PMF-CL: Pareto-Minimal-Forgetting Continual Learner for Conflicting Tasks

arXiv:2605.19145 · cs.LG · Submitted 2026-05-18 · Read on arXiv

cs.LG

Submitted: 2026-05-18

Updated: 2026-09-30

Code: https://github.com/aimagelab/mammoth

Terminology

• Catastrophic Forgetting — 3× in this paper · explained in 5 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes

Sources

• The Future of Continual Learning in the Era of Foundation Models: Three Key Directions
• Unifying Regularisation Methods for Continual Learning
• On Tiny Episodic Memories in Continual Learning
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
• Scaling Laws for Neural Language Models
• On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients
• Optimal Rates in Continual Linear Regression via Increasing Regularization
• Towards Understanding the Transferability of Deep Representations
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• GPT-4 Technical Report
• Learning Transferable Visual Models From Natural Language Supervision
• LLaMA: Open and Efficient Foundation Language Models
• A distillation-based approach integrating continual learning and federated learning for pervasive services
• Federated Continual Learning for Edge-AI: A Comprehensive Survey

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks