Abstract
Meta-learning has emerged as an effective and popular approach for few-shot learning (FSL) due to its fast adaptation to novel tasks. However, this kind of method assumes that the meta-training and testing tasks come from the same task distribution and assigns equal weights to all tasks during meta-training. This assumption limits their ability to perform well in real-world scenarios where some meta-training tasks contribute more to the testing tasks than others. To address this issue, we propose a parameter-efficient task reweighting (PETR) method, which assigns proper weights to meta-training tasks according to their contribution to the testing tasks while using few parameters. Specifically, we formulate a bi-level optimization problem to jointly learn the few-shot learning model and the task weights. In the inner loop, the meta-parameters of the few-shot learning model are updated based on a weighted training loss. In the outer loop, the task weight parameters are updated with the implicit gradient. Additionally, to address the challenge of a large number of task weight parameters, we introduce a hypothesis that significantly reduces the required parameters by considering the factors that influence the importance of each meta-training task. Empirical evaluation results on both traditional FSL and FSL with out-of-distribution (OOD) tasks show that our PETR method outperforms state-of-the-art meta-learning-based FSL methods by assigning proper weights to different meta-training tasks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Communications ACM 60(6), 84–90 (2017)
He, K., Gkioxari, G., Dollár, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference On Computer Vision, pp. 2961–2969 (2017)
Schmidhuber, J.: Evolutionary principles in self-referential learning, or on learning how to learn: the meta-meta-... hook. PhD thesis, Technische Universität München (1987)
Naik, D.K., Mammone, R.J.: Meta-neural networks that learn by learning. In: [Proceedings 1992] IJCNN International Joint Conference on Neural Networks, vol. 1, pp. 437–442. IEEE (1992)
Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In International Conference on Machine Learning, pp. 1126–1135. PMLR (2017)
Li, Z., Zhou, F., Chen, F., Li, H.: Meta-sgd: learning to learn quickly for few-shot learning. arXiv preprint arXiv:1707.09835 (2017)
Nichol, A., Schulman, J.: Reptile: a scalable metalearning algorithm, vol. 2(3), p. 4. arXiv preprint arXiv:1803.02999 (2018)
Rajeswaran, A., Finn, C., Kakade, S.M., Levine, S.: Meta-learning with implicit gradients. In: Advances in Neural Information Processing Systems 32 (2019)
Flennerhag, S., Rusu, A.A., Pascanu, R., Visin, F., Yin, H., Hadsell, R.: Meta-learning with warped gradient descent. arXiv preprint arXiv:1909.00025 (2019)
Cai, D., Sheth, R., Mackey, L., Fusi, N.: Weighted meta-learning. arXiv preprint arXiv:2003.09465 (2020)
Killamsetty, K., Li, C., Zhao, C., Chen, F., Iyer, R.: A nested bi-level optimization framework for robust few shot learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 7176–7184 (2022)
Shimodaira, H.: Improving predictive inference under covariate shift by weighting the log-likelihood function. J. Stat. Planning Inference 90(2), 227–244 (2000)
Sugiyama, M., Suzuki, T., Nakajima, S., Kashima, H., Nau, P.B., Kawanabe, M.: Direct importance estimation for covariate shift adaptation. Annals Inst. Stat. Mathem. 60(4), 699–746 (2008)
Fang, T., Nan, L., Niu, G., Sugiyama, M.: Rethinking importance weighting for deep learning under distribution shift. Adv. Neural. Inf. Process. Syst. 33, 11996–12007 (2020)
Kuang, K., Xiong, R., Cui, P., Athey, S., Li, B.: Stable prediction with model misspecification and agnostic distribution shift. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 4485–4492 (2020)
Zhang, X., Cui, P., Xu, R., Zhou, L., He, Y., Shen, Z.: Deep stable learning for out-of-distribution generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5372–5382 (2021)
Ren, M., Zeng, W., Yang, B., Urtasun, R.: Learning to reweight examples for robust deep learning. In International Conference on Machine Learning, pp. 4334–4343. PMLR (2018)
Zhou, X., et al.: Model agnostic sample reweighting for out-of-distribution learning. In: International Conference on Machine Learning, pp. 27203–27221. PMLR (2022)
Finn, C., Xu, K., Levine, S.: Probabilistic model-agnostic meta-learning. In: Advances in Neural Information Processing Systems 31 (2018)
Grant, E., Finn, C., Levine, S., Darrell, T., Griffiths, T.: Recasting gradient-based meta-learning as hierarchical bayes. arXiv preprint arXiv:1801.08930 (2018)
Ravi, S., Beatson, A.: Amortized bayesian meta-learning. In: International Conference on Learning Representations (2019)
Lee, H.B., Nam, T., Yang, E., Hwang, S.J.: Learning to perturb latent features for generalization, Meta dropout (2020)
Ni, R., Goldblum, M., Sharaf, A., Kong, K., Goldstein, T.: Data augmentation for meta-learning. In International Conference on Machine Learning, pp. 8152–8161. PMLR (2021)
Yao, H., Zhang, L., Finn, C.: Meta-learning with fewer tasks through task interpolation. arXiv preprint arXiv:2106.02695 (2021)
Vuorio, R., Sun, S.-H., Hu, H., Lim, J.J.: Multimodal model-agnostic meta-learning via task-aware modulation. In: Advances in Neural Information Processing Systems 32 (2019)
Lee, H.B., et al.: Learning to balance: Bayesian meta-learning for imbalanced and out-of-distribution tasks. arXiv preprint arXiv:1905.12917 (2019)
Baik, S., Choi, J., Kim, H., Cho, D., Min, J., Lee, K.M.: Meta-learning with task-adaptive loss function for few-shot learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9465–9474 (2021)
