Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 134 tok/s
Gemini 2.5 Pro 41 tok/s Pro
GPT-5 Medium 33 tok/s Pro
GPT-5 High 30 tok/s Pro
GPT-4o 86 tok/s Pro
Kimi K2 173 tok/s Pro
GPT OSS 120B 438 tok/s Pro
Claude Sonnet 4.5 37 tok/s Pro
2000 character limit reached

Taxonomy-Structured Domain Adaptation (2306.07874v2)

Published 13 Jun 2023 in cs.LG, cs.AI, and cs.CV

Abstract: Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nuanced domain relationships in the real world. In this work, we tackle a generalization with taxonomy-structured domains, which formalizes domains with nested, hierarchical similarity structures such as animal species and product catalogs. We build on the classic adversarial framework and introduce a novel taxonomist, which competes with the adversarial discriminator to preserve the taxonomy information. The equilibrium recovers the classic adversarial domain adaptation's solution if given a non-informative domain taxonomy (e.g., a flat taxonomy where all leaf nodes connect to the root node) while yielding non-trivial results with other taxonomies. Empirically, our method achieves state-of-the-art performance on both synthetic and real-world datasets with successful adaptation. Code is available at https://github.com/Wang-ML-Lab/TSDA.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. A theory of learning from different domains. Machine learning, 79(1):151–175, 2010.
  2. Blending-target domain adaptation by adversarial meta-adaptation networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  2248–2257, 2019.
  3. Adaptation across extreme variations using unlabeled domain bridges. arXiv preprint arXiv:1906.02238, 2019.
  4. Graph matching and pseudo-label guided deep unsupervised domain adaptation. In Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III 27, pp.  342–352. Springer, 2018.
  5. Zero-shot recommender systems. In ICLR Workshop on Deep Generative Models for Highly Structured Data, 2022.
  6. Domain-adversarial training of neural networks. JMLR, 17(1):2096–2030, 2016.
  7. Tada: Taxonomy adaptive domain adaptation. Withdrawn from ICLR 2022, 2021.
  8. Tacs: Taxonomy adaptive cross-domain semantic segmentation. In ECCV, 2022.
  9. Generative adversarial nets. In NIPS, pp.  2672–2680, 2014.
  10. Semi-supervised learning by entropy minimization. Advances in neural information processing systems, 17, 2004.
  11. Fine-grained visual-textual representation learning. IEEE Transactions on Circuits and Systems for Video Technology, 30(2):520–531, 2019.
  12. Recurrent poisson process unit for speech recognition. In AAAI, volume 33, pp.  6538–6545, 2019.
  13. Deep graph random process for relational-thinking-based speech recognition. In ICML, 2020.
  14. Domain adaptation for time series forecasting via attention sharing. In International Conference on Machine Learning, pp. 10280–10297. PMLR, 2022.
  15. Adam: A method for stochastic optimization. In ICLR, 2015.
  16. Understanding self-training for gradual domain adaptation. In International Conference on Machine Learning, pp. 5468–5479. PMLR, 2020.
  17. Unsupervised domain adaptation based on source-guided discrepancy. In AAAI, pp.  4122–4129, 2019.
  18. Conditional adversarial domain adaptation. In NIPS, pp.  1647–1657, 2018.
  19. Adagraph: Unifying predictive and continuous domain adaptation through graphs. In CVPR, pp.  6568–6577, 2019.
  20. Adversarial attacks are reversible with natural supervision. In ICCV, 2021.
  21. Autodial: Automatic domain alignment layers. In Proceedings of the IEEE international conference on computer vision, pp.  5067–5075, 2017.
  22. Training-free uncertainty estimation for neural networks. In AAAI, 2022.
  23. Miller, G. A. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39–41, 1995.
  24. Unsupervised multi-target domain adaptation through knowledge distillation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp.  1339–1347, 2021.
  25. Learning deep representation with large-scale attributes. In Proceedings of the IEEE International Conference on Computer Vision, pp.  1895–1903, 2015.
