Continual Learning with Guarantees via Weight Interval Constraints

By Maciej Wołczyk, Karol J. Piczak, Bartosz W'ojcik, Lukasz Pustelnik, Pawel Morawiecki, Jacek Tabor, Tomasz Trzcinski, Przemyslaw Spurek. 2022

13 citations recorded by the source corpus.

We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus on training neural networks efficiently from a stream of data, while reducing the negative impact of catastrophic forgetting, yet they do not provide any firm guarantees that network performance will not deteriorate uncontrollably over time. In this work, we show how to put bounds on forgetting by reformulating continual learning of a model as a continual contraction of its parameter space. To that end, we propose Hyperrectangle Training, a new training methodology where each task is represented by a hyperrectangle in the parameter space, fully contained in the hyperrectangles of the previous tasks. This formulation reduces the NP-hard CL problem back to polynomial time while providing full resilience against forgetting. We validate our claim by developing InterContiNet (Interval Continual Learning) algorithm which leverages interval arithmetic to effectively model parameter regions as hyperrectangles. Through experimental results, we show that our approach performs well in a continual learning setup without storing data from previous tasks.

Subfields: Meta & Continual Learning

How researchers see this paper

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

In Meta & Continual Learning

  1. Xingxing Zhang
  2. Liyuan Wang
  3. Hang Su
  4. Jun Zhu
  5. Simone Scardapane
  6. Valerio Marsocci
  7. Liyuan Wang
  8. Hongwei Yan

Citations in the corpus