paper-with-me

Papers

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

2025-03-30 · Song Lai, Zhe Zhao, Fei Zhu, Xi Lin, Qingfu Zhang, Gaofeng Meng

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.

📄 PDF Abstract BibTeX arXiv:2503.23390

Code (1)

laisong-22004009/paretocl 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets

2026-05-09 · Akihiro Kubo, Kosuke Nakanishi, Shin Ishii arxiv

Preference-conditioned multi-objective reinforcement learning aims to learn a single policy that captures trade-offs across preferences, but under nonlinear scalarization the uniqueness and continuity of the preference-t…

Reinforcement Learning

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

2023-05-24 · Pengyuan Lu, Michele Caprio, Eric Eaton, Insup Lee

Like generic multi-task learning, continual learning has the nature of multi-objective optimization, and therefore faces a trade-off between the performance of different tasks. That is, to optimize for the current task d…

Continual Learningimage-classificationImage ClassificationMulti-Task Learning

IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning

2023-10-04 · Pengyuan Lu, Michele Caprio, Eric Eaton, Insup Lee

Like generic multi-task learning, continual learning has the nature of multi-objective optimization, and therefore faces a trade-off between the performance of different tasks. That is, to optimize for the current task d…

Continual Learningimage-classificationImage ClassificationMulti-Task Learning

Scalable Pareto Front Approximation for Deep Multi-Objective Learning

2021-03-24 · Michael Ruchte, Josif Grabocka

Multi-objective optimization (MOO) is a prevalent challenge for Deep Learning, however, there exists no scalable MOO solution for truly deep neural networks. Prior work either demand optimizing a new network for every po…

Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation

2024-08-22 · Woo Kyung Kim, Minjong Yoo, Honguk Woo

Data-driven offline reinforcement learning and imitation learning approaches have been gaining popularity in addressing sequential decision-making problems. Yet, these approaches rarely consider learning Pareto-optimal p…

Autonomous DrivingDecision MakingImitation Learningreinforcement-learning+2