DeepAI AI Chat
Log In Sign Up

Learning to Transfer Learn

by   Linchao Zhu, et al.
University of Technology Sydney

We propose a novel framework, learning to transfer learn (L2TL), to improve transfer learning on a target dataset by judicious extraction of information from a source dataset. Our framework considers joint optimization of strongly-shared weights between models of source and target tasks, and employs adaptive weights for scaling of constituent loss terms. The adaptation of the weights is done using a reinforcement learning (RL)-based policy model, which is guided based on a performance metric on the target validation set. We demonstrate state-of-the-art performance of L2TL given fixed models, consistently outperforming fine-tuning baselines on various datasets. In addition, in the regimes of small-scale target datasets and significant label mismatch between source and target datasets, L2TL outperforms previous methods by a large margin.


Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement

Fine-tuning deep neural networks pre-trained on large scale datasets is ...

Investigation on How Data Volume Affects Transfer Learning Performances in Business Applications

Transfer Learning helps to build a system to recognize and apply knowled...

Investigating the Impact of Data Volume and Domain Similarity on Transfer Learning Applications

Transfer Learning helps to build a system to recognize and apply knowled...

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

Prompt-tuning, which freezes pretrained language models (PLMs) and only ...

Scalable Transfer Evolutionary Optimization: Coping with Big Task Instances

In today's digital world, we are confronted with an explosion of data an...

SOSELETO: A Unified Approach to Transfer Learning and Training with Noisy Labels

We present SOSELETO (SOurce SELEction for Target Optimization), a new me...

An Information-Geometric Distance on the Space of Tasks

This paper computes a distance between tasks modeled as joint distributi...