Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge

@article{Wu2021OnlineTL,
  title={Online Transfer Learning: Negative Transfer and Effect of Prior Knowledge},
  author={Xuetong Wu and Jonathan H. Manton and Uwe Aickelin and Jingge Zhu},
  journal={2021 IEEE International Symposium on Information Theory (ISIT)},
  year={2021},
  pages={1540-1545}
}
  • Xuetong Wu, J. Manton, +1 author Jingge Zhu
  • Published 4 May 2021
  • Computer Science, Mathematics
  • 2021 IEEE International Symposium on Information Theory (ISIT)
Transfer learning is a machine learning paradigm where the knowledge from one task is utilized to resolve the problem in a related task. On the one hand, it is conceivable that knowledge from one task could be useful for solving a related problem. On the other hand, it is also recognized that if not executed properly, transfer learning algorithms could in fact impair the learning performance instead of improving it - commonly known as negative transfer. In this paper, we study the online… Expand

Figures from this paper

References

SHOWING 1-10 OF 18 REFERENCES
Online Transfer Learning
TLDR
This work proposes a novel machine learning framework called "Online Transfer Learning" (OTL), which aims to attack an online learning task on a target domain by transferring knowledge from some source domain, and investigates two different settings of OTL: (i) OTL on homogeneous domains of common feature space, and (ii) O TL across heterogeneous domainsof different feature spaces. Expand
Transfer of samples in batch reinforcement learning
TLDR
A novel algorithm is introduced that transfers samples from the source tasks that are mostly similar to the target task, and is empirically show that, following the proposed approach, the transfer of samples is effective in reducing the learning complexity. Expand
A Survey on Transfer Learning
TLDR
The relationship between transfer learning and other related machine learning techniques such as domain adaptation, multitask learning and sample selection bias, as well as covariate shift are discussed. Expand
Online transfer learning with multiple source domains for multi-class classification
TLDR
This paper makes the first attempt to study OnTL with Multiple Source Domains for multi- class classification (MC), and proposes an algorithm, referred to as Online Multi-source Transfer Learning for Multi-class classification (OMTL-MC) algorithm, built on two-stage ensemble strategy. Expand
Online transfer learning by leveraging multiple source domains
TLDR
This paper proposes a new online transfer learning algorithm that merges and leverages the classifiers of the source and target domain with an ensemble method and demonstrates that the algorithm outperforms the compared baseline algorithms. Expand
Transfer Learning for Reinforcement Learning Domains: A Survey
TLDR
This article presents a framework that classifies transfer learning methods in terms of their capabilities and goals, and then uses it to survey the existing literature, as well as to suggest future directions for transfer learning work. Expand
Transfer in Reinforcement Learning: A Framework and a Survey
  • A. Lazaric
  • Computer Science
  • Reinforcement Learning
  • 2012
TLDR
This chapter provides a formalization of the general transfer problem, the main settings which have been investigated so far, and the most important approaches to transfer in reinforcement learning. Expand
Online Transfer Learning in Reinforcement Learning Domains
TLDR
An online transfer framework to capture the interaction among agents is proposed and it is shown that current transfer learning in reinforcement learning is a special case of online transfer. Expand
Multi-Source Iterative Adaptation for Cross-Domain Classification
TLDR
A novel multi-source iterative domain adaptation algorithm that leverages knowledge from selective sources to improve the performance in a target domain and significantly outperforms existing cross-domain classification approaches on the real world and benchmark datasets. Expand
A Graphbased Framework for Multi-Task Multi-View Learning
TLDR
This paper introduces Multi-Task Multi-View (M2TV) learning for such complicated learning problems with both feature heterogeneity and task heterogeneity, and proposes a graph-based framework (GraM2) to take full advantage of the dual-heterogeneous nature. Expand
...
1
2
...