# Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off

arXiv: https://arxiv.org/abs/2503.23390 · HTML: https://mlsanity.com/paper/2503.23390/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [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)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/1904.00310/) (2019)
- [Pareto Multi-Task Learning](https://mlsanity.com/paper/1912.12854/) (2019)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Compacting, Picking and Growing for Unforgetting Continual Learning](https://mlsanity.com/paper/1910.06562/) (2019)
- [Learning the Pareto Front with Hypernetworks](https://mlsanity.com/paper/2010.04104/) (2020)
- [Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System](https://mlsanity.com/paper/2201.12604/) (2022)
- [Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data](https://mlsanity.com/paper/2108.09020/) (2021)
- [Continual Learning: Applications and the Road Forward](https://mlsanity.com/paper/2311.11908/) (2023)
- [Pareto Set Learning for Neural Multi-objective Combinatorial Optimization](https://mlsanity.com/paper/2203.15386/) (2022)
- [On Quadratic Penalties in Elastic Weight Consolidation](https://mlsanity.com/paper/1712.03847/) (2017)
- [La-MAML: Look-ahead Meta Learning for Continual Learning](https://mlsanity.com/paper/2007.13904/) (2020)
- [ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning](https://mlsanity.com/paper/2301.12618/) (2023)
- [Multi-FR: A Multi-objective Optimization Framework for Multi-stakeholder Fairness-aware Recommendation](https://mlsanity.com/paper/2105.02951/) (2021)

## Built on by (most cited first, 3 of 3)

- [Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training](https://mlsanity.com/paper/2507.05386/) (2025)
- [PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks](https://mlsanity.com/paper/2605.19145/) (2026)
- [AdaHome: An Adaptive Smart Home Assistant using Local Small Language Models](https://mlsanity.com/paper/2607.18034/) (2026)

## Abstract (arXiv)

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience replay methods, which store and replay past data alongside new data, have become a widely adopted approach to mitigate catastrophic forgetting. However, these methods neglect the dynamic nature of the stability-plasticity trade-off and aim to find a fixed and unchanging balance, resulting in suboptimal adaptation during training and inference. In this paper, we propose Pareto Continual Learning (ParetoCL), a novel framework that reformulates the stability-plasticity trade-off in continual learning as a multi-objective optimization (MOO) problem. ParetoCL introduces a preference-conditioned model to efficiently learn a set of Pareto optimal solutions representing different trade-offs and enables dynamic adaptation during inference. From a generalization perspective, ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity. Extensive experiments across multiple datasets and settings demonstrate that ParetoCL outperforms state-of-the-art methods and adapts to diverse continual learning scenarios.