Continual Learning Model

Continual learning aims to enable artificial intelligence models to learn continuously from a stream of data without forgetting previously acquired knowledge, mirroring human learning capabilities. Current research focuses on mitigating "catastrophic forgetting" through various techniques, including representation-based methods, prompt-based approaches, and variational methods, often incorporating task heuristics or memory mechanisms to manage information efficiently. This field is crucial for developing more robust and adaptable AI systems, impacting applications ranging from personalized medicine to energy-efficient AI and improving the generalizability of models in dynamic environments.

Papers

November 7, 2024

Differentially Private Continual Learning using Pre-Trained Models
Marlon Tobaben, Marcus Klasson, Rui Li, Arno Solin, Antti Honkela
Continual LEArning Differential Privacy Pre Trained Model Continual Learning Data Privacy Continual Learning Model

October 6, 2024

Leveraging Hierarchical Taxonomies in Prompt-based Continual Learning
Quyen Tran, Minh Le, Tuan Truong, Dinh Phung, Linh Ngo, Thien Nguyen, Nhat Ho, Trung Le
Deep Learning Model Continual LEArning Catastrophic Forgetting Regularization Loss Learning Process Continual Learning Model Hierarchical Taxonomy

September 27, 2024

How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models
Tomaso Trinci, Simone Magistri, Roberto Verdecchia, Andrew D. Bagdanov
Continual LEArning Energy Consumption Vision Foundation Model Continual Learning Algorithm Continual Training Green AI Free Continual Learning Continual Learning Model

August 29, 2024

Adaptive Variational Continual Learning via Task-Heuristic Modelling
Fan Yang
Learning Algorithm Continual Learning Model Task Model Variational Continual Learning

May 6, 2024

Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
Nishant Suresh Aswani, Amira Guesmi, Muhammad Abdullah Hanif, Muhammad Shafique
Continual LEArning Continual Learning Internal Representation Tensor Decomposition Pre Change Information Continual Learning Model Representation Forgetting

April 11, 2024

Calibration of Continual Learning Models
Lanpei Li, Elia Piccoli, Andrea Cossu, Davide Bacciu, Vincenzo Lomonaco
Continual LEArning Calibration Performance Model Calibration Continual Learning Model Accurate Predictive Model Continual Calibration

December 6, 2023

Benchmarking Continual Learning from Cognitive Perspectives
Xiaoqian Liu, Junge Zhang, Mingyi Zhang, Peipei Yang
Continual LEArning Cognitive Science Continual Learning Benchmark Cognitive Capability Continual Learning Model

November 7, 2023

Class-Incremental Continual Learning for General Purpose Healthcare Models
Amritpal Singh, Mustafa Burak Gurbuz, Shiva Souhith Gantha, Prahlad Jasti
Deep Learning Model Continual LEArning Continual Learning Class Incremental Continual Learning Continual Learning Model General Purpose Medical

July 9, 2023

Class-Incremental Mixture of Gaussians for Deep Continual Learning
Lukasz Korycki, Bartosz Krawczyk
Continual Learning Gradient Based RSD Difference of Gaussian Discriminative Feature COntinual Learning Framework Learning Mixture Continual Learning Model Time Varying Objective

March 31, 2023

Towards Adversarially Robust Continual Learning
Tao Bai, Chen Chen, Lingjuan Lyu, Jun Zhao, Bihan Wen
Adversarial Attack Continual LEArning Adversarial Training Adversarial Robustness Continual Learning Model Continual Adversarial Defense

February 16, 2023

New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning
Guoqiang Liang, Zhaojie Chen, Zhaoqiang Chen, Shiyu Ji, Yanning Zhang
Continual LEArning Incremental Learning Replay Based Stability Plasticity Continual Learning Model Online Class Incremental Learning New Insight Recency Bias

November 29, 2022

Data Poisoning Attack Aiming the Vulnerability of Continual Learning
Gyojin Han, Jaehyun Choi, Hyeong Gwon Hong, Junmo Kim
Continual LEArning Continual Learning Data Poisoning Attack Latent Vulnerability Continual Learning Model Regularization Based Continual Learning

August 7, 2022

Continual Learning for Tumor Classification in Histopathology Images
Veena Kaustaban, Qinle Ba, Ipshita Bhattacharya, Nahil Sobh, Satarupa Mukherjee, Jim Martin, Mohammad Saleh Miri, Christoph Guetter, Amal Chaturvedi
Continual LEArning Digital Pathology Breast Cancer Image Analysis Histopathology Image Image Data Cancer Classification Continual Learning Model

May 26, 2022

Continual evaluation for lifelong learning: Identifying the stability gap
Matthias De Lange, Gido van de Ven, Tinne Tuytelaars
Continual LEArning Catastrophic Forgetting Lifelong Learning Continual Learning Model

April 12, 2022

Dynamic Dialogue Policy for Continual Reinforcement Learning
Christian Geishauser, Carel van Niekerk, Nurul Lubis, Michael Heck, Hsien-Chin Lin, Shutong Feng, Milica Gašić
Continual LEArning Continual Reinforcement Learning Dialogue Policy Continual Learning Model Dialog Policy Learning

March 29, 2022

Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
Jihwan Bang, Hyunseo Koh, Seulki Park, Hwanjun Song, Jung-Woo Ha, Jonghyun Choi
Continual LEArning Noisy Data Online Continual Learning Episodic Memory Continual Learning Model Sample Diversity Task Boundary

March 21, 2022

Online Continual Learning for Embedded Devices
Tyler L. Hayes, Christopher Kanan
Continual LEArning Continual Learning Online Continual Learning Embedded System Device Learning Continual Learning Model

January 23, 2022

Learning to Predict Gradients for Semi-Supervised Continual Learning
Yan Luo, Yongkang Wong, Mohan Kankanhalli, Qi Zhao
LeArning Abstract Continual LEArning Continual Learning Model Semi Supervised Continual Learning Supervised Continual Learning

December 16, 2021

Effective prevention of semantic drift as angular distance in memory-less continual deep neural networks
Khouloud Saadi, Muhammad Taimoor Khan
Continual Learning Semantic Change Stability Plasticity Effective Prevention Continual Learning Model Point to Plane Distance Lifelong Machine Learning

December 6, 2021

Is Class-Incremental Enough for Continual Learning?
Andrea Cossu, Gabriele Graffieti, Lorenzo Pellegrini, Davide Maltoni, Davide Bacciu, Antonio Carta, Vincenzo Lomonaco
Continual LEArning Catastrophic Forgetting Exercise Repetition Continual Learning Model Class Incremental