Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective (2402.12627v1)

Published 20 Feb 2024 in cs.LG, cs.AI, and cs.CV

Abstract: Recent AI technologies show remarkable evolution in various academic fields and industries. However, in the real world, dynamic data lead to principal challenges for deploying AI models. An unexpected data change brings about severe performance degradation in AI models. We identify two major related research fields, domain shift and concept drift according to the setting of the data change. Although these two popular research fields aim to solve distribution shift and non-stationary data stream problems, the underlying properties remain similar which also encourages similar technical approaches. In this review, we regroup domain shift and concept drift into a single research problem, namely the data change problem, with a systematic overview of state-of-the-art methods in the two research fields. We propose a three-phase problem categorization scheme to link the key ideas in the two technical fields. We thus provide a novel scope for researchers to explore contemporary technical strategies, learn industrial applications, and identify future directions for addressing data change challenges.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (206)
  1. D. Alvarez-Coello, D. Wilms, A. Bekan, and J. M. Gómez, “Towards a data-centric architecture in the automotive industry,” Procedia Computer Science, vol. 181, pp. 658–663, 2021.
  2. U. Jayasinghe, A. Otebolaku, T.-W. Um, and G. M. Lee, “Data centric trust evaluation and prediction framework for iot,” in ITU K, 2017, pp. 1–7.
  3. M. H. Jarrahi, A. Memariani, and S. Guha, “The principles of data-centric ai (dcai),” arXiv:2211.14611, 2022.
  4. L. Zhang and X. Gao, “Transfer adaptation learning: A decade survey,” IEEE TNNLS, 2022.
  5. J. Jiang, Y. Shu, J. Wang, and M. Long, “Transferability in deep learning: A survey,” arXiv:2201.05867, 2022.
  6. C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A survey on deep transfer learning,” in ICANN.   Springer, 2018, pp. 270–279.
  7. W. M. Kouw and M. Loog, “An introduction to domain adaptation and transfer learning,” arXiv:1812.11806, 2018.
  8. H. Hu, M. Kantardzic, and T. S. Sethi, “No free lunch theorem for concept drift detection in streaming data classification: A review,” WIREs DMKD, vol. 10, no. 2, p. e1327, 2020.
  9. S. Wares, J. Isaacs, and E. Elyan, “Data stream mining: methods and challenges for handling concept drift,” SN Applied Sciences, vol. 1, pp. 1–19, 2019.
  10. A. S. Iwashita and J. P. Papa, “An overview on concept drift learning,” IEEE Access, vol. 7, pp. 1532–1547, 2019.
  11. J. Lu, A. Liu, F. Dong, F. Gu, J. Gama, and G. Zhang, “Learning under concept drift: A review,” IEEE Transactions on Knowledge and Data Engineering, vol. 31, no. 12, pp. 2346–2363, 2019.
  12. P. A. Nayak, P. Sriganesh, K. Rakshitha, M. Manoj Kumar, B. S. Prashanth, and H. R. Sneha, “Literature review on phenomenon of concept drift and its handling approaches,” in ASIANCON, 2021, pp. 1–7.
  13. M. A. Hashmani, S. M. Jameel, M. Rehman, and A. Inoue, “Concept drift evolution in machine learning approaches: a systematic literature review,” International Journal on Smart Sensing and Intelligent Systems, vol. 13, no. 1, pp. 1–16, 2020.
  14. A. Farahani, S. Voghoei, K. Rasheed, and H. R. Arabnia, “A brief review of domain adaptation,” ICDATA and IKE, pp. 877–894, 2021.
  15. Y. Ganin, E. Ustinova, H. Ajakan, P. Germain et al., “Domain-adversarial training of neural networks,” The journal of machine learning research, vol. 17, no. 1, pp. 2096–2030, 2016.
  16. M. Xu, J. Zhang, B. Ni, T. Li, C. Wang, Q. Tian, and W. Zhang, “Adversarial domain adaptation with domain mixup,” AAAI Conference Proceedings, vol. 34, no. 04, pp. 6502–6509, 2020.
  17. X. Yu, T. Liu, M. Gong, K. Zhang, K. Batmanghelich, and D. Tao, “Label-noise robust domain adaptation,” in ICML.   PMLR, 2020, pp. 10 913–10 924.
  18. T. Lesort, M. Caccia, and I. Rish, “Understanding continual learning settings with data distribution drift analysis,” arXiv:2104.01678, 2021.
  19. P. Ceravolo, G. M. Tavares, S. B. Junior, and E. Damiani, “Evaluation goals for online process mining: A concept drift perspective,” IEEE Transactions on Services Computing, vol. 15, no. 4, pp. 2473–2489, 2022.
  20. W. M. Kouw and M. Loog, “A review of domain adaptation without target labels,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 3, pp. 766–785, 2021.
  21. X. Liu, C. Yoo, F. Xing, H. Oh, G. E. Fakhri, J.-W. Kang, and J. Woo, “Deep unsupervised domain adaptation: A review of recent advances and perspectives,” APSIPA Transactions on Signal and Information Processing, vol. 11, no. 1, pp. –, 2022.
  22. S. Zhao, X. Yue, S. Zhang, B. Li, H. Zhao et al., “A review of single-source deep unsupervised visual domain adaptation,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 473–493, 2022.
