# Robustness-preserving Lifelong Learning via Dataset Condensation

arXiv: https://arxiv.org/abs/2303.04183 · HTML: https://mlsanity.com/paper/2303.04183/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 7 Mar 2023.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Class-incremental learning: survey and performance evaluation on image classification](https://mlsanity.com/paper/2010.15277/) (2020)
- [Coresets via Bilevel Optimization for Continual Learning and Streaming](https://mlsanity.com/paper/2006.03875/) (2020)
- [You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle](https://mlsanity.com/paper/1905.00877/) (2019)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Turning Big data into tiny data: Constant-size coresets for k-means, PCA and projective clustering](https://mlsanity.com/paper/1807.04518/) (2018)
- [Coresets for Scalable Bayesian Logistic Regression](https://mlsanity.com/paper/1605.06423/) (2016)
- [Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization](https://mlsanity.com/paper/2112.12376/) (2021)
- [Automated Scalable Bayesian Inference via Hilbert Coresets](https://mlsanity.com/paper/1710.05053/) (2017)
- [Training Gaussian Mixture Models at Scale via Coresets](https://mlsanity.com/paper/1703.08110/) (2017)
- [Revisiting Distillation and Incremental Classifier Learning](https://mlsanity.com/paper/1807.02802/) (2018)
- [Rk-means: Fast Clustering for Relational Data](https://mlsanity.com/paper/1910.04939/) (2019)
- [Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning](https://mlsanity.com/paper/2206.07842/) (2022)

## Built on by (most cited first, 4 of 4)

- [An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning](https://mlsanity.com/paper/2308.00788/) (2023)
- [Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning](https://mlsanity.com/paper/2310.08782/) (2023)
- [The Power of Few: Accelerating and Enhancing Data Reweighting with Coreset Selection](https://mlsanity.com/paper/2403.12166/) (2024)
- [Noise-Tolerant Coreset-Based Class Incremental Continual Learning](https://mlsanity.com/paper/2504.16763/) (2025)

## Abstract (arXiv)

Lifelong learning (LL) aims to improve a predictive model as the data source evolves continuously. Most work in this learning paradigm has focused on resolving the problem of 'catastrophic forgetting,' which refers to a notorious dilemma between improving model accuracy over new data and retaining accuracy over previous data. Yet, it is also known that machine learning (ML) models can be vulnerable in the sense that tiny, adversarial input perturbations can deceive the models into producing erroneous predictions. This motivates the research objective of this paper - specification of a new LL framework that can salvage model robustness (against adversarial attacks) from catastrophic forgetting. Specifically, we propose a new memory-replay LL strategy that leverages modern bi-level optimization techniques to determine the 'coreset' of the current data (i.e., a small amount of data to be memorized) for ease of preserving adversarial robustness over time. We term the resulting LL framework 'Data-Efficient Robustness-Preserving LL' (DERPLL). The effectiveness of DERPLL is evaluated for class-incremental image classification using ResNet-18 over the CIFAR-10 dataset. Experimental results show that DERPLL outperforms the conventional coreset-guided LL baseline and achieves a substantial improvement in both standard accuracy and robust accuracy.