Insights from the Future for Continual Learning

By Arthur Douillard, Eduardo Valle, Charles Ollion, Thomas Robert, Matthieu Cord. 2020

12 citations recorded by the source corpus.

Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting. In this work, we propose prescient continual learning, a novel experimental setting, to incorporate existing information about the classes, prior to any training data. Usually, each task in a traditional continual learning setting evaluates the model on present and past classes, the latter with a limited number of training samples. Our setting adds future classes, with no training samples at all. We introduce Ghost Model, a representation-learning-based model for continual learning using ideas from zero-shot learning. A generative model of the representation space in concert with a careful adjustment of the losses allows us to exploit insights from future classes to constraint the spatial arrangement of the past and current classes. Quantitative results on the AwA2 and aP&Y datasets and detailed visualizations showcase the interest of this new setting and the method we propose to address it.1

Subfields: Education

How researchers see this paper

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

Citations in the corpus

PLOP: Learning without Forgetting for Continual Semantic Segmentation (2020, background): “Further works should investigate how to exploit the already present future information with Zeroshot [41, 40] as already done in semantic segmentation [35, 5] and explored for continual classification [71, 18].”
Continuum: Simple Management of Complex Continual Learning Scenarios (2021, background): “However, recent works challenge some of those common assumptions such as ﬁxed label [6, 2], uncorrelated data stream [5, 42], labeled new data [16], or even no meta-data about tasks and unavailability of information about the future [11].”
Continual Learning with Foundation Models: An Empirical Study of Latent Replay (2022, background): “On the other hand, in line with Douillard et al. (2020b), we found that getting access to some information about the downstream tasks a priori can help to improve our predictions about downstream performance.”
Understanding Continual Learning Settings with Data Distribution Drift Analysis (2021, background): “Indeed, in a wide part of continual learning literature, incremental learning is associated with the “disjoint class scenarios” ( virtual concept drifts ) (Belouadah and Popescu, 2018; Wu et al., 2019; Douillard et al., 2020b).”