mlsanityData to 7 Oct 2026

Interpretations of Domain Adaptations via Layer Variational Analysis

arXiv 2302.01798 ↗First posted 3 Feb 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Transfer learning is known to perform efficiently in many applications empirically, yet limited literature reports the mechanism behind the scene. This study establishes both formal derivations and heuristic analysis to formulate the theory of transfer learning in deep learning. Our framework utilizing layer variational analysis proves that the success of transfer learning can be guaranteed with corresponding data conditions. Moreover, our theoretical calculation yields intuitive interpretations towards the knowledge transfer process. Subsequently, an alternative method for network-based transfer learning is derived. The method shows an increase in efficiency and accuracy for domain adaptation. It is particularly advantageous when new domain data is sufficiently sparse during adaptation. Numerical experiments over diverse tasks validated our theory and verified that our analytic expression achieved better performance in domain adaptation than the gradient descent method.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 25 of its 45 references that are in the map. First posted on arXiv 3 Feb 2023.

Builds on

25 of 45 references.

References · 25

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  7. 2014How transferable are features in deep neural networks?cited by 1,216
  8. 2018Deep Visual Domain Adaptation: A Surveycited by 634
  9. 2018Do Better ImageNet Models Transfer Better?cited by 560
  10. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 422
  11. 2018A Survey on Deep Transfer Learningcited by 417
  12. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
13 more
  1. 2020What is being transferred in transfer learning?cited by 365
  2. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 226
  3. 2016Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learningcited by 209
  4. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 166
  5. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 128
  6. 2018An introduction to domain adaptation and transfer learningcited by 112
  7. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  8. 2017Partial Transfer Learning with Selective Adversarial Networkscited by 84
  9. 2019DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networkscited by 80
  10. 2020FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancementcited by 66
  11. 2017Label Efficient Learning of Transferable Representations across Domains and Taskscited by 49
  12. 2017Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuningcited by 48
  13. 2020An analysis of the transfer learning of convolutional neural networks for artistic imagescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASRcited by 3
  2. 2025Transfer Learning Analysis of Variational Quantum Circuitscited by 3
  3. 2025Cross-modal Knowledge Transfer Learning as Graph Matching Based on Optimal Transport for ASRcited by 1
  4. 2026Tunable Domain Adaptation Using Unfoldingcited by 0