Identifying useful learnwares via learnable specification

Abstract

The learnware paradigm has been proposed as a new manner for reusing models from a market of various well-trained models, which can relieve users’ burden of training a new model from scratch. A learnware consists of a well-trained model and a specification which explains the purpose or specialty of the model without revealing data. By specification matching, the market can identify the most useful learnwares for users’ tasks. Prior art attempted to generate the specification by a reduced kernel mean embedding approach. However, such kind of specification is defined by some pre-designed kernel function, which lacks flexibility. In this paper, we advance a methodology for direct specification learning from data, introducing a novel neural network named SpecNet for this purpose. Our approach accepts unordered datasets as input and subsequently produces specification vectors in a latent space. Notably, the flexibility and efficiency of our learned specifications are underscored by their derivation from diverse tasks, rendering them particularly adept for learnware identification. Empirical studies provide validation for the efficacy of our proposed approach.

Graphical abstract

Keywords

learnware / specification / model reuse

Zhi-Yu Shen received the BEng degree in computer science and technology from Nanjing University, China in 2014. Currently he is a PhD candidate in the Department of Computer Science and Technology, Nanjing University, and is a member of the LAMDA Group. His research interests mainly include machine learning and data mining, especially in domain adaptation and transfer learning

Ming Li is currently a professor with the LAMDA group, the National Key Laboratory for Novel Software Technology, Nanjing University, China. His major research interests include machine learning and data mining, especially on software mining. He has served as the area chair of IJCAI, IEEE ICDM, etc., senior PC member of the premium conferences in artificial intelligence such as AAAI, and PC members for other premium conferences such as KDD, NeurIPS, and ICML. He is the founding chair of the International Workshop on Software Mining. He has been granted various awards including the PAKDD Early Career Award, the NSFC Excellent Youth Award, the New Century Excellent Talents program of the Education Ministry of China, etc

References

[1] Zhou Z H . Learnware: on the future of machine learning. Frontiers of Computer Science, 2016, 10( 4): 589–590

[2] Tan P, Tan Z H, Jiang Y, Zhou Z H . Towards enabling learnware to handle heterogeneous feature spaces. Machine Learning, 2024, 113( 4): 1839–1860

[3] Zhang Y J, Yan Y H, Zhao P, Zhou Z H. Towards enabling learnware to handle unseen jobs. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence. 2021, 10964−10972

[4] Guo L Z, Zhou Z, Li Y F, Zhou Z H. Identifying useful learnwares for heterogeneous label spaces. In: Proceedings of the 40th International Conference on Machine Learning. 2023, 12122−12131

[5] Hoffman J, Tzeng E, Park T, Zhu J Y, Isola P, Saenko K, Efros A, Darrell T. CyCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning. 2018, 1994−2003

[6] Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan J W. A theory of learning from different domains. Machine Learning, 2010, 79(1−2): 151−175

[7] Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on Machine Learning. 2015, 1180−1189

[8] Kumar A, Ma T, Liang P. Understanding self-training for gradual domain adaptation. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 507

[9] Luo Y, Wang Z, Huang Z, Baktashmotlagh M. Progressive graph learning for open-set domain adaptation. In: Proceedings of the 37th International Conference on Machine Learning. 2020, 600

[10] Wu X Z, Xu W, Liu S, Zhou Z H . Model reuse with reduced kernel mean embedding specification. IEEE Transactions on Knowledge and Data Engineering, 2023, 35( 1): 699–710

[11] Smola A, Gretton A, Song L, Schölkopf B. A hilbert space embedding for distributions. In: Proceedings of the 18th International Conference on Algorithmic Learning Theory. 2007, 13−31

[12] Ding Y X, Zhou Z H. Boosting-based reliable model reuse. In: Proceedings of the 12th Asian Conference on Machine Learning. 2020, 145−160

[13] Ben-David S, Blitzer J, Crammer K, Pereira F. Analysis of representations for domain adaptation. In: Proceedings of the 19th International Conference on Neural Information Processing Systems. 2006, 137−144

[14] Germain P, Habrard A, Laviolette F, Morvant E. A new PAC-Bayesian perspective on domain adaptation. In: Proceedings of the 33rd International Conference on Machine Learning. 2016, 859−868

[15] Liu M Y, Tuzel O. Coupled generative adversarial networks. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 469−477

[16] Chang W, Shi Y, Tuan H D, Wang J. Unified optimal transport framework for universal domain adaptation. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 2140

[17] Zhu Y, Wu X, Qiang J, Yuan Y, Li Y . Representation learning via an integrated autoencoder for unsupervised domain adaptation. Frontiers of Computer Science, 2023, 17( 5): 175334

[18] Pan S J, Yang Q . A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22( 10): 1345–1359

[19] Ding Y X, Wu X Z, Zhou K, Zhou Z H. Pre-trained model reusability evaluation for small-data transfer learning. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. 2022, 2710

[20] Wang B, Mendez J A, Cai M B, Eaton E. Transfer learning via minimizing the performance gap between domains. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. 2019, 955

[21] Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De Laroussilhe Q, Gesmundo A, Attariyan M, Gelly S. Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th International Conference on Machine Learning. 2019, 2790−2799

[22] Yang Y, Guo J, Li G, Li L, Li W, Yang J . Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning. Frontiers of Computer Science, 2024, 18( 1): 181335

[23] Wang Z, Dai Z, Póczos B, Carbonell J. Characterizing and avoiding negative transfer. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 11293−11302

[24] Maturana D, Scherer S. VoxNet: a 3D convolutional neural network for real-time object recognition. In: Proceedings of 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems. 2015, 922−928

[25] Qi C R, Su H, Nießner M, Dai A, Yan M, Guibas L J. Volumetric and multi-view CNNs for object classification on 3D data. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 5648−5656

[26] Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J. 3D ShapeNets: a deep representation for volumetric shapes. In: Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. 2015, 1912−1920

[27] Vinyals O, Bengio S, Kudlur M. Order matters: sequence to sequence for sets. In: Proceedings of the 4th International Conference on Learning Representations. 2016

[28] Qi Charles R, Su H, Kaichun M, Guibas L J. PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017, 77−85

[29] Le Y, Yang X. Tiny ImageNet visual recognition challenge. In: Proceedings of the Stanford CS231N Convolutional Neural Networks for Visual Recognition. 2015

[30] Krizhevsky A. Learning multiple layers of features from tiny images. Technical Report TR-2009. Toronto: University of Toronto, 2009

Acknowledgements

This research was supported by the National Natural Science Foundation of China (Grant Nos. 62076121, 61921006) and the Major Program (JD) of Hubei Province (2023BAA024).

Competing interests

Ming Li is an Editorial Board member of the journal and a co-author of this article. To minimize bias, they were excluded from all editorial decision-making related to the acceptance of this article for publication. The remaining authors declare no conflict of interest.

RIGHTS & PERMISSIONS

2025 Higher Education Press