This is a comprehensive list of Heterogeneous Transfer Learning Methods with corresponding resources such as research papers, code, and datasets. Please feel free to contact us at [email protected] or [email protected] if you discover any errors or have any suggestions.

🌟 The organization of papers aligns with our survey: A Recent Survey on Heterogeneous Transfer Learning. If you find this resource helpful, please consider to star this repository and cite our survey paper.

1. TTL:"Transitive transfer learning". Tan, Ben, et al. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2015.[paper]
2. HTLIC:"Heterogeneous transfer learning for image classification.". Zhu, Yin, et al. Proceedings of the AAAI conference on artificial intelligence. Vol. 25. No. 1. 2011. [paper]
3. DHTL:"Deep semantic mapping for heterogeneous multimedia transfer learning using co-occurrence data.". Zhao, Liang, et al. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 15.1s (2019): 1-21. [paper]
4. OHKT:"Online heterogeneous transfer learning by knowledge transition.". Wu, Hanrui, et al. ACM Transactions on Intelligent Systems and Technology (TIST) 10.3 (2019): 1-19. [paper]
5. OHT:"Online heterogeneous transfer by hedge ensemble of offline and online decisions.". Yan, Yuguang, et al. IEEE transactions on neural networks and learning systems 29.7 (2017): 3252-3263. [paper]

1. CDLS:"Learning cross-domain landmarks for heterogeneous domain adaptation.". Tsai, Yao-Hung Hubert, Yi-Ren Yeh, and Yu-Chiang Frank Wang. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. [paper] [code]
2. SHDA-RF:"Supervised Heterogeneous Domain Adaptation via Random Forests.". Sukhija, Sanatan, Narayanan Chatapuram Krishnan, and Gurkanwal Singh. IJCAI. 2016. [paper]
3. SHFR:"Multi-class heterogeneous domain adaptation.". Zhou, Joey Tianyi, et al. Journal of Machine Learning Research (2019). [paper]
4. HeMap:"Transfer learning on heterogenous feature spaces via spectral transformation.". Shi, Xiaoxiao, et al. 2010 IEEE international conference on data mining. IEEE, 2010. [paper]
5. DACoM:"Semi-supervised domain adaptation by covariance matching.". Li, Limin, and Zhenyue Zhang. IEEE transactions on pattern analysis and machine intelligence 41.11 (2018): 2724-2739. [paper]
6. DAMA:"Heterogeneous domain adaptation using manifold alignment.". Wang, Chang, and Sridhar Mahadevan. IJCAI proceedings-international joint conference on artificial intelligence. Vol. 22. No. 1. 2011. [paper]
7. LPJT:"Locality preserving joint transfer for domain adaptation.". Li, Jingjing, et al. IEEE Transactions on Image Processing 28.12 (2019): 6103-6115. [paper] [code]
8. ICDM:"Heterogeneous domain adaptation by information capturing and distribution matching.". Wu, Hanrui, et al. IEEE Transactions on Image Processing 30 (2021): 6364-6376. [paper]
9. CDSPP:"Cross-domain structure preserving projection for heterogeneous domain adaptation.". Wang, Qian, and Toby P. Breckon. Pattern Recognition 123 (2022): 108362. [paper]
10. STN:"Heterogeneous domain adaptation via soft transfer network.". Yao, Yuan, et al. Proceedings of the 27th ACM international conference on multimedia. 2019. [paper] [code]
11. SCT:"Semantic Correlation Transfer for Heterogeneous Domain Adaptation.". Zhao, Ying, et al. IEEE Transactions on Neural Networks and Learning Systems (2022). [paper]
12. HDAPA:"Heterogeneous domain adaptation through progressive alignment.". Li, Jingjing, et al. IEEE transactions on neural networks and learning systems 30.5 (2018): 1381-1391. [paper] [code]
13. HANDA:"Heterogeneous domain adaptation with adversarial neural representation learning: experiments on e-commerce and cybersecurity.". Ebrahimi, Mohammadreza, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence 45.2 (2022): 1862-1875. [paper] [code]
14. FSR:"Transfer learning across feature-rich heterogeneous feature spaces via feature-space remapping (FSR).". Feuz, Kyle D., and Diane J. Cook. ACM transactions on intelligent systems and technology (TIST) 6.1 (2015): 1-27. [paper]
15. SSKMDA:"Feature space independent semi-supervised domain adaptation via kernel matching.". Xiao, Min, and Yuhong Guo. IEEE transactions on pattern analysis and machine intelligence 37.1 (2014): 54-66. [paper]
16. TNT:"Transfer neural trees for heterogeneous domain adaptation." Chen, Wei-Yu, et al. ECCV 2016. [paper] [code]

1. SHFA:"Learning with augmented features for supervised and semi-supervised heterogeneous domain adaptation." Li, Wen, et al. IEEE Transactions on Pattern analysis and machine intelligence 36.6 (2013): 1134-1148. [paper] [code]
2. DCA:"Learning Discriminative Correlation Subspace for Heterogeneous Domain Adaptation." Yan, Yuguang, et al. IJCAI. 2017. [paper]
3. KPDA:"Knowledge preserving and distribution alignment for heterogeneous domain adaptation." Wu, Hanrui, Qingyao Wu, and Michael K. Ng. ACM Transactions on Information Systems (TOIS) 40.1 (2021): 1-29. [paper] [code]
4. Sym-GANs:"Exploiting images for video recognition: Heterogeneous feature augmentation via symmetric adversarial learning." Yu, Feiwu, et al. IEEE Transactions on Image Processing 28.11 (2019): 5308-5321. [paper]
5. HTLA:"Transfer learning for cross-language text categorization through active correspondences construction." Zhou, Joey, et al. Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 30. No. 1. 2016. [paper]
6. NMF:"Heterogeneous domain adaptation via nonlinear matrix factorization." Li, Haoliang, et al. IEEE transactions on neural networks and learning systems 31.3 (2019): 984-996. [paper]
7. Deep-MCA:"Heterogeneous transfer learning via deep matrix completion with adversarial kernel embedding." Li, Haoliang, et al. Proceedings of the AAAI conference on artificial intelligence. Vol. 33. No. 01. 2019. [paper]

1. REFORM:"Heterogeneous few-shot model rectification with semantic mapping." Ye, Han-Jia, et al. IEEE Transactions on Pattern Analysis and Machine Intelligence 43.11 (2020): 3878-3891. [paper]
2. DTNs:"Weakly-shared deep transfer networks for heterogeneous-domain knowledge propagation." Shu, Xiangbo, et al. Proceedings of the 23rd ACM international conference on Multimedia. 2015. [paper]

1. resizer:"Learning to resize images for computer vision tasks." Talebi, Hossein, and Peyman Milanfar. Proceedings of the IEEE/CVF international conference on computer vision. 2021. [paper] [code]
2. ImageBERT:"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data." Qi, Di, et al. arXiv preprint arXiv:2001.07966 (2020). [paper]
3. ProteinChat:"ProteinChat: Towards Achieving ChatGPT-Like Functionalities on Protein 3D Structures." Guo, Han, et al. 2023. [paper] [code]
4. ViT:"An image is worth 16x16 words: Transformers for image recognition at scale." Dosovitskiy, Alexey, et al. ICLR 2021. [paper] [code]
5. VL-BERT:"VL-BERT: Pre-training of generic visual-linguistic representations." Su, Weijie, et al. ICLR 2020. [paper] [code]

For more detailed information, please read our survey: A Recent Survey on Heterogeneous Transfer Learning.

For general Transfer Learning Papers, Tutorials, and Surveys, please check Dr. Jindong Wang's Transfer Learning Repo.