AFGN: Adaptive Filtering Graph Neural Network for Few-Shot Learning
Source abstract
Abstract
The combination of few-shot learning and graph neural networks can effectively solve the issue of extracting more useful information from limited data. However, most graph-based few-shot models only consider the global feature information extracted by the backbone during the construction process, while ignoring the dependency information hidden within the features. Additionally, the essence of graph convolution is the filtering of graph signals, and the majority of graph-based few-shot models construct fixed, single-property filters to process these graph signals. Therefore, in this paper, we propose an Adaptive Filtering Graph Convolutional Neural Network (AFGN) for few-shot classification. AFGN explores the hidden dependency information within the features, providing a new approach for constructing graph tasks in few-shot scenarios. Furthermore, we design an adaptive filter for the graph convolution of AFGN, which can adaptively adjust its strategy for acquiring high and low-frequency information from graph signals based on different few-shot episodic tasks. We conducted experiments on three standard few-shot benchmarks, including image recognition and fine-grained categorization. The experimental results demonstrate that our AFGN performs better compared to other state-of-the-art models.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Learning and ELM · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Automation, Guangdong University of Technology, Guangzhou 510006, China
College of Electronics and Information Engineering, Shenzhen University, Shenzhen 518060, China
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, China
School of Electric Power Engineering, South China University of Technology, Guangzhou 510006, China
Funding
National Major Scientific Instruments and Equipments Development Project of National Natural Science Foundation of China
References (40)
Show source-provided references
1. Hwang, R.H., Peng, M.C., Nguyen, V.L., and Chang, Y.L. (2019). An LSTM-based deep learning approach for classifying malicious traffic at the packet level. Appl. Sci., 9.10.3390/app9163414 ↗
2. Federated learning-empowered AI-generated content in wireless networks10.1109/MNET.2024.3353377 ↗
3. Zemouri, R., Zerhouni, N., and Racoceanu, D. (2019). Deep learning in the biomedical applications: Recent and future status. Appl. Sci., 9.10.3390/app9081526 ↗
4. Li, F.F. (2003, January 13–16). A Bayesian approach to unsupervised one-shot learning of object categories. Proceedings of the Ninth IEEE International Conference on Computer Vision, Nice, France.
5. Garcia, V., and Bruna, J. (May, January 30). Few-shot learning with graph neural networks. Proceedings of the 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada.
6. HDGN: Heat diffusion graph network for few-shot learning10.1016/j.patrec.2023.04.005 ↗
7. Multi-level semantic feature augmentation for one-shot learning10.1109/TIP.2019.2910052 ↗
8. Bridging the gap between few-shot and many-shot learning via distribution calibration10.1109/TPAMI.2021.3132021 ↗
9. Ravi, S., and Larochelle, H. (2016, January 2–4). Optimization as a model for few-shot learning. Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico.
10. Finn, C., Abbeel, P., and Levine, S. (2017, January 6–11). Model-agnostic meta-learning for fast adaptation of deep networks. Proceedings of the International Conference on Machine Learning. ICML, Sydney, Australia.
11. Matching networks for one shot learning
12. Prototypical networks for few-shot learning
13. Liu, Y., Lee, J., Park, M., Kim, S., Yang, E., Hwang, S., and Yang, Y. (2019, January 6–9). Learning to propagate labels: Transductive propagation network for few-shot learning. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA.
14. Kim, J., Kim, T., Kim, S., and Yoo, C.D. (2019, January 15–20). Edge-labeling graph neural network for few-shot learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00010 ↗
15. Cheng, H., Yang, S., Zhou, J.T., Guo, L., and Wen, B. (2023, January 18–22). Frequency guidance matters in few-shot learning. Proceedings of the IEEE/CVF International Conference on Computer Vision, Vancouver, BC, Canada.10.1109/ICCV51070.2023.01085 ↗
16. Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., and Huang, J.B. (2019). A closer look at few-shot classification. arXiv.
