mlsanityData to 7 Oct 2026

A Comprehensive Survey on Transfer Learning

arXiv 1911.02685 ↗First posted 7 Nov 2019cs.LG stat.MLcited by 1,154

Not on the map. Why?

Abstract (arXiv)

Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. Due to the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning researches, as well as to summarize and interpret the mechanisms and the strategies of transfer learning in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Unlike previous surveys, this survey paper reviews more than forty representative transfer learning approaches, especially homogeneous transfer learning approaches, from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, over twenty representative transfer learning models are used for experiments. The models are performed on three different datasets, i.e., Amazon Reviews, Reuters-21578, and Office-31. And the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.

Key facts. Cited by 1,154 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 133; 2022: 222; 2023: 259; 2024: 269; 2025: 193; 2026: 77.

1,154 papers.

Sort:

By area:

  1. 2022Visual Prompt Tuningcited by 1,674
  2. 2022Editing Models with Task Arithmeticcited by 1,076
  3. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  4. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 795
  5. 2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
  6. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  7. 2021Domain Adaptation for Medical Image Analysis: A Surveycited by 351
  8. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 349
  9. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  10. 2021A Survey on Deep Semi-supervised Learningcited by 250
  11. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  12. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 218
38 more
  1. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  2. 2023Knowledge Editing for Large Language Models: A Surveycited by 189
  3. 2024Arcee's MergeKit: A Toolkit for Merging Large Language Modelscited by 189
  4. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 181
  5. 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
  6. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  7. 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
  8. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  9. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  10. 2021Deep Subdomain Adaptation Network for Image Classificationcited by 119
  11. 2022A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learningcited by 104
  12. 2023A Comprehensive Survey on Source-free Domain Adaptationcited by 104
  13. 2021Unsupervised Domain Adaptation of Object Detectors: A Surveycited by 93
  14. 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
  15. 2022SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learningcited by 93
  16. 2022Head2Toe: Utilizing Intermediate Representations for Better Transfer Learningcited by 83
  17. 2022Deep transfer operator learning for partial differential equations under conditional shiftcited by 83
  18. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  19. 2024Robust agents learn causal world modelscited by 81
  20. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  21. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  22. 2022Recent Advances in Bayesian Optimizationcited by 74
  23. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  24. 2024Parameter Competition Balancing for Model Mergingcited by 71
  25. 2022MDFEND: Multi-domain Fake News Detectioncited by 68
  26. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 63
  27. 2022Reliable extrapolation of deep neural operators informed by physics or sparse observationscited by 62
  28. 2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
  29. 2023Continual Learning: Applications and the Road Forwardcited by 59
  30. 2021Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Makingcited by 58
  31. 2021Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Darkcited by 57
  32. 2022Transferability in Deep Learning: A Surveycited by 57
  33. 2022Visual Query Tuning: Towards Effective Usage of Intermediate Representations for Parameter and Memory Efficient Transfer Learningcited by 57
  34. 2023Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalizationcited by 57
  35. 2021Incorporating Domain Knowledge into Deep Neural Networkscited by 56
  36. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  37. 2022A Review of Deep Transfer Learning and Recent Advancementscited by 56
  38. 2023PRIOR: Prototype Representation Joint Learning from Medical Images and Reportscited by 55

50 most cited of 1,154 All 1,154 (JSON)