{"type":"ScholarlyArticle","title":"Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph","authors":[{"name":"Lu Liu","slug":"lu-liu","given":"Lu","family":"Liu","affiliation":"Center for Artificial Intelligence , FEIT , University of Technology Sydney"},{"name":"Tianyi Zhou","slug":"tianyi-zhou","given":"Tianyi","family":"Zhou","affiliation":"Paul G. Allen School of Computer Science & Engineering , University of Washington"},{"name":"Guodong Long","slug":"guodong-long","given":"Guodong","family":"Long","affiliation":"Center for Artificial Intelligence , FEIT , University of Technology Sydney"},{"name":"Jing Jiang","slug":"jing-jiang","given":"Jing","family":"Jiang","affiliation":"Center for Artificial Intelligence , FEIT , University of Technology Sydney"},{"name":"Lina Yao","slug":"lina-yao","given":"Lina","family":"Yao","affiliation":"School of Computer Science and Engineering , University of New South Wales"},{"name":"Chengqi Zhang","slug":"chengqi-zhang","given":"Chengqi","family":"Zhang","affiliation":"Center for Artificial Intelligence , FEIT , University of Technology Sydney"}],"abstract":"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.","doi":"10.24963/ijcai.2019/418","url":"https://ijcai.org/proceedings/2019/418","pdf":"https://ijcai.org/proceedings/2019/0418.pdf","markdown":"https://ijcai.org/proceedings/2019/418.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/418","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":418,"pages":{"first":3015,"last":3022},"keywords":["Machine Learning: Deep Learning","Machine Learning: Data Mining","Machine Learning: Classification"],"videos":[],"references":[{"position":1,"raw":"[Belkin et al., 2006] Mikhail Belkin, Partha Niyogi, and Vikas Sindhwani. Manifold regularization: A geometric framework for learning from labeled and unlabeled exam- ples. JMLR, pages 2399-2434, 2006.","title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","authors":"Mikhail Belkin, Partha Niyogi, Vikas Sindhwani","year":"2006","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Caruana, 1997] Rich Caruana. Multitask learning. Machine Learning, pages 41-75, 1997.","title":"Rich Caruana","authors":"Caruana","year":"1997","venue":"Multitask learning. Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[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.","title":"A closer look at few-shot classification","authors":"Wei-Yu Chen, Yen-Cheng Liu, Zsolt Liu, Yu-Chiang Frank, Wang, Jia-Bin Huang","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dai et al., 2018] Hanjun Dai, Yingtao Tian, Bo Dai, Steven Skiena, and Le Song. Syntax-directed variational autoen- coder for structured data. In ICLR, 2018.","title":"Syntax-directed variational autoencoder for structured data","authors":"Dai","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. ImageNet: A large-scale hierarchical image database. In CVPR, pages 248-255, 2009.","title":"ImageNet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong and Yang, 2019] Xuanyi Dong and Yi Yang. Search- ing for a robust neural architecture in four gpu hours. In CVPR, pages 1761-1770, 2019.","title":"Searching for a robust neural architecture in four gpu hours","authors":"Dong, Yang ;, Xuanyi Dong, Yi Yang","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, pages 1126-1135, 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Garcia and Bruna, 2018] Victor Garcia and Joan Bruna. Few-shot learning with graph neural networks. In ICLR, 2018.","title":"Few-shot learning with graph neural networks","authors":"Bruna ; Garcia, Victor Garcia, Joan Bruna","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. In NeurIPS, pages 1024-1034, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ioffe and Szegedy, 2015] Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep net- work training by reducing internal covariate shift. In ICML, pages 448-456, 2015.","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","authors":"Szegedy Ioffe, Sergey Ioffe, Christian Szegedy","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2015] Diederik P Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lake et al., 2015] Brenden M Lake, Ruslan Salakhutdinov, and Joshua B Tenenbaum. Human-level concept learning through probabilistic program induction. Science, pages 1332-1338, 2015.","title":"Human-level concept learning through probabilistic program induction","authors":"Ruslan Brenden M Lake, Joshua B Salakhutdinov, Tenenbaum","year":"2015","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2019] Yanbin Liu, Juho Lee, Minseop Park, Sae- hoon Kim, and Yi Yang. Transductive propagation net- work for few-shot learning. In ICLR, 2019.","title":"Transductive propagation network for few-shot learning","authors":"Yanbin Liu, Juho Lee, Minseop Park, Saehoon Kim, Yi Yang","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Maaten and Hinton, 2008] Laurens van der Maaten and Ge- offrey Hinton. Visualizing data using t-sne. JMLR, pages 2579-2605, 2008.","title":"Laurens van der Maaten and Geoffrey Hinton","authors":"Hinton Maaten","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mishra et al., 2018] Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, and Pieter Abbeel. A simple neural attentive meta-learner. In ICLR, 2018.","title":"A simple neural attentive meta-learner","authors":"Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Nichol and Schulman, 2018] Alex Nichol and John Schul- man. Reptile: A scalable metalearning algorithm. arXiv preprint arXiv:1803.02999, 2018.","title":"Reptile: A scalable metalearning algorithm","authors":"Alex Nichol, John Schulman","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Oreshkin et al., 2018] Boris N Oreshkin, Alexandre La- coste, and Pau Rodriguez. Tadam: Task dependent adap- tive metric for improved few-shot learning. In NeurIPS, pages 721-731, 2018.","title":"Tadam: Task dependent adaptive metric for improved few-shot learning","authors":"Alexandre Boris N Oreshkin, Pau Lacoste, Rodriguez","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ravi and Beatson, 2019] Sachin Ravi and Alex Beatson. Amortized bayesian meta-learning. In ICLR, 2019.","title":"Amortized bayesian meta-learning","authors":"Sachin Ravi, Alex Beatson","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ravi and Larochelle, 2017] Sachin Ravi and Hugo Larochelle. Optimization as a model for few-shot learning. In ICLR, 2017.","title":"Optimization as a model for few-shot learning","authors":"Larochelle ; Ravi, Sachin Ravi, Hugo Larochelle","year":"2017","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ren et al., 2018] Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B Tenenbaum, Hugo Larochelle, and Richard S Zemel. Meta-learning for semi-supervised few-shot classification. In ICLR, 2018.","title":"Meta-learning for semi-supervised few-shot classification","authors":"Ren","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Schapiro et al., 2017] Anna C Schapiro, Nicholas B Turk- Browne, Matthew M Botvinick, and Kenneth A Norman. Complementary learning systems within the hippocam- pus: A neural network modelling approach to reconciling episodic memory with statistical learning. Philosophical Transactions of the Royal Society of London. Series B, Bi- ological sciences, page 20160049, 2017.","title":"Complementary learning systems within the hippocampus: A neural network modelling approach to reconciling episodic memory with statistical learning","authors":"Anna C Schapiro, Nicholas B Turk-Browne, Matthew M Botvinick, Kenneth A Norman","year":"2017","venue":"Philosophical Transactions of the Royal Society of London. Series B, Biological sciences","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Snell et al., 2017] Jake Snell, Kevin Swersky, and Richard Zemel. Prototypical networks for few-shot learning. In NeurIPS, pages 4077-4087, 2017.","title":"Prototypical networks for few-shot learning","authors":"Jake Snell, Kevin Swersky, Richard Zemel","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Veličković et al., 2018] Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. Graph attention networks. In ICLR, 2018.","title":"Graph attention networks","authors":"Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Vinyals et al., 2016] Oriol Vinyals, Charles Blundell, Tim Lillicrap, Daan Wierstra, et al. Matching networks for one shot learning. In NeurIPS, pages 3630-3638, 2016.","title":"Matching networks for one shot learning","authors":"Oriol Vinyals, Charles Blundell, Tim Lillicrap, Daan Wierstra","year":"2016","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang et al., 2017] Chun Wang, Shirui Pan, Guodong Long, Xingquan Zhu, and Jing Jiang. Mgae: Marginalized graph autoencoder for graph clustering. In CIKM, pages 889- 898. ACM, 2017.","title":"Mgae: Marginalized graph autoencoder for graph clustering","authors":"Chun Wang, Shirui Pan, Guodong Long, Xingquan Zhu, Jing Jiang","year":"2017","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wong and Yuille, 2015] Alex Wong and Alan L Yuille. One shot learning via compositions of meaningful patches. In ICCV, pages 1197-1205, 2015.","title":"One shot learning via compositions of meaningful patches","authors":"Alex Wong, Alan L Yuille","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wu et al., 2019] Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and Philip S Yu. A comprehensive survey on graph neural networks. arXiv preprint arXiv:1901.00596, 2019.","title":"A comprehensive survey on graph neural networks","authors":"Wu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yu et al., 2018] Wenchao Yu, Cheng Zheng, Wei Cheng, Charu C Aggarwal, Dongjin Song, Bo Zong, Haifeng Chen, and Wei Wang. Learning deep network represen- tations with adversarially regularized autoencoders. In SIGKDD, pages 2663-2671, 2018.","title":"Learning deep network representations with adversarially regularized autoencoders","authors":"Wenchao Yu, Cheng Zheng, Wei Cheng, C Charu, Dongjin Aggarwal, Bo Song, Haifeng Zong, Wei Chen, Wang","year":"2018","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2017] Tianyi Zhou, Hua Ouyang, Yi Chang, Jeff Bilmes, and Carlos Guestrin. Scaling submodular maximization via pruned submodularity graphs. In AIS- TATS, pages 316-324, 2017.","title":"Scaling submodular maximization via pruned submodularity graphs","authors":"Tianyi Zhou, Hua Ouyang, Yi Chang, Jeff Bilmes, Carlos Guestrin","year":"2017","venue":"AIS-TATS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhou, 2017] Zhi-Hua Zhou. A brief introduction to weakly supervised learning. National Science Review, pages 44- 53, 2017.","title":"A brief introduction to weakly supervised learning","authors":"Zhi-Hua Zhou","year":"2017","venue":"National Science Review","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu and Ghahramani, 2002] Xiaojin Zhu and Zoubin Ghahramani. Learning from labeled and unlabeled data with label propagation. Technical report, Citeseer, 2002.","title":"Learning from labeled and unlabeled data with label propagation","authors":"Xiaojin Zhu, Zoubin Ghahramani","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}