# Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay

arXiv: https://arxiv.org/abs/2410.07110 · HTML: https://mlsanity.com/paper/2410.07110/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 39 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Benign Overfitting in Linear Regression](https://mlsanity.com/paper/1906.11300/) (2019)
- [Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics](https://mlsanity.com/paper/2009.10795/) (2020)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Using Hindsight to Anchor Past Knowledge in Continual Learning](https://mlsanity.com/paper/2002.08165/) (2020)
- [Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning](https://mlsanity.com/paper/2103.13885/) (2021)
- [Class-Incremental Continual Learning into the eXtended DER-verse](https://mlsanity.com/paper/2201.00766/) (2022)
- [DataPerf: Benchmarks for Data-Centric AI Development](https://mlsanity.com/paper/2207.10062/) (2022)
- [Distributional Robustness Loss for Long-tail Learning](https://mlsanity.com/paper/2104.03066/) (2021)
- [Rehearsal revealed: The limits and merits of revisiting samples in continual learning](https://mlsanity.com/paper/2104.07446/) (2021)
- [On the Stability-Plasticity Dilemma of Class-Incremental Learning](https://mlsanity.com/paper/2304.01663/) (2023)
- [PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning](https://mlsanity.com/paper/2304.04408/) (2023)
- [Exploring Example Influence in Continual Learning](https://mlsanity.com/paper/2209.12241/) (2022)
- [Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning](https://mlsanity.com/paper/2303.09483/) (2023)
- [On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning](https://mlsanity.com/paper/2210.06443/) (2022)
- [How Re-sampling Helps for Long-Tail Learning?](https://mlsanity.com/paper/2310.18236/) (2023)
- [Towards an Understanding of Benign Overfitting in Neural Networks](https://mlsanity.com/paper/2106.03212/) (2021)
- [A Data-Centric Approach for Training Deep Neural Networks with Less Data](https://mlsanity.com/paper/2110.03613/) (2021)
- [Regularizing Second-Order Influences for Continual Learning](https://mlsanity.com/paper/2304.10177/) (2023)

## Abstract (arXiv)

Machine learning models often suffer from catastrophic forgetting of previously learned knowledge when learning new classes. Various methods have been proposed to mitigate this issue. However, rehearsal-based learning, which retains samples from previous classes, typically achieves good performance but tends to memorize specific instances, struggling with Out-of-Distribution (OOD) generalization. This often leads to high forgetting rates and poor generalization. Surprisingly, the OOD generalization capabilities of these methods have been largely unexplored. In this paper, we highlight this issue and propose a simple yet effective strategy inspired by contrastive learning and data-centric principles to address it. We introduce Adaptive Contrastive Replay (ACR), a method that employs dual optimization to simultaneously train both the encoder and the classifier. ACR adaptively populates the replay buffer with misclassified samples while ensuring a balanced representation of classes and tasks. By refining the decision boundary in this way, ACR achieves a balance between stability and plasticity. Our method significantly outperforms previous approaches in terms of OOD generalization, achieving an improvement of 13.41% on Split CIFAR-100, 9.91% on Split Mini-ImageNet, and 5.98% on Split Tiny-ImageNet.