  23. N. L. A. Ghani, I. A. Aziz, and M. Mehat, “Concept drift detection on unlabeled data streams: A systematic literature review,” in ICBDA, 2020, pp. 61–65.
  24. C. Fahy, S. Yang, and M. Gongora, “Scarcity of labels in non-stationary data streams: A survey,” ACM Comput. Surv., vol. 55, no. 2, 2022.
  25. S. Agrahari and A. K. Singh, “Concept drift detection in data stream mining : A literature review,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 10, Part B, pp. 9523–9540, 2022.
  26. Z. Yu, J. Li, Z. Du, L. Zhu, and H. T. Shen, “A comprehensive survey on source-free domain adaptation,” arXiv:2302.11803, 2023.
  27. A. L. Suárez-Cetrulo, D. Quintana, and A. Cervantes, “A survey on machine learning for recurring concept drifting data streams,” Expert Systems with Applications, vol. 213, p. 118934, 2023.
  28. S. M. Jameel, M. A. Hashmani, H. Alhussain, M. Rehman, and A. Budiman, “A critical review on adverse effects of concept drift over machine learning classification models,” IJACSA, vol. 11, no. 1, 2020.
  29. K. Zhou, Z. Liu, Y. Qiao, T. Xiang, and C. C. Loy, “Domain generalization: A survey,” IEEE PAMI, no. 01, pp. 1–20, 2022.
  30. M. Lima, M. Neto, T. S. Filho, and R. A. de A. Fagundes, “Learning under concept drift for regression—a systematic literature review,” IEEE Access, vol. 10, pp. 45 410–45 429, 2022.
  31. M. Fan, Z. Cai, T. Zhang, and B. Wang, “A survey of deep domain adaptation based on label set classification,” Multimedia Tools Appl., vol. 81, no. 27, p. 39545–39576, 2022.
  32. S. Wang, L. L. Minku, and X. Yao, “A systematic study of online class imbalance learning with concept drift,” IEEE TNNLS, vol. 29, no. 10, pp. 4802–4821, 2018.
  33. D. Saunders, “Domain adaptation and multi-domain adaptation for neural machine translation: A survey,” Journal of Artificial Intelligence Research, vol. 75, pp. 351–424, 2022.
  34. X. Guo and H. Yu, “On the domain adaptation and generalization of pretrained language models: A survey,” arXiv:2211.03154, 2022.
  35. J. Y.-L. Chan, K. T. Bea, S. M. H. Leow, S. W. Phoong, and W. K. Cheng, “State of the art: a review of sentiment analysis based on sequential transfer learning,” Artificial Intelligence Review, vol. 56, no. 1, pp. 749–780, 2023.
  36. L. Yuan, H. Li, B. Xia, C. Gao, M. Liu, W. Yuan, and X. You, “Recent advances in concept drift adaptation methods for deep learning,” in IJCAI, 2022, pp. 5654–5661.
  37. H. Yadav and S. Sitaram, “A survey of multilingual models for automatic speech recognition,” in LREC, 2022, pp. 5071–5079.
  38. P. Bell, J. Fainberg, O. Klejch, J. Li, S. Renals, and P. Swietojanski, “Adaptation algorithms for neural network-based speech recognition: An overview,” IEEE Open Journal of Signal Processing, vol. 2, pp. 33–66, 2021.
  39. F. Bayram, B. S. Ahmed, and A. Kassler, “From concept drift to model degradation: An overview on performance-aware drift detectors,” Knowledge-Based Systems, vol. 245, p. 108632, 2022.
  40. Z. Zhu, K. Lin, and J. Zhou, “Transfer learning in deep reinforcement learning: A survey,” arXiv:2009.07888, 2020.
  41. T. Mahmood and T. Fatima, “Concept drift in streaming data: A systematic literature review,” KIET Journal of Computing and Information Sciences, vol. 4, no. 1, pp. 17–17, 2021.
  42. M. Arjovsky, L. Bottou, I. Gulrajani, and D. Lopez-Paz, “Invariant risk minimization,” arXiv:1907.02893, 2019.
  43. M. Ghifary, W. B. Kleijn, M. Zhang, and D. Balduzzi, “Domain generalization for object recognition with multi-task autoencoders,” in ICCV, 2015, pp. 2551–2559.
  44. D. Hendrycks and T. Dietterich, “Benchmarking neural network robustness to common corruptions and perturbations,” in ICLR, 2019.
  45. J. Sun, Q. Zhang, B. Kailkhura, Z. Yu, C. Xiao, and Z. M. Mao, “Benchmarking robustness of 3d point cloud recognition against common corruptions,” arXiv:2201.12296, 2022.
  46. X. Peng, B. Usman, N. Kaushik, J. Hoffman, D. Wang, and K. Saenko, “Visda: The visual domain adaptation challenge,” arXiv:1710.06924, 2017.
  47. H. Song, M. Kim, and J.-G. Lee, “SELFIE: Refurbishing unclean samples for robust deep learning,” in ICML, vol. 97.   PMLR, 2019, pp. 5907–5915.
  48. J. Wei, Z. Zhu, H. Cheng, T. Liu, G. Niu, and Y. Liu, “Learning with noisy labels revisited: A study using real-world human annotations,” in ICLR, 2022.
  49. T. Xiao, T. Xia, Y. Yang, C. Huang, and X. Wang, “Learning from massive noisy labeled data for image classification,” in CVPR, 2015, pp. 2691–2699.
