Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph
Open accessAbstract
A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · see citing works
(2008) · Journal of Machine Learning Research · Cited by 33,051 · see citing works
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · see citing works
Inductive Representation Learning on Large Graphs
Hamilton, W. L., Ying, R., & Leskovec, J. (2017) · arXiv · doi:10.48550/arxiv.1706.02216 · Cited by 10,639 · see citing works
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Finn, C., Abbeel, P., & Levine, S. (2017) · arXiv · doi:10.48550/arxiv.1703.03400 · Cited by 8,512 · see citing works
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636 · see citing works
Prototypical Networks for Few-shot LearningPreprint
Snell, J., Swersky, K., & Zemel, R. S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.05175 · Cited by 5,863 · see citing works
Matching Networks for One Shot LearningPreprint
Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K., & Wierstra, D. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04080 · Cited by 4,874 · see citing works
(2006) · Cited by 3,624 · see citing works
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. (2020) · UTS ePRESS (University of Technology Sydney) · Cited by 3,174 · see citing works
Self-citationHuman-level concept learning through probabilistic program induction
Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B. (2015) · Science · doi:10.1126/science.aab3050 · Cited by 2,817 · see citing works
Optimization as a Model for Few-Shot Learning
Ravi, S., & Larochelle, H. (2017) · International Conference on Learning Representations · Cited by 2,766 · see citing works
A brief introduction to weakly supervised learning
Zhou, Z.-H. (2018) · National Science Review · doi:10.1093/nsr/nwx106 · Cited by 1,899 · see citing works
Learning from labeled and unlabeled data with label propagation
Zhu, X., & Ghahramani, Z. (2002) · Cited by 1,547 · see citing works
TADAM: Task dependent adaptive metric for improved few-shot learningPreprint
Oreshkin, B. N., Rodríguez, P., & Lacoste, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.10123 · Cited by 1,094 · see citing works
A Simple Neural Attentive Meta-LearnerPreprint
Mishra, N., Rohaninejad, M., Chen, X., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.03141 · Cited by 961 · see citing works
Few-Shot Learning with Graph Neural NetworksPreprint
García, V., & Bruna, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04043 · Cited by 863 · see citing works
Searching for a Robust Neural Architecture in Four GPU Hours
Dong, X., & Yang, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00186 · Cited by 658 · see citing works
Attributed Graph Clustering: A Deep Attentional Embedding Approach
Wang, C., Pan, S., Hu, R., Long, G., Jiang, J. B., & Zhang, C. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/509 · Cited by 619 · see citing works
Self-citationReptile: a Scalable Metalearning AlgorithmPreprint
Nichol, A., & Schulman, J. (2018) · arXiv (Cornell University) · Cited by 548 · see citing works
Schapiro, A. C., Turk‐Browne, N. B., Botvinick, M., & Norman, K. A. (2016) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2016.0049 · Cited by 481 · see citing works
Syntax-Directed Variational Autoencoder for Structured DataPreprint
Dai, H., Tian, Y., Dai, B., Skiena, S., & Song, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.08786 · Cited by 220 · see citing works
Learning Deep Network Representations with Adversarially Regularized Autoencoders
Yu, W., Zheng, C., Cheng, W., Aggarwal, C. C., Song, D., Zong, B., Chen, H., & Wang, W. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3220000 · Cited by 188 · see citing works
Meta-Learning for Semi-Supervised Few-Shot ClassificationPreprint
Triantafillou, E., Larochelle, H., Snell, J., Tenenbaum, J. B., Swersky, K., Ren, M., Zemel, R. S., & Ravi, S. (2018) · arXiv (Cornell University) · Cited by 176 · see citing works
(2018) · International Conference on Learning Representations · Cited by 83 · see citing works
Transductive Propagation Network for Few-shot Learning
Liu, Y., Lee, J., Park, M., et al. (2018) · Cited by 56 · see citing works
One Shot Learning via Compositions of Meaningful Patches
Wong, A., & Yuille, A. (2015) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.142 · Cited by 44 · see citing works
Scaling Submodular Maximization via Pruned Submodularity GraphsPreprint
Zhou, T., Ouyang, H. J., Chang, Y., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.00399 · Cited by 4 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 2
- [Chen et al. , 2019] Wei-Yu Chen, Yen-Cheng Liu, Zsolt Liu, Yu-Chiang Frank Wang, and Jia-Bin Huang. A closer look at few-shot classification. In ICLR , 2019.
- [Veliˇ ckovi´ c et al. , 2018] Petar Veliˇ ckovi´ c, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. In ICLR , 2018.
Cited by
Sorted by citations
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · see citing works
Self-citation
- Authors
- Liu, L., Zhou, T., Long, G., Jiang, J., Yao, L., & Zhang, C.
- Affiliations
- University of Technology Sydney (AU)
- University of Washington (US)
- UNSW Sydney (AU)
- Venue
- Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
- Published
- 2019-08
- Pages
- 3015-3022
- OpenAlex
- W2944206301
- Cited by
- 65
- References
- 30
- Citations by year
- 2025: 3 · 2024: 4 · 2023: 8 · 2022: 7 · 2021: 25 · 2020: 14 · 2019: 4
- FWCI
- 4.78
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Joint Conference on Artificial Intelligence (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- UTS ePRESS (University of Technology Sydney) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Nvidia
- Australian Government
- Department of Health and Aged Care, Australian Government (LP150100671)
- Australian Research Council (LP160100630, LP150100671)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- few-shot learning, weakly supervised learning, meta-learning, graph attention mechanism, subgraph sampling, k-nearest neighbors, few-shot classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