Liu, C., Wang, Z., Sahoo, D., Fang, Y., Zhang, K., Hoi, S.C.H.: Adaptive task sampling for meta-learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 752–769. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58523-5_44
Zhang, J., Song, J., Yao, Y., Gao, L.: Curriculum-based meta-learning. In Proceedings of the 29th ACM International Conference on Multimedia, pp. 1838–1846 (2021)
Zhou, Y., Wang, Y., Cai, J., Zhou, Y., Hu, Q., Wang, W.: Expert training: Task hardness aware meta-learning for few-shot classification. arXiv preprint arXiv:2007.06240 (2020)
Bennequin, E., Bouvier, V., Tami, M., Toubhans, A., Hudelot, C.: Bridging few-shot learning and adaptation: new challenges of support-query shift. In: Oliver, N., Pérez-Cruz, F., Kramer, S., Read, J., Lozano, J.A. (eds.) ECML PKDD 2021. LNCS (LNAI), vol. 12975, pp. 554–569. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86486-6_34
Aimen, A., Ladrecha, B., Krishnan, N.C.: Adversarial projections to tackle support-query shifts in few-shot meta-learning. In: Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, 19–23 September 2022, Proceedings, Part III, pp. 615–630. Springer (2023). https://doi.org/10.1007/978-3-031-26409-2_37
Foo, C.-S., Ng, A., et al.: Efficient multiple hyperparameter learning for log-linear models. In: Advances in Neural Information Processing Systems 20 (2007)
Okuno, T., Takeda, A., Kawana, A., Watanabe, M.: On \(l_p-\)hyperparameter learning via bilevel nonsmooth optimization. arXiv preprint arXiv:1806.01520 (2018)
Lorraine, J., Vicol, P., Duvenaud, D.: Optimizing millions of hyperparameters by implicit differentiation. In: International Conference on Artificial Intelligence and Statistics, pp. 1540–1552. PMLR (2020)
Mao, Y., Wang, Z., Liu, W., Lin, X., Xie, P.: Metaweighting: learning to weight tasks in multi-task learning. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 3436–3448 (2022)
Chen, H., Wang, X., Guan, C., Liu, Y., Zhu, W.: Auxiliary learning with joint task and data scheduling. In: International Conference on Machine Learning, pp. 3634–3647. PMLR (2022)
Franceschi, L., Frasconi, P., Salzo, S., Grazzi, R., Pontil, M.: Bilevel programming for hyperparameter optimization and meta-learning. In: International Conference on Machine Learning, pp. 1568–1577. PMLR (2018)
Lian, D., et al.: Towards fast adaptation of neural architectures with meta learning. In: International Conference on Learning Representations (2020)
Hu, Y., Wu, X., He, R.: TF-NAS: rethinking three search freedoms of latency-constrained differentiable neural architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 123–139. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58555-6_8
Chen, Z., Jiang, H., Shi, Y., Dai, B., Zhao, T.: Learning to defense by learning to attack (2019)
Tian, Y., Shen, L., Guinan, S., Li, Z., Liu, W.: Alphagan: fully differentiable architecture search for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6752–6766 (2021)
Yang, Z., Chen, Y., Hong, M., Wang, Z.: Provably global convergence of actor-critic: A case for linear quadratic regulator with ergodic cost. In: Advances in Neural Information Processing Systems 32 (2019)
Zhang, H., Chen, W., Huang, Z., Li, M., Yang, Y., Zhang, W., Wang, J.: Bi-level actor-critic for multi-agent coordination. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7325–7332 (2020)
Rüschendorf, L.: The wasserstein distance and approximation theorems. Probab. Theory Relat. Fields 70(1), 117–129 (1985)
Zhao, S., Sinha, A., He, Y., Perreault, A., Song, J., Ermon, S.: H-divergence: A decision-theoretic probability discrepancy measure
Arazo, E., Ortego, D., Albert, P., O’Connor, N., McGuinness, K.: Unsupervised label noise modeling and loss correction. In: International conference on machine learning, pp. 312–321. PMLR (2019)
Bottou, L., Bousquet, O.: The tradeoffs of large scale learning. In: Advances in Neural Information Processing Systems 20 (2008)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211–252 (2015)
Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: International Conference on Learning Representations (2017)
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
Acknowledgments
This work was partly supported by the Fundamental Research Funds for the Central Universities (2019JBZ110); the Beijing Natural Science Foundation under Grant L211016; the National Natural Science Foundation of China under Grant 62176020; the National Key Research and Development Program (2020AAA0106800); and Chinese Academy of Sciences (OEIP-O-202004).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethical Statement
The authors declare that they have no conflict of interest. All procedures performed in studies involving human participants were by the ethical standards of the institutional and national research committees. This article does not contain any studies with animals performed by any of the authors. Informed consent was obtained from all individual participants included in the study.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Lyu, Y., Jing, L., Zeng, T., Yu, J. (2023). Not All Tasks Are Equal: A Parameter-Efficient Task Reweighting Method for Few-Shot Learning. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14170. Springer, Cham. https://doi.org/10.1007/978-3-031-43415-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-43415-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43414-3
Online ISBN: 978-3-031-43415-0
eBook Packages: Computer ScienceComputer Science (R0)
