Continual Learning Paradigm

Continual learning aims to enable artificial intelligence systems to learn a sequence of tasks without forgetting previously acquired knowledge, a phenomenon known as catastrophic forgetting. Current research focuses on mitigating this forgetting through techniques like experience replay, knowledge distillation, and structural knowledge integration, often applied within various neural network architectures tailored to specific data types (e.g., time series, point clouds, images). These advancements are crucial for developing more robust and adaptable AI systems, impacting fields ranging from robotics and personalized medicine to efficient active learning strategies where retraining costs are significant.

Papers

March 11, 2024

On the Diminishing Returns of Width for Continual Learning
Etash Guha, Vihan Lakshman
Neural Network Continual LEArning Catastrophic Forgetting Customer Service Minimum Width Continual Learning Paradigm

February 20, 2024

Structural Knowledge Informed Continual Multivariate Time Series Forecasting
Zijie Pan, Yushan Jiang, Dongjin Song, Sahil Garg, Kashif Rasul, Anderson Schneider, Yuriy Nevmyvaka
Catastrophic Forgetting Multivariate Time Series Forecasting Continual Learning Paradigm Continual Knowledge Learning

September 18, 2023

A Continual Learning Paradigm for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks
Wentao Wan, Nan Kang, Zeqing Wang, Zhuojie Yang, Liang Lin, Keze Wang
Visual Reasoning Visual Task Visual Programming Compositional Task Continual Learning Paradigm

May 10, 2023

Accelerating Batch Active Learning Using Continual Learning Techniques
Arnav Das, Gantavya Bhatt, Megh Bhalerao, Vianne Gao, Rui Yang, Jeff Bilmes
Active Learning Catastrophic Forgetting Continual Learning Replay Based Continual Learning Batch Active Learning Continual Learning Paradigm

April 8, 2023

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data
Elena Camuffo, Simone Milani
Continual LEArning LiDAR Point Cloud Coarse to Fine Sparse Data Lidar Semantic Segmentation Class Incremental Continual Learning Continual Learning Paradigm

February 2, 2023

Online Continual Learning via the Knowledge Invariant and Spread-out Properties
Ya-nan Han, Jian-wei Liu
Continual LEArning Catastrophic Forgetting Online Continual Learning Many Property Continual Learning Algorithm Continual Learning Paradigm

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

March 8, 2022

New Insights on Reducing Abrupt Representation Change in Online Continual Learning
Lucas Caccia, Rahaf Aljundi, Nader Asadi, Tinne Tuytelaars, Joelle Pineau, Eugene Belilovsky
Continual Learning Anti Forgetting Online Continual Learning Experience Replay Parameter Update New Insight Continual Learning Paradigm