  50. W. Li, L. Wang, W. Li, E. Agustsson, and L. Van Gool, “Webvision database: Visual learning and understanding from web data,” arXiv:1708.02862, 2017.
  51. D. Li, Y. Yang, Y.-Z. Song, and T. M. Hospedales, “Deeper, broader and artier domain generalization,” in ICCV, 2017, pp. 5542–5550.
  52. H. Venkateswara, J. Eusebio, S. Chakraborty, and S. Panchanathan, “Deep hashing network for unsupervised domain adaptation,” in CVPR, 2017, pp. 5018–5027.
  53. S. Zhao, B. Li, X. Yue, Y. Gu, P. Xu, R. Hu, H. Chai, and K. Keutzer, “Multi-source domain adaptation for semantic segmentation,” NeurIPS, vol. 32, 2019.
  54. D. Hendrycks, S. Basart, N. Mu, S. Kadavath, F. Wang, E. Dorundo, R. Desai, T. Zhu, S. Parajuli, M. Guo et al., “The many faces of robustness: A critical analysis of out-of-distribution generalization,” in ICCV, 2021, pp. 8340–8349.
  55. C. Fang, Y. Xu, and D. N. Rockmore, “Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias,” in ICCV, 2013, pp. 1657–1664.
  56. P. W. Koh, S. Sagawa, H. Marklund, S. M. Xie, M. Zhang et al., “Wilds: A benchmark of in-the-wild distribution shifts,” in ICML.   PMLR, 2021, pp. 5637–5664.
  57. Y. He, Z. Shen, and P. Cui, “Towards non-iid image classification: A dataset and baselines,” Pattern Recognition, vol. 110, p. 107383, 2021.
  58. M. Nǎdejde, A. Currey, B. Hsu, X. Niu, M. Federico, and G. Dinu, “Cocoa-mt: A dataset and benchmark for contrastive controlled mt with application to formality,” in NAACL, 2022, pp. 616–632.
  59. Y. Zheng, G. Chen, and M. Huang, “Out-of-domain detection for natural language understanding in dialog systems,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 28, pp. 1198–1209, 2020.
  60. A. Coucke, A. Saade, A. Ball, T. Bluche, A. Caulier et al., “Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces,” arXiv:1805.10190, 2018.
  61. S. Larson, A. Mahendran, J. J. Peper, C. Clarke, A. Lee et al., “An evaluation dataset for intent classification and out-of-scope prediction,” in EMNLP-IJCNLP, 2019.
  62. X. Zang, A. Rastogi, S. Sunkara, R. Gupta, J. Zhang, and J. Chen, “MultiWOZ 2.2 : A dialogue dataset with additional annotation corrections and state tracking baselines,” in NLP4ConvAI, 2020, pp. 109–117.
  63. C. Walker, S. Strassel, J. Medero, and K. Maeda, “Ace 2005 multilingual training corpus,” Linguistic Data Consortium, Philadelphia, vol. 57, p. 45, 2006.
  64. J. Blitzer, M. Dredze, and F. Pereira, “Biographies, Bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification,” in ACL, 2007, pp. 440–447.
  65. A. Mathur, F. Kawsar, N. Berthouze, and N. D. Lane, “Libri-adapt: a new speech dataset for unsupervised domain adaptation,” in ICASSP, 2020, pp. 7439–7443.
  66. R. Ardila, M. Branson, K. Davis, M. Henretty, M. Kohler et al., “Common voice: A massively-multilingual speech corpus,” in LREC 2020, 2020, pp. 4211–4215.
  67. C. Karouzos, G. Paraskevopoulos, and A. Potamianos, “UDALM: Unsupervised domain adaptation through language modeling,” in NAACL, 2021, pp. 2579–2590.
  68. T. Chu, Y. Liu, J. Deng, W. Li, and L. Duan, “Denoised maximum classifier discrepancy for source-free unsupervised domain adaptation,” in AAAI, vol. 36, no. 1, 2022, pp. 472–480.
  69. S. Ao, X. Li, and C. Ling, “Fast generalized distillation for semi-supervised domain adaptation,” in AAAI, vol. 31, no. 1, 2017.
  70. C.-M. Chang, B.-H. Su, S.-C. Lin, J.-L. Li, and C.-C. Lee, “A bootstrapped multi-view weighted kernel fusion framework for cross-corpus integration of multimodal emotion recognition,” in ACII, 2017, pp. 377–382.
  71. C.-C. Lu, J.-L. Li, and C.-C. Lee, “Learning an arousal-valence speech front-end network using media data in-the-wild for emotion recognition,” in AVEC, 2018, pp. 99–105.
  72. R. Elwell and R. Polikar, “Incremental learning of concept drift in nonstationary environments,” IEEE Transactions on Neural Networks, vol. 22, no. 10, pp. 1517–1531, 2011.
  73. I. Zliobaite, “How good is the electricity benchmark for evaluating concept drift adaptation,” arXiv:1301.3524, 2013.
  74. J. A. Blackard and D. J. Dean, “Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables,” Computers and electronics in agriculture, vol. 24, no. 3, pp. 131–151, 1999.
  75. V. Losing, B. Hammer, and H. Wersing, “Interactive online learning for obstacle classification on a mobile robot,” in IJCNN, 2015, pp. 1–8.
  76. ——, “Knn classifier with self adjusting memory for heterogeneous concept drift,” in ICDM, 2016, pp. 291–300.
