Rethinking Knowledge Graph Propagation for Zero-Shot Learning
作者： Michael Kampffmeyer , Yinbo Chen , Xiaodan Liang , Hao Wang , Yujia Zhang
关键词:
摘要: Graph convolutional neural networks have recently shown great potential for the task of zero-shot learning. These models are highly sample efficient as related concepts in the graph structure share statistical strength allowing generalization to new classes when faced with a lack of data. However, multi-layer architectures, which are required to propagate knowledge to distant nodes in the graph, dilute the knowledge by performing extensive Laplacian smoothing at each layer and thereby consequently decrease performance. In order to still …
computer.org
sci-hub.se 参考文章(32)
Yoshua Bