# A Framework for Supervised Heterogeneous Transfer Learning using Dynamic Distribution Adaptation and Manifold Regularization

arXiv: https://arxiv.org/abs/2108.12293 · HTML: https://mlsanity.com/paper/2108.12293/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 53 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 16 of 16)

- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [Understanding Self-Training for Gradual Domain Adaptation](https://mlsanity.com/paper/2002.11361/) (2020)
- [Learning Deep Kernels for Non-Parametric Two-Sample Tests](https://mlsanity.com/paper/2002.09116/) (2020)
- [Visual Domain Adaptation with Manifold Embedded Distribution Alignment](https://mlsanity.com/paper/1807.07258/) (2018)
- [Transfer Adaptation Learning: A Decade Survey](https://mlsanity.com/paper/1903.04687/) (2019)
- [Transfer Learning with Dynamic Distribution Adaptation](https://mlsanity.com/paper/1909.08531/) (2019)
- [Balanced Distribution Adaptation for Transfer Learning](https://mlsanity.com/paper/1807.00516/) (2018)
- [Heterogeneous domain adaptation: An unsupervised approach](https://mlsanity.com/paper/1701.02511/) (2017)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Heterogeneous Domain Adaptation via Soft Transfer Network](https://mlsanity.com/paper/1908.10552/) (2019)
- [Easy Transfer Learning By Exploiting Intra-domain Structures](https://mlsanity.com/paper/1904.01376/) (2019)
- [Learning from a Complementary-label Source Domain: Theory and Algorithms](https://mlsanity.com/paper/2008.01454/) (2020)
- [Adaptive Decision Forest: An Incremental Machine Learning Framework](https://mlsanity.com/paper/2101.11828/) (2021)

## Built on by (most cited first, 1 of 1)

- [A transfer learning enhanced the physics-informed neural network model for vortex-induced vibration](https://mlsanity.com/paper/2112.14448/) (2021)

## Abstract (arXiv)

Transfer learning aims to learn classifiers for a target domain by transferring knowledge from a source domain. However, due to two main issues: feature discrepancy and distribution divergence, transfer learning can be a very difficult problem in practice. In this paper, we present a framework called TLF that builds a classifier for the target domain having only few labeled training records by transferring knowledge from the source domain having many labeled records. While existing methods often focus on one issue and leave the other one for the further work, TLF is capable of handling both issues simultaneously. In TLF, we alleviate feature discrepancy by identifying shared label distributions that act as the pivots to bridge the domains. We handle distribution divergence by simultaneously optimizing the structural risk functional, joint distributions between domains, and the manifold consistency underlying marginal distributions. Moreover, for the manifold consistency we exploit its intrinsic properties by identifying k nearest neighbors of a record, where the value of k is determined automatically in TLF. Furthermore, since negative transfer is not desired, we consider only the source records that are belonging to the source pivots during the knowledge transfer. We evaluate TLF on seven publicly available natural datasets and compare the performance of TLF against the performance of fourteen state-of-the-art techniques. We also evaluate the effectiveness of TLF in some challenging situations. Our experimental results, including statistical sign test and Nemenyi test analyses, indicate a clear superiority of the proposed framework over the state-of-the-art techniques.