  77. I. Žliobaitė, “Combining similarity in time and space for training set formation under concept drift,” Intelligent Data Analysis, vol. 15, no. 4, pp. 589–611, 2011.
  78. V. M. Souza, D. M. dos Reis, A. G. Maletzke, and G. E. Batista, “Challenges in benchmarking stream learning algorithms with real-world data,” Data Mining and Knowledge Discovery, vol. 34, pp. 1805–1858, 2020.
  79. J. Yang, K. Zhou, Y. Li, and Z. Liu, “Generalized out-of-distribution detection: A survey,” arXiv:2110.11334, 2021.
  80. P. Morteza and Y. Li, “Provable guarantees for understanding out-of-distribution detection,” in AAAI, vol. 36, no. 7, 2022, pp. 7831–7840.
  81. Y. Sun, C. Guo, and Y. Li, “ReAct: out-of-distribution detection with rectified activations,” in NeurIPS, vol. 34, 2021, pp. 144–157.
  82. Y. Sun, Y. Ming, X. Zhu, and Y. Li, “Out-of-distribution detection with deep nearest neighbors,” in ICML, vol. 162.   PMLR, 2022, pp. 20 827–20 840.
  83. J. Winkens, R. Bunel, A. G. Roy, R. Stanforth, V. Natarajan et al., “Contrastive training for improved out-of-distribution detection,” arXiv:2007.05566, 2020.
  84. S. Mohseni, M. Pitale, J. Yadawa, and Z. Wang, “Self-supervised learning for generalizable out-of-distribution detection,” in AAAI, vol. 34, no. 04, 2020, pp. 5216–5223.
  85. X. Du, G. Gozum, Y. Ming, and Y. Li, “SIREN: Shaping representations for detecting out-of-distribution objects,” in NeurIPS, 2022.
  86. D. Jin, S. Gao, S. Kim, Y. Liu, and D. Hakkani-Tür, “Towards textual out-of-domain detection without in-domain labels,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 30, pp. 1386–1395, 2022.
  87. J. Zhang, J. Yang, P. Wang, H. Wang, Y. Lin et al., “OpenOOD v1.5: Enhanced benchmark for out-of-distribution detection,” in arXiv preprint arXiv:2306.09301, 2023.
  88. K. Kirchheim, M. Filax, and F. Ortmeier, “PyTorch-OOD: A library for out-of-distribution detection based on PyTorch,” in CVPR Workshops, 2022, pp. 4351–4360.
  89. J. Wang, C. Lan, C. Liu, Y. Ouyang, T. Qin et al., “Generalizing to unseen domains: A survey on domain generalization,” IEEE Transactions on Knowledge and Data Engineering, 2022.
  90. F. Qiao, L. Zhao, and X. Peng, “Learning to learn single domain generalization,” in CVPR, 2020.
  91. F. Wang, Z. Han, Y. Gong, and Y. Yin, “Exploring domain-invariant parameters for source free domain adaptation,” in CVPR, 2022, pp. 7151–7160.
  92. Y. Kim, D. Cho, and S. Hong, “Towards privacy-preserving domain adaptation,” IEEE Signal Processing Letters, vol. 27, pp. 1675–1679, 2020.
  93. N. Ding, Y. Xu, Y. Tang, C. Xu, Y. Wang, and D. Tao, “Source-free domain adaptation via distribution estimation,” in CVPR, 2022, pp. 7212–7222.
  94. H. Xia, H. Zhao, and Z. Ding, “Adaptive adversarial network for source-free domain adaptation,” in ICCV, 2021, pp. 9010–9019.
  95. A. Frikha, H. Chen, D. Krompaß, T. Runkler, and V. Tresp, “Towards data-free domain generalization,” in NeurIPS Workshop, 2021.
  96. H. Niu, H. Li, F. Zhao, and B. Li, “Domain-unified prompt representations for source-free domain generalization,” arXiv:2209.14926, 2022.
  97. J. Li, M. L. Seltzer, X. Wang, R. Zhao, and Y. Gong, “Large-scale domain adaptation via teacher-student learning,” Proc. Interspeech, pp. 2386–2390, 2017.
  98. D. Kim, Y. Yoo, S. Park, J. Kim, and J. Lee, “SelfReg: Self-supervised contrastive regularization for domain generalization,” in ICCV, 2021, pp. 9619–9628.
  99. H. Tang and K. Jia, “Discriminative adversarial domain adaptation,” in AAAI, vol. 34, 2020, pp. 5940–5947.
  100. J. Yang, J. Liu, N. Xu, and J. Huang, “Tvt: Transferable vision transformer for unsupervised domain adaptation,” in WACV, 2023, pp. 520–530.
  101. J. Gideon, M. G. McInnis, and E. M. Provost, “Improving cross-corpus speech emotion recognition with adversarial discriminative domain generalization (ADDoG),” IEEE Transactions on Affective Computing, vol. 12, no. 4, pp. 1055–1068, 2019.
  102. A. Rozantsev, M. Salzmann, and P. Fua, “Beyond sharing weights for deep domain adaptation,” IEEE PAMI, vol. 41, no. 4, pp. 801–814, 2018.
  103. B. Sun, J. Feng, and K. Saenko, “Return of frustratingly easy domain adaptation,” in AAAI, vol. 30, no. 1, 2016.
  104. G. Kang, L. Jiang, Y. Yang, and A. G. Hauptmann, “Contrastive adaptation network for unsupervised domain adaptation,” in CVPR, 2019.
  105. J. Shen, Y. Qu, W. Zhang, and Y. Yu, “Wasserstein distance guided representation learning for domain adaptation,” in AAAI, vol. 32, no. 1, 2018.
  106. Y. Li, N. Wang, J. Shi, J. Liu, and X. Hou, “Revisiting batch normalization for practical domain adaptation,” arXiv:1603.04779, 2016.
  107. Z. Lipton, Y.-X. Wang, and A. Smola, “Detecting and correcting for label shift with black box predictors,” in ICML.   PMLR, 2018, pp. 3122–3130.
  108. K. Azizzadenesheli, A. Liu, F. Yang, and A. Anandkumar, “Regularized learning for domain adaptation under label shifts,” in ICLR, 2019.
  109. L. Chen, M. Zaharia, and J. Y. Zou, “Is unsupervised performance estimation impossible when both covariates and labels shift?” in NeurIPS Workshop, 2022.
  110. R. Wu, C. Guo, Y. Su, and K. Q. Weinberger, “Online adaptation to label distribution shift,” in NeurIPS, vol. 34, 2021, pp. 11 340–11 351.
  111. H. Song, M. Kim, D. Park, Y. Shin, and J.-G. Lee, “Learning from noisy labels with deep neural networks: A survey,” IEEE TNNLS, 2022.
  112. A. Kumar, P. K. Sharma, A. Illa, S. Venkatapathy et al., “Learning under label noise for robust spoken language understanding systems,” in Proc. Interspeech 2022, 2022, pp. 3463–3467.
  113. Z. Han, X.-J. Gui, C. Cui, and Y. Yin, “Towards accurate and robust domain adaptation under noisy environments,” in IJCAI, 2021, pp. 2269–2276.
  114. Q. Yu, A. Hashimoto, and Y. Ushiku, “Divergence optimization for noisy universal domain adaptation,” in CVPR, 2021, pp. 2515–2524.
  115. W. Chen, L. Lin, S. Yang, D. Xie, S. Pu, and Y. Zhuang, “Self-supervised noisy label learning for source-free unsupervised domain adaptation,” in IROS, 2022, pp. 10 185–10 192.
  116. L. Yi, G. Xu, P. Xu, J. Li, R. Pu, C. Ling, I. McLeod, and B. Wang, “When source-free domain adaptation meets learning with noisy labels,” in ICLR, 2023.
  117. A. Parnami and M. Lee, “Learning from few examples: A summary of approaches to few-shot learning,” arXiv:2203.04291, 2022.
  118. Z. Chi, L. Gu, H. Liu, Y. Wang, Y. Yu, and J. Tang, “MetaFSCIL: A meta-learning approach for few-shot class incremental learning,” in CVPR, 2022, pp. 14 166–14 175.
  119. Y. Song, T. Wang, P. Cai, S. K. Mondal, and J. P. Sahoo, “A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities,” ACM Comput. Surv., 2023.
  120. A. Zhao, M. Ding, Z. Lu, T. Xiang, Y. Niu, J. Guan, and J.-R. Wen, “Domain-adaptive few-shot learning,” in WACV, 2021, pp. 1390–1399.
  121. X. Yue, Z. Zheng, S. Zhang, Y. Gao, T. Darrell et al., “Prototypical cross-domain self-supervised learning for few-shot unsupervised domain adaptation,” in CVPR, 2021, pp. 13 834–13 844.
  122. Z. Hu, Y. Sun, and Y. Yang, “Switch to generalize: Domain-switch learning for cross-domain few-shot classification,” in ICLR, 2022.
  123. F. Pourpanah, M. Abdar, Y. Luo, X. Zhou, R. Wang, C. P. Lim, X.-Z. Wang, and Q. J. Wu, “A review of generalized zero-shot learning methods,” IEEE PAMI, 2022.
  124. C. Zhou, Q. Li, C. Li, J. Yu, Y. Liu, G. Wang et al., “A comprehensive survey on pretrained foundation models: A history from BERT to ChatGPT,” arXiv:2302.09419, 2023.
  125. Y. Du, Z. Liu, J. Li, and W. X. Zhao, “A survey of vision-language pre-trained models,” in IJCAI, 2022, pp. 5436–5443.
  126. W. Wang, J. Dai, Z. Chen, Z. Huang, Z. Li et al., “Internimage: Exploring large-scale vision foundation models with deformable convolutions,” in CVPR, 2023, pp. 14 408–14 419.
  127. A. Baevski, Y. Zhou, A. Mohamed, and M. Auli, “wav2vec 2.0: A framework for self-supervised learning of speech representations,” NeurIPS, vol. 33, pp. 12 449–12 460, 2020.
  128. Y. Tian, X. Chen, and S. Ganguli, “Understanding self-supervised learning dynamics without contrastive pairs,” in ICML.   PMLR, 2021, pp. 10 268–10 278.
  129. Q. Garrido, Y. Chen, A. Bardes, L. Najman, and Y. LeCun, “On the duality between contrastive and non-contrastive self-supervised learning,” in ICLR, 2023.
  130. A. Baevski, W.-N. Hsu, Q. Xu, A. Babu, J. Gu, and M. Auli, “Data2vec: A general framework for self-supervised learning in speech, vision and language,” in ICML.   PMLR, 2022, pp. 1298–1312.