  26. A survey on transfer learning. TKDE, 22(10):1345–1359, 2009.
  27. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2010.
  28. Domain adaptation via transfer component analysis. TNN, 22(2):199–210, 2010.
  29. Moment matching for multi-source domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  1406–1415, 2019.
  30. Domain2vec: Domain embedding for unsupervised domain adaptation. arXiv preprint arXiv:2007.09257, 2020.
  31. Domain adaptation on graphs by learning aligned graph bases. IEEE Transactions on Knowledge and Data Engineering, 34(2):587–600, 2020.
  32. Sentry: Selective entropy optimization via committee consistency for unsupervised domain adaptation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp.  8558–8567, 2021.
  33. Coherent probabilistic forecasting of temporal hierarchies. In International Conference on Artificial Intelligence and Statistics, pp.  9362–9376. PMLR, 2023.
  34. A survey on domain adaptation theory: learning bounds and theoretical guarantees. arXiv preprint arXiv:2004.11829, 2020.
  35. Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR, pp.  3723–3732, 2018.
  36. Generate to adapt: Aligning domains using generative adversarial networks. In CVPR, pp.  8503–8512, 2018.
  37. Deep CORAL: correlation alignment for deep domain adaptation. In ICCV workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), pp.  443–450, 2016.
  38. Standardgan: Multi-source domain adaptation for semantic segmentation of very high resolution satellite images by data standardization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.  192–193, 2020.
  39. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474, 2014.
  40. Adversarial discriminative domain adaptation. In CVPR, pp.  7167–7176, 2017.
  41. Wang, H. Bayesian Deep Learning for Integrated Intelligence: Bridging the Gap between Perception and Inference. PhD thesis, Hong Kong University of Science and Technology, 2017.
  42. Towards bayesian deep learning: A framework and some existing methods. TDKE, 28(12):3395–3408, 2016.
  43. A survey on bayesian deep learning. CSUR, 53(5):1–37, 2020.
  44. Collaborative deep learning for recommender systems. In KDD, pp.  1235–1244, 2015.
  45. Bidirectional inference networks: A class of deep bayesian networks for health profiling. In AAAI, volume 33, pp.  766–773, 2019.
  46. Continuously indexed domain adaptation. In ICML, 2020a.
  47. Causal discovery from incomplete data: A deep learning approach. 2020b.
  48. Database resources of the national center for biotechnology information. Nucleic acids research, 36(suppl_1):D13–D21, 2007.
  49. Domain adaptation with asymmetrically-relaxed distribution alignment. In International conference on machine learning, pp. 6872–6881. PMLR, 2019.
  50. Graph-relational domain adaptation. In ICLR, 2022.
  51. Domain-indexing variational bayes: Interpretable domain index for domain adaptation. In ICLR, 2023.
  52. Cross-domain visual representations via unsupervised graph alignment. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pp.  5613–5620, 2019.
  53. Artificial intelligence-enabled detection and assessment of parkinson’s disease using nocturnal breathing signals. Nature medicine, 1(1):1–1, 2022.
  54. Bridging theory and algorithm for domain adaptation. arXiv preprint arXiv:1904.05801, 2019.
  55. Adversarial multiple source domain adaptation. In NIPS, pp.  8568–8579, 2018.
  56. On learning invariant representations for domain adaptation. In ICML, pp.  7523–7532, 2019.
  57. Learning sleep stages from radio signals: A conditional adversarial architecture. In ICML, pp.  4100–4109, 2017.
  58. Assessment of medication self-administration using artificial intelligence. Nature medicine, 2020.
  59. A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1):43–76, 2020.
  60. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European Conference on Computer Vision (ECCV), September 2018.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - Wang-ML-Lab/TSDA: [ICML 2023] Taxonomy-Structured Domain Adaptation (12 stars)
Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube