# Probing Representation Forgetting in Supervised and Unsupervised Continual Learning

arXiv: https://arxiv.org/abs/2203.13381 · HTML: https://mlsanity.com/paper/2203.13381/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 52 references that are in the map.
- First posted on arXiv 24 Mar 2022.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Memory Aware Synapses: Learning what (not) to forget](https://mlsanity.com/paper/1711.09601/) (2017)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [Expert Gate: Lifelong Learning with a Network of Experts](https://mlsanity.com/paper/1611.06194/) (2016)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics](https://mlsanity.com/paper/2007.07400/) (2020)
- [Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning](https://mlsanity.com/paper/2103.13885/) (2021)
- [Incremental Learning Through Deep Adaptation](https://mlsanity.com/paper/1705.04228/) (2017)
- [Toward Understanding Catastrophic Forgetting in Continual Learning](https://mlsanity.com/paper/1908.01091/) (2019)
- [Task Agnostic Continual Learning via Meta Learning](https://mlsanity.com/paper/1906.05201/) (2019)
- [Continual Learning Through Synaptic Intelligence](https://mlsanity.com/paper/1703.04200/) (2017)
- [Building a Regular Decision Boundary with Deep Networks](https://mlsanity.com/paper/1703.01775/) (2017)

## Built on by (most cited first, 30 of 76)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Continual Pre-Training of Large Language Models: How to (re)warm your model?](https://mlsanity.com/paper/2308.04014/) (2023)
- [Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks](https://mlsanity.com/paper/2312.06795/) (2023)
- [Reliability of CKA as a Similarity Measure in Deep Learning](https://mlsanity.com/paper/2210.16156/) (2022)
- [Continual Pre-Training Mitigates Forgetting in Language and Vision](https://mlsanity.com/paper/2205.09357/) (2022)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning](https://mlsanity.com/paper/2303.13199/) (2023)
- [Recent Advances of Foundation Language Models-based Continual Learning: A Survey](https://mlsanity.com/paper/2405.18653/) (2024)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Grow and Merge: A Unified Framework for Continuous Categories Discovery](https://mlsanity.com/paper/2210.04174/) (2022)
- [A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm](https://mlsanity.com/paper/2310.12244/) (2023)
- [MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction](https://mlsanity.com/paper/2308.08741/) (2023)
- [A Comprehensive Empirical Evaluation on Online Continual Learning](https://mlsanity.com/paper/2308.10328/) (2023)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2303.09447/) (2023)
- [Investigating Forgetting in Pre-Trained Representations Through Continual Learning](https://mlsanity.com/paper/2305.05968/) (2023)
- [A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application](https://mlsanity.com/paper/2310.14277/) (2023)
- [Challenging Common Assumptions about Catastrophic Forgetting](https://mlsanity.com/paper/2207.04543/) (2022)
- [Consistency is the key to further mitigating catastrophic forgetting in continual learning](https://mlsanity.com/paper/2207.04998/) (2022)
- [Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting](https://mlsanity.com/paper/2304.00933/) (2023)
- [Guiding The Last Layer in Federated Learning with Pre-Trained Models](https://mlsanity.com/paper/2306.03937/) (2023)
- [Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models](https://mlsanity.com/paper/2312.07887/) (2023)
- [Accelerating Heterogeneous Federated Learning with Closed-form Classifiers](https://mlsanity.com/paper/2406.01116/) (2024)
- [Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning](https://mlsanity.com/paper/2304.05260/) (2023)
- [Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?](https://mlsanity.com/paper/2402.15414/) (2024)
- [Alleviating Representational Shift for Continual Fine-tuning](https://mlsanity.com/paper/2204.10535/) (2022)
- [Regularizing with Pseudo-Negatives for Continual Self-Supervised Learning](https://mlsanity.com/paper/2306.05101/) (2023)
- [Integrating Present and Past in Unsupervised Continual Learning](https://mlsanity.com/paper/2404.19132/) (2024)
- [Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications](https://mlsanity.com/paper/2410.09218/) (2024)

## Abstract (arXiv)

Continual Learning 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.