Continual Learning Algorithm

Continual learning algorithms aim to enable artificial intelligence models to learn from a continuous stream of data without forgetting previously acquired knowledge, a phenomenon known as catastrophic forgetting. Current research focuses on improving the efficiency and robustness of these algorithms, exploring various approaches such as replay buffers, regularization techniques, and parameter isolation methods, often applied to pre-trained models like Vision Transformers. This field is crucial for developing more adaptable and environmentally sustainable AI systems, addressing challenges in real-world applications where data is constantly evolving and resource constraints are significant.

Papers

November 14, 2022

Hierarchically Structured Task-Agnostic Continual Learning
Heinke Hihn, Daniel A. Braun
Reinforcement Learning Continual LEArning Continual Reinforcement Learning Continual Learning Algorithm Agnostic Continual Learning Continual Learning Paradigm

September 30, 2022

Task Formulation Matters When Learning Continually: A Case Study in Visual Question Answering
Mavina Nikandrou, Lu Yu, Alessandro Suglia, Ioannis Konstas, Verena Rieser
Continual LEArning Case Study Visual Question Answering Visual Representation Vision Language Task Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G Continual Learning Algorithm Task Formulation

July 11, 2022

Susceptibility of Continual Learning Against Adversarial Attacks
Hikmat Khan, Pir Masoom Shah, Syed Farhan Alam Zaidi, Saif ul Islam, Qasim Zia
Adversarial Attack Continual LEArning Continual Learning Continual Learning Algorithm State of the Art Continual

July 4, 2022

Memory Population in Continual Learning via Outlier Elimination
Julio Hurtado, Alain Raymond-Saez, Vladimir Araujo, Vincenzo Lomonaco, Alvaro Soto, Davide Bacciu
Continual LEArning Catastrophic Forgetting Continual Learning Algorithm Outlier Removal Memory Population

March 14, 2022

L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
Erik C. Johnson, Eric Q. Nguyen, Blake Schreurs, Chigozie S. Ewulum, Chace Ashcraft, Neil M. Fendley, Megan M. Baker, Alexander New, Gautam K. Vallabha
Reinforcement Learning Lifelong Learning Continual Reinforcement Learning Continual Learning Algorithm Lifelong Reinforcement Learning Reinforcement Learning Solution

March 8, 2022

On Generalizing Beyond Domains in Cross-Domain Continual Learning
Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu, Samuel Schulter, Yumin Suh, Mehrtash Harandi, Manmohan Chandraker
Strong Generalization Continual LEArning Domain Shift Unseen Domain Domain Name Continual Learning Algorithm

March 2, 2022

Continual Feature Selection: Spurious Features in Continual Learning
Timothée Lesort
Continual LEArning Catastrophic Forgetting Feature Selection Spurious Feature Continual Learning Algorithm

December 13, 2021

Ex-Model: Continual Learning from a Stream of Trained Models
Antonio Carta, Andrea Cossu, Vincenzo Lomonaco, Davide Bacciu
Full Model Continual LEArning Continual Learning Link Stream Continual Learning Algorithm Model Paradigm Trained Model