Adaptive Transfer Learning

Adaptive transfer learning aims to improve the efficiency and effectiveness of machine learning by intelligently transferring knowledge from previously learned tasks to new, related tasks. Current research focuses on developing algorithms that automatically adapt the transfer process based on the characteristics of both source and target data, employing techniques like adaptive knowledge distillation, fused-penalty methods for feature and sample selection, and data-driven approaches to select optimal pretrained model weights or feature maps. This field is significant because it addresses the challenges of data scarcity and computational cost in many applications, leading to improved performance in areas such as recommendation systems, plant phenotyping, and machine translation.

Papers

July 2, 2024

ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation
Chaoqun Hou, Yuanhang Zhou, Yi Cao, Tong Liu
Cross Domain Recommendation Continuous Environment Industrial Recommender System Adaptive Knowledge Distillation Adaptive Transfer Learning Event Annotation

May 28, 2024

An adaptive transfer learning perspective on classification in non-stationary environments
Henry W J Reeve
Classification Code Non Stationary Non Stationary Environment Dynamic Regret Adaptive Transfer Learning

March 20, 2024

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression
Zelin He, Ying Sun, Jingyuan Liu, Runze Li
High Dimensional Feature Wise Information Transfer Weak Signal Adaptive Transfer Learning

February 28, 2024

Diffusion-Based Neural Network Weights Generation
Bedionita Soro, Bruno Andreis, Hayeon Lee, Wonyong Jeong, Song Chong, Frank Hutter, Sung Ju Hwang
Transfer Learning Variational Autoencoder Latent Diffusion Model Neural Network Weight Recent Deep Learning Adaptive Transfer Learning

January 22, 2024

Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedure
T. Tony Cai, Hongming Pu
Transfer Learning Adaptive Method Nonparametric Regression Excess Risk Adaptive Transfer Learning

April 30, 2023

The ART of Transfer Learning: An Adaptive and Robust Pipeline
Boxiang Wang, Yunan Wu, Chenglong Ye
Transfer Learning Adaptive Importance Learning Rate Adaptive Transfer Learning Robust Transfer Learning Generic Machine Learning

January 1, 2023

An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects
Thanh Vinh Vo, Arnab Bhattacharyya, Young Lee, Tze-Yun Leong
Causal Effect Decentralized Data Heterogeneous Treatment Effect Adaptive Transfer Learning

September 13, 2022

Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican
Nathaniel R. Robinson, Cameron J. Hogan, Nancy Fulda, David R. Mortensen
Case Study Cross Lingual Transfer Cross Lingual View Translation Back Translation Low Resource Machine Translation Adaptive Transfer Learning

January 14, 2022

Adaptive Transfer Learning for Plant Phenotyping
Jun Wu, Elizabeth A. Ainsworth, Sheng Wang, Kaiyu Guan, Jingrui He
Machine Learning Model Transfer Learning Plant Phenotyping Adaptive Transfer Learning

November 22, 2021

Adaptive Transfer Learning: a simple but effective transfer learning
Jung H Lee, Henry J Kvinge, Scott Howland, Zachary New, John Buckheit, Lauren A. Phillips, Elliott Skomski, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas
Deep Learning Shot Learning Teacher Model Feature Extractor Effective Transfer Learning Adaptive Transfer Learning

Adaptive Transfer Learning

Papers

ECAT: A Entire space Continual and Adaptive Transfer Learning Framework for Cross-Domain Recommendation

An adaptive transfer learning perspective on classification in non-stationary environments

AdaTrans: Feature-wise and Sample-wise Adaptive Transfer Learning for High-dimensional Regression

Diffusion-Based Neural Network Weights Generation

Transfer Learning for Nonparametric Regression: Non-asymptotic Minimax Analysis and Adaptive Procedure

The ART of Transfer Learning: An Adaptive and Robust Pipeline

An Adaptive Kernel Approach to Federated Learning of Heterogeneous Causal Effects

Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican

Adaptive Transfer Learning for Plant Phenotyping

Adaptive Transfer Learning: a simple but effective transfer learning