetting Trade-Off in Continual Learning

Abstract

Publication series

Conference

Funding

Other files and links

Fingerprint

Cite this