Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

By Mohammad-Javad Davari, Nader Asadi, Sudhir P. Mudur, Rahaf Aljundi, Eugene Belilovsky. 2022

98 citations recorded by the source corpus.

Continual Learning (CL) research typically focuses on tackling the phenomenon of catastrophic forgetting in neural networks. Catastrophic forgetting is associated with an abrupt loss of knowledge previously learned by a model when the task, or more broadly the data distribution, being trained on changes. In supervised learning problems this forgetting, resulting from a change in the model's representation, is typically measured or observed by evaluating the decrease in old task performance. However, a model's representation can change without losing knowledge about prior tasks. In this work we consider the concept of representation forgetting, observed by using the difference in performance of an optimal linear classifier before and after a new task is introduced. Using this tool we revisit a number of standard continual learning benchmarks and observe that, through this lens, model representations trained without any explicit control for forgetting often experience small representation forgetting and can sometimes be comparable to methods which explicitly control for forgetting, especially in longer task sequences. We also show that representation forgetting can lead to new insights on the effect of model capacity and loss function used in continual learning. Based on our results, we show that a simple yet competitive approach is to learn representations continually with standard supervised contrastive learning while constructing prototypes of class samples when queried on old samples.11The code to reproduce our results is publicly available at: https://github.com/rezazzr/Probing-Representation-Forgetting

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Representation & Self-Supervised Learning, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

In Representation & Self-Supervised Learning

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “In particular, the benefits for downstream continual learning tend to be more apparent when pre-training with larger data size [316], [352], larger model size [352] and contrastive loss [83], [125].”
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning (2023, background): “Thus, recent works either focus on fixing the softmax classifier [4, 1, 44] or deploy nearest class mean classifiers (NCM) as an alternative [25, 5, 11].”
Scaling the Number of Tasks in Continual Learning (2022, background): “In the literature, other works used indirect methods such as linear probing to witness that forgetting in deep neural networks is maybe not as catastrophic as expected Fini et al. [2022], Davari et al. [2022].”
An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning (2023, unknown): “However, Davari et al. (2022) [22] discovered that even when the model performance on previously learned tasks is preserved, the representations still suffer from signiﬁcant drift due to parameter updates.”
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning (2023, background): “Embeddings have been recognized for their resilience against information loss [66, 11].”