Fast Adaptation

Fast adaptation in machine learning focuses on enabling models to quickly and efficiently adjust to new tasks or data distributions with minimal retraining. Current research emphasizes techniques like meta-learning (including Model-Agnostic Meta-Learning and its variants), test-time training, and parameter-efficient fine-tuning methods such as Low-Rank Adaptation (LoRA), often applied to pre-trained foundation models. This area is crucial for deploying AI in dynamic real-world scenarios, improving efficiency in applications ranging from robotics and recommendation systems to medical image analysis and disaster response.

Papers

October 3, 2023

OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation
Kuntai Du, Yuhan Liu, Yitian Hao, Qizheng Zhang, Haodong Wang, Yuyang Huang, Ganesh Ananthanarayanan, Junchen Jiang
Back Propagation DNN Model Deep Learning Application Fast Adaptation Neural Network Output Adaptation Protocol Adaptive Scheme

October 1, 2023

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm
Qi Wang, Yiqin Lv, Yanghe Feng, Zheng Xie, Jincai Huang
Meta Learning Fast Adaptation Simple Strategy Robust Meta Learning Meta Learning Benchmark

August 31, 2023

Adaptation Speed Analysis for Fairness-aware Causal Models
Yujie Lin, Chen Zhao, Minglai Shao, Xujiang Zhao, Haifeng Chen
Domain Shift Fast Adaptation

August 17, 2023

META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection
Jinbo Hu, Yin Cao, Ming Wu, Feiran Yang, Ziying Yu, Wenwu Wang, Mark D. Plumbley, Jun Yang
Data Detection Fast Adaptation Acoustic Environment Sound Event Localization New Environment Sound Event Localization and Detection

August 12, 2023

A Sequential Meta-Transfer (SMT) Learning to Combat Complexities of Physics-Informed Neural Networks: Application to Composites Autoclave Processing
Milad Ramezankhani, Abbas S. Milani
LeArning Abstract Physic Informed Neural Network Nonlinear Dynamic Fast Adaptation Efficient Adaptation Initial Condition PDE System Meta Transfer

July 15, 2023

Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation
Victor Gallego
Faithful Generation Large Multimodal Model Image Text Fast Adaptation Preference Prediction Bradley Terry

June 27, 2023

Exploiting Inferential Structure in Neural Processes
Dharmesh Tailor, Mohammad Emtiyaz Khan, Eric Nalisnick
End to End Latent Variable Stochastic Gradient Neural Process Explanatory Inference Fast Adaptation

May 16, 2023

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim, Philip H. S. Torr, Adel Bibi, Bernard Ghanem
Online Continual Learning Fast Adaptation High Precision Accuracy on the Line

May 10, 2023

Fast Teammate Adaptation in the Presence of Sudden Policy Change
Ziqian Zhang, Lei Yuan, Lihe Li, Ke Xue, Chengxing Jia, Cong Guan, Chao Qian, Yang Yu
Speech Presence Fast Adaptation Agent Benchmark Unknown Teammate Policy Switching

April 27, 2023

Discovering Object-Centric Generalized Value Functions From Pixels
Somjit Nath, Gopeshh Raaj Subbaraj, Khimya Khetarpal, Samira Ebrahimi Kahou
Deep Reinforcement Learning Scientific Discovery Value Function Tetromino Pixel Fast Adaptation Dimensional Input Useful Representation

April 13, 2023

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning
Enze Xie, Lewei Yao, Han Shi, Zhili Liu, Daquan Zhou, Zhaoqiang Liu, Jiawei Li, Zhenguo Li
Parameter Efficient Fine Tuning Pre Trained Diffusion Model Pre Trained Convolutional Neural Network Fast Adaptation Diffusion Based Method Improving Transferability Large Diffusion Model

April 10, 2023

Evaluation of Test-Time Adaptation Under Computational Time Constraints
Motasem Alfarra, Hani Itani, Alejandro Pardo, Shyma Alhuwaider, Merey Ramazanova, Juan C. Pérez, Zhipeng Cai, Matthias Müller, Bernard Ghanem
Global Evaluation Test Time Adaptation Fast Adaptation Resource Constraint Time Adaptation

March 26, 2023

$\Delta$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss
Chaitanya Devaguptapu, Samarth Sinha, K J Joseph, Vineeth N Balasubramanian, Animesh Garg
Zero Shot Transfer Learning New Framework Pre Trained Model Pre Trained Convolutional Neural Network Fast Adaptation Q Network Performance Degradation

March 23, 2023

Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence
Chaoqun You, Kun Guo, Gang Feng, Peng Yang, Tony Q. S. Quek
Early Stage Convergence Fast Adaptation Model Agnostic Meta Learning Federated Meta Learning

March 22, 2023

Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation
Zijian Liu, Zhengyuan Zhou
Stochastic Gradient Convex Optimization Fast Adaptation Stochastic Optimization Problem Heavy Tailed Noise High Probability Bound

March 2, 2023

Bipedal Robot Running: Human-like Actuation Timing Using Fast and Slow Adaptations
Yusuke Sakurai, Tomoya Kamimura, Yuki Sakamoto, Shohei Nishii, Kodai Sato, Yuta Fujiwara, Akihito Sano
Human Like Bipedal Robot Fast Adaptation Central Pattern Generator Human Locomotion Bipedal System

February 23, 2023

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption
Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren
Edge AI Fast Adaptation Device Inference Traditional Neural Network Device Multi Modal Model Adaptation

February 9, 2023

Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics
Anton Voronov, Mikhail Khoroshikh, Artem Babenko, Max Ryabinin
Text to Image Generation Image Synthesis Text to Image Fast Adaptation Dynamic Goal BCE Loss

February 7, 2023

Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
Mohamed Elsayed, A. Rupam Mahmood
Continual LEArning Representation Learning Catastrophic Forgetting Fast Adaptation Superior Optimizer

January 19, 2023

Concept Discovery for Fast Adapatation
Shengyu Feng, Hanghang Tong
Shot Learning Meta Learning Fast Adaptation Concept Discovery Well Trained Model

Fast Adaptation

Papers

OneAdapt: Fast Adaptation for Deep Learning Applications via Backpropagation

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

Adaptation Speed Analysis for Fairness-aware Causal Models

META-SELD: Meta-Learning for Fast Adaptation to the new environment in Sound Event Localization and Detection

A Sequential Meta-Transfer (SMT) Learning to Combat Complexities of Physics-Informed Neural Networks: Application to Composites Autoclave Processing

Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation

Exploiting Inferential Structure in Neural Processes

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?

Fast Teammate Adaptation in the Presence of Sudden Policy Change

Discovering Object-Centric Generalized Value Functions From Pixels

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning

Evaluation of Test-Time Adaptation Under Computational Time Constraints

$\Delta$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss

Automated Federated Learning in Mobile Edge Networks -- Fast Adaptation and Convergence

Stochastic Nonsmooth Convex Optimization with Heavy-Tailed Noises: High-Probability Bound, In-Expectation Rate and Initial Distance Adaptation

Bipedal Robot Running: Human-like Actuation Timing Using Fast and Slow Adaptations

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption

Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics

Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning

Concept Discovery for Fast Adapatation