17. Brownian distance covariance
18. Convolutional neural networks on graphs with fast localized spectral filtering
19. Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., and Hospedales, T.M. (2018, January 18–22). Learning to compare: Relation network for few-shot learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00131 ↗
20. Bertinetto, L., Henriques, J., Torr, P., and Vedaldi, A. (2019, January 6–9). Meta-learning with differentiable closed-form solvers. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA.
21. Afrasiyabi, A., Lalonde, J.F., and Gagné, C. (2020, January 23–28). Associative alignment for few-shot image classification. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part V 16.10.1007/978-3-030-58558-7_2 ↗
22. Li, A., Luo, T., Xiang, T., Huang, W., and Wang, L. (November, January 27). Few-shot learning with global class representations. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
23. Cai, Q., Pan, Y., Yao, T., Yan, C., and Mei, T. (2018, January 18–22). Memory Matching Networks for One-Shot Image Recognition. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00429 ↗
24. Ye, H.J., Hu, H., Zhan, D.C., and Sha, F. (2018). Learning embedding adaptation for few-shot learning. arXiv.
25. Gidaris, S., and Komodakis, N. (2018, January 18–22). Dynamic few-shot visual learning without forgetting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00459 ↗
26. Hu, S.X., Moreno, P.G., Xiao, Y., Shen, X., Obozinski, G., Lawrence, N.D., and Damianou, A. (2020). Empirical bayes transductive meta-learning with synthetic gradients. arXiv.
27. Yoon, S.W., Seo, J., and Moon, J. (2019, January 9–15). Tapnet: Neural network augmented with task-adaptive projection for few-shot learning. Proceedings of the International Conference on Machine Learning. PMLR, Long Beach, CA, USA.
28. Lifchitz, Y., Avrithis, Y., Picard, S., and Bursuc, A. (2019, January 15–20). Dense classification and implanting for few-shot learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00948 ↗
29. Lee, K., Maji, S., Ravichandran, A., and Soatto, S. (2019, January 15–20). Meta-learning with differentiable convex optimization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.01091 ↗
30. Chen, Y., Liu, Z., Xu, H., Darrell, T., and Wang, X. (2021, January 10–17). Meta-baseline: Exploring simple meta-learning for few-shot learning. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00893 ↗
31. Qiao, L., Shi, Y., Li, J., Wang, Y., Huang, T., and Tian, Y. (November, January 27). Transductive episodic-wise adaptive metric for few-shot learning. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea.
32. Zhou, Z., Qiu, X., Xie, J., Wu, J., and Zhang, C. (2021, January 10–17). Binocular mutual learning for improving few-shot classification. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00829 ↗
33. Afrasiyabi, A., Larochelle, H., Lalonde, J.F., and Gagné, C. (2022, January 18–24). Matching feature sets for few-shot image classification. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.10.1109/CVPR52688.2022.00881 ↗
34. Tadam: Task dependent adaptive metric for improved few-shot learning
35. Kim, J., Kim, H., and Kim, G. (2020, January 23–28). Model-agnostic boundary-adversarial sampling for test-time generalization in few-shot learning. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part I 16.10.1007/978-3-030-58452-8_35 ↗
36. Dhillon, G.S., Chaudhari, P., Ravichandran, A., and Soatto, S. (2019). A baseline for few-shot image classification. arXiv.
37. Liu, Y., Schiele, B., and Sun, Q. (2020, January 23–28). An ensemble of epoch-wise empirical bayes for few-shot learning. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIV 16.10.1007/978-3-030-58517-4_24 ↗
38. Xu, W., Xu, Y., Wang, H., and Tu, Z. (2021, January 3–7). Attentional Constellation Nets for Few-Shot Learning. Proceedings of the International Conference on Learning Representations, Virtual Event, Austria.
39. Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J.B., and Isola, P. (2020, January 23–28). Rethinking few-shot image classification: A good embedding is all you need?. Proceedings of the Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK. Proceedings, Part XIV 16.10.1007/978-3-030-58568-6_16 ↗
40. Afrasiyabi, A., Lalonde, J.F., and Gagné, C. (2021, January 10–17). Mixture-based feature space learning for few-shot image classification. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, QC, Canada.10.1109/ICCV48922.2021.00891 ↗