  131. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh et al., “Learning transferable visual models from natural language supervision,” in ICML.   PMLR, 2021, pp. 8748–8763.
  132. A. Babu, C. Wang, A. Tjandra, K. Lakhotia, Q. Xu et al., “Xls-r: Self-supervised cross-lingual speech representation learning at scale,” arXiv, vol. abs/2111.09296, 2021.
  133. T. L. Scao, A. Fan, C. Akiki, E. Pavlick, S. Ilić et al., “Bloom: A 176b-parameter open-access multilingual language model,” arXiv:2211.05100, 2022.
  134. N. Ding, Y. Qin, G. Yang, F. Wei, Z. Yang et al., “Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models,” arXiv:2203.06904, 2022.
  135. N. Houlsby, A. Giurgiu, S. Jastrzebski, B. Morrone, Q. De Laroussilhe et al., “Parameter-efficient transfer learning for NLP,” in ICML, vol. 97.   PMLR, 2019, pp. 2790–2799.
  136. X. L. Li and P. Liang, “Prefix-tuning: Optimizing continuous prompts for generation,” in IJCNLP-AACL, 2021, pp. 4582–4597.
  137. B. Lester, R. Al-Rfou, and N. Constant, “The power of scale for parameter-efficient prompt tuning,” in Proceedings of EMNLP, 2021, pp. 3045–3059.
  138. E. J. Hu, yelong shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “Lora: Low-rank adaptation of large language models,” in ICLR, 2022.
  139. J. He, C. Zhou, X. Ma, T. Berg-Kirkpatrick, and G. Neubig, “Towards a unified view of parameter-efficient transfer learning,” in ICLR, 2022.
  140. Y. Sun, X. Wang, L. Zhuang, J. Miller, M. Hardt, and A. A. Efros, “Test-time training with self-supervision for generalization under distribution shifts,” in ICML, 2020.
  141. Z. Chi, Y. Wang, Y. Yu, and J. Tang, “Test-time fast adaptation for dynamic scene deblurring via meta-auxiliary learning,” in CVPR, 2021, pp. 9137–9146.
  142. S. Goyal, M. Sun, A. Raghunathan, and J. Z. Kolter, “Test time adaptation via conjugate pseudo-labels,” in NeurIPS, 2022.
  143. D. Chen, D. Wang, T. Darrell, and S. Ebrahimi, “Contrastive test-time adaptation,” in CVPR, 2022.
  144. Y. Liu, P. Kothari, B. van Delft, B. Bellot-Gurlet, T. Mordan, and A. Alahi, “Ttt++: When does self-supervised test-time training fail or thrive?” in NeurIPS, vol. 34.   Curran Associates, Inc., 2021, pp. 21 808–21 820.
  145. Y. Gandelsman, Y. Sun, X. Chen, and A. A. Efros, “Test-time training with masked autoencoders,” in NeurIPS, 2022.
  146. Y. Su, X. Xu, and K. Jia, “Revisiting realistic test-time training: Sequential inference and adaptation by anchored clustering,” in NeurIPS, 2022.
  147. Y. Iwasawa and Y. Matsuo, “Test-time classifier adjustment module for model-agnostic domain generalization,” NeurIPS, vol. 34, pp. 2427–2440, 2021.
  148. S. Niu, J. Wu, Y. Zhang, Y. Chen, S. Zheng, P. Zhao, and M. Tan, “Efficient test-time model adaptation without forgetting,” in ICML.   PMLR, 2022, pp. 16 888–16 905.
  149. Q. Wang, O. Fink, L. Van Gool, and D. Dai, “Continual test-time domain adaptation,” in CVPR, 2022, pp. 7201–7211.
  150. A. Søgaard, S. Ebert, J. Bastings, and K. Filippova, “We need to talk about random splits,” in EACL, 2021, pp. 1823–1832.
  151. J. Gama, P. Medas, G. Castillo, and P. Rodrigues, “Learning with drift detection,” in Advances in Artificial Intelligence–SBIA.   Springer, 2004, pp. 286–295.
  152. A. Bifet and R. Gavalda, “Learning from time-changing data with adaptive windowing,” in SDM.   SIAM, 2007, pp. 443–448.
  153. A. Liu, J. Lu, Y. Song, J. Xuan, and G. Zhang, “Concept drift detection delay index,” IEEE Transactions on Knowledge and Data Engineering, pp. 1–1, 2022.
  154. S. Yu, X. Wang, and J. C. Príncipe, “Request-and-reverify: hierarchical hypothesis testing for concept drift detection with expensive labels,” in IJCAI, 2018, pp. 3033–3039.
  155. P. Sidhu and M. Bhatia, “An online ensembles approach for handling concept drift in data streams: diversified online ensembles detection,” International Journal of Machine Learning and Cybernetics, vol. 6, no. 6, pp. 883–909, 2015.
  156. I. Khamassi, M. Sayed-Mouchaweh, M. Hammami, and K. Ghédira, “A new combination of diversity techniques in ensemble classifiers for handling complex concept drift,” Learning from Data Streams in Evolving Environments: Methods and Applications, pp. 39–61, 2019.
  157. R. Anderson, Y. S. Koh, G. Dobbie, and A. Bifet, “Recurring concept meta-learning for evolving data streams,” Expert Systems with Applications, vol. 138, p. 112832, 2019.
