Retraining Method

Retraining methods in machine learning aim to improve model performance or adapt them to new data without the computationally expensive process of training from scratch. Current research focuses on developing techniques for efficient retraining across various model architectures, including large language models and convolutional neural networks, often leveraging strategies like prompt recycling, sparse inference, and low-rank fine-tuning to minimize resource consumption. These advancements are crucial for enhancing the sustainability and scalability of AI applications, particularly in resource-constrained environments and domains requiring continuous adaptation to evolving data streams. The ability to rapidly and cost-effectively retrain models is vital for deploying and maintaining AI systems in dynamic real-world scenarios.

Papers

May 4, 2023

Neuralizer: General Neuroimage Analysis without Re-Training
Steffen Czolbe, Adrian V. Dalca
Deep Learning Deep Learning Model Retraining Method Multi Task Network

March 27, 2023

Explain, Adapt and Retrain: How to improve the accuracy of a PPM classifier through different explanation styles
Williams Rizzi, Chiara Di Francescomarino, Chiara Ghidini, Fabrizio Maria Maggi
Predictive Model Explanation Method Outcome Prediction Retraining Method Predictive Process Monitoring

December 14, 2022

Backdoor Mitigation in Deep Neural Networks via Strategic Retraining
Akshay Dhonthi, Ernst Moritz Hahn, Vahid Hashemi
Deep Neural Network Backdoor Attack Retraining Method Hidden Backdoor

August 10, 2022

Reducing Retraining by Recycling Parameter-Efficient Prompts
Brian Lester, Joshua Yurtsever, Siamak Shakeri, Noah Constant
Complex Prompt Task Specific Soft Prompt Retraining Method Structure Guided Prompt Frozen Pre Trained Language Model

July 8, 2022

Guiding the retraining of convolutional neural networks against adversarial inputs
Francisco Durán López, Silverio Martínez-Fernández, Michael Felderer, Xavier Franch
Convolutional Neural Network Deep Learning Model Adversarial Input Retraining Method Adequacy Metric

March 14, 2022

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, Bo Li
Machine Unlearning Unlearning Framework Centralized Training Retraining Method Efficient Realization

March 3, 2022

Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining
Benjamin Billot, Magdamo Colin, Sean E. Arnold, Sudeshna Das, Juan. E. Iglesias
Wild Challenge Brain MRI Robust Segmentation Retraining Method Neuroimaging Study

February 7, 2022

Soft Actor-Critic with Inhibitory Networks for Faster Retraining
Jaime S. Ide, Daria Mićović, Michael J. Guarino, Kevin Alcedo, David Rosenbluth, Adrian P. Pope
Deep Reinforcement Learning Faster Training Soft Actor Critic Retraining Method Auto Tuning Path Entropy Inhibitory Neuron

January 13, 2022

Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering
Mohammed Oualid Attaoui, Hazem Fahmy, Fabrizio Pastore, Lionel Briand
Deep Neural Network Feature Extraction DNN Model DNN Training DNN Accuracy Safety Analysis DNN Repair Retraining Method

Retraining Method

Papers

Neuralizer: General Neuroimage Analysis without Re-Training

Explain, Adapt and Retrain: How to improve the accuracy of a PPM classifier through different explanation styles

Backdoor Mitigation in Deep Neural Networks via Strategic Retraining

Reducing Retraining by Recycling Parameter-Efficient Prompts

Guiding the retraining of convolutional neural networks against adversarial inputs

The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining

Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining

Soft Actor-Critic with Inhibitory Networks for Faster Retraining

Black-box Safety Analysis and Retraining of DNNs based on Feature Extraction and Clustering