  158. H. Yu, Q. Zhang, T. Liu, J. Lu, Y. Wen, and G. Zhang, “Meta-add: A meta-learning based pre-trained model for concept drift active detection,” Information Sciences, vol. 608, pp. 996–1009, 2022.
  159. A. Zubaroğlu and V. Atalay, “Data stream clustering: a review,” Artificial Intelligence Review, vol. 54, no. 2, pp. 1201–1236, 2021.
  160. G. Oliveira, L. L. Minku, and A. L. Oliveira, “Tackling virtual and real concept drifts: An adaptive gaussian mixture model approach,” IEEE Transactions on Knowledge and Data Engineering, 2021.
  161. A. Liu, J. Lu, F. Liu, and G. Zhang, “Accumulating regional density dissimilarity for concept drift detection in data streams,” Pattern Recognition, vol. 76, pp. 256–272, 2018.
  162. A. Castellani, S. Schmitt, and B. Hammer, “Task-sensitive concept drift detector with constraint embedding,” in SSCI.   IEEE, 2021, pp. 01–08.
  163. W. Li, X. Yang, W. Liu, Y. Xia, and J. Bian, “DDG-DA: Data distribution generation for predictable concept drift adaptation,” in AAAI, vol. 36, no. 4, 2022, pp. 4092–4100.
  164. C. Raab, M. Heusinger, and F.-M. Schleif, “Reactive soft prototype computing for concept drift streams,” Neurocomputing, vol. 416, pp. 340–351, 2020.
  165. P. Li, Y. Liu, Y. Hu, Y. Zhang, X. Hu, and K. Yu, “A drift-sensitive distributed lstm method for short text stream classification,” IEEE Transactions on Big Data, vol. 9, no. 1, pp. 341–357, 2023.
  166. A. Liu, J. Lu, and G. Zhang, “Diverse instance-weighting ensemble based on region drift disagreement for concept drift adaptation,” IEEE Trans. NNLS, vol. 32, no. 1, pp. 293–307, 2021.
  167. H. Ghomeshi, M. M. Gaber, and Y. Kovalchuk, “Eacd: evolutionary adaptation to concept drifts in data streams,” Data Mining and Knowledge Discovery, vol. 33, pp. 663–694, 2019.
  168. M. Heusinger, C. Raab, and F.-M. Schleif, “Passive concept drift handling via variations of learning vector quantization,” Neural Computing and Applications, vol. 34, no. 1, pp. 89–100, 2022.
  169. W. Zheng, P. Zhao, G. Chen, H. Zhou, and Y. Tian, “A hybrid spiking neurons embedded lstm network for multivariate time series learning under concept-drift environment,” IEEE Transactions on Knowledge and Data Engineering, pp. 1–1, 2022.
  170. I. Chalkidis and A. Søgaard, “Improved multi-label classification under temporal concept drift: Rethinking group-robust algorithms in a label-wise setting,” in ACL, 2022, pp. 2441–2454.
  171. Z. Li, W. Huang, Y. Xiong, S. Ren, and T. Zhu, “Incremental learning imbalanced data streams with concept drift: The dynamic updated ensemble algorithm,” Knowledge-Based Systems, vol. 195, p. 105694, 2020.
  172. H. J. Jung and M. Lease, “Modeling temporal crowd work quality with limited supervision,” in AAAI, vol. 3, 2015, pp. 83–91.
  173. I. Abraham, O. Alonso, V. Kandylas, R. Patel, S. Shelford, and A. Slivkins, “How many workers to ask? adaptive exploration for collecting high quality labels,” in SIGIR.   Association for Computing Machinery, 2016, p. 473–482.
  174. T. Goyal, T. McDonnell, M. Kutlu, T. Elsayed, and M. Lease, “Your behavior signals your reliability: Modeling crowd behavioral traces to ensure quality relevance annotations,” AAAI, vol. 6, no. 1, pp. 41–49, 2018.
  175. F. Zafari, I. Moser, and T. Baarslag, “Modelling and analysis of temporal preference drifts using a component-based factorised latent approach,” Expert Systems with Applications, vol. 116, pp. 186–208, 2019.
  176. Y. Xie, J. Li, T. Zhu, and C. Liu, “Continuous-valued annotations aggregation for heart rate detection,” IEEE Access, vol. 7, pp. 37 664–37 671, 2019.
  177. S. Liu, S. Xue, J. Wu, C. Zhou, J. Yang, Z. Li, and J. Cao, “Online active learning for drifting data streams,” IEEE Trans. NNLS, vol. 34, no. 1, pp. 186–200, 2023.
  178. X. Zhan, Q. Wang, K.-h. Huang, H. Xiong, D. Dou, and A. B. Chan, “A comparative survey of deep active learning,” arXiv:2203.13450, 2022.
  179. Y. Yu, R. Zhang, R. Xu, J. Zhang, J. Shen, and C. Zhang, “Cold-start data selection for few-shot language model fine-tuning: A prompt-based uncertainty propagation approach,” arXiv:2209.06995, 2022.
  180. G. Hacohen, A. Dekel, and D. Weinshall, “Active learning on a budget: Opposite strategies suit high and low budgets,” in ICML.   PMLR, 2022, pp. 8175–8195.
  181. Ł. Korycki and B. Krawczyk, “Streaming decision trees for lifelong learning,” in ECML PKDD.   Springer, 2021, pp. 502–518.
  182. M. Pratama, C. Za’in, A. Ashfahani, Y. S. Ong, and W. Ding, “Automatic construction of multi-layer perceptron network from streaming examples,” in CIKM, 2019, pp. 1171–1180.
  183. D. Liu, Y. Wu, and H. Jiang, “Fp-elm: An online sequential learning algorithm for dealing with concept drift,” Neurocomputing, vol. 207, pp. 322–334, 2016.
  184. G. M. van de Ven, T. Tuytelaars, and A. S. Tolias, “Three types of incremental learning,” Nature Machine Intelligence, pp. 1–13, 2022.
  185. L. Korycki and B. Krawczyk, “Class-incremental experience replay for continual learning under concept drift,” in CVPR Workshops, June 2021, pp. 3649–3658.
  186. A. A. Darem, F. A. Ghaleb, A. A. Al-Hashmi, J. H. Abawajy, S. M. Alanazi, and A. Y. Al-Rezami, “An adaptive behavioral-based incremental batch learning malware variants detection model using concept drift detection and sequential deep learning,” IEEE Access, vol. 9, pp. 97 180–97 196, 2021.
  187. A. M. N. Taufique, C. S. Jahan, and A. Savakis, “Unsupervised continual learning for gradually varying domains,” in CVPR Workshops, 2022, pp. 3740–3750.
  188. J. Li, M. Jing, H. Su, K. Lu, L. Zhu, and H. T. Shen, “Faster domain adaptation networks,” IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 12, pp. 5770–5783, 2022.
  189. B. Jiao, Y. Guo, D. Gong, and Q. Chen, “Dynamic ensemble selection for imbalanced data streams with concept drift,” IEEE Trans. NNLS, pp. 1–14, 2022.
  190. B. Jiao, Y. Guo, C. Yang, J. Pu, Z. Zheng, and D. Gong, “Incremental weighted ensemble for data streams with concept drift,” IEEE Transactions on Artificial Intelligence, pp. 1–12, 2022.
  191. C.-C. J. Kuo and A. M. Madni, “Green learning: Introduction, examples and outlook,” Journal of Visual Communication and Image Representation, p. 103685, 2022.
  192. X. Huang, D. Kroening, W. Ruan, J. Sharp et al., “A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability,” Computer Science Review, vol. 37, p. 100270, 2020.
  193. T. Bai, J. Luo, J. Zhao, B. Wen, and Q. Wang, “Recent advances in adversarial training for adversarial robustness,” in IJCAI, 2021, pp. 4312–4321.
  194. J. Wang, H. Xixu, W. Hou, H. Chen, R. Zheng, Y. Wang et al., “On the robustness of chatgpt: An adversarial and out-of-distribution perspective,” in ICLR Workshop, 2023.
  195. K. Jin, X. Cheng, J. Yang, and K. Shen, “Differentially private correlation alignment for domain adaptation.” in IJCAI, vol. 21, 2021, pp. 3649–3655.
  196. D. Peterson, P. Kanani, and V. J. Marathe, “Private federated learning with domain adaptation,” arXiv:1912.06733, 2019.
  197. D. M. Manias, I. Shaer, L. Yang, and A. Shami, “Concept drift detection in federated networked systems,” in GLOBECOM, 2021, pp. 1–6.
  198. F. E. Casado, D. Lema, M. F. Criado, R. Iglesias, C. V. Regueiro, and S. Barro, “Concept drift detection and adaptation for federated and continual learning,” Multimedia Tools and Applications, pp. 1–23, 2022.
  199. D. Mukherjee, F. Petersen, M. Yurochkin, and Y. Sun, “Domain adaptation meets individual fairness. and they get along.” in NeurIPS, 2022.
  200. H. Wang, J. Hong, J. Zhou, and Z. Wang, “How robust is your fairness? evaluating and sustaining fairness under unseen distribution shifts,” arXiv:2207.01168, 2022.
  201. D. Madras, E. Creager, T. Pitassi, and R. Zemel, “Learning adversarially fair and transferable representations,” in ICML.   PMLR, 2018, pp. 3384–3393.
  202. J. Zenisek, N. Wild, and J. Wolfartsberger, “Investigating the potential of smart manufacturing technologies,” Procedia Computer Science, vol. 180, pp. 507–516, 2021.
  203. J. a. Gama, I. Žliobaitundefined, A. Bifet, M. Pechenizkiy, and A. Bouchachia, “A survey on concept drift adaptation,” ACM Comput. Surv., vol. 46, no. 4, 2014.
  204. C.-C. Lin, D.-J. Deng, C.-H. Kuo, and L. Chen, “Concept drift detection and adaption in big imbalance industrial iot data using an ensemble learning method of offline classifiers,” IEEE Access, vol. 7, pp. 56 198–56 207, 2019.
  205. J. J. Thiagarajan, D. Rajan, and P. Sattigeri, “Understanding behavior of clinical models under domain shifts,” in ACM SIGKDD, 2019.
  206. L. Ju, X. Wang, L. Wang, D. Mahapatra, X. Zhao, Q. Zhou, T. Liu, and Z. Ge, “Improving medical images classification with label noise using dual-uncertainty estimation,” IEEE Transactions on Medical Imaging, vol. 41, no. 6, pp. 1533–1546, 2022.
Citations (1)
View on Semantic Scholar

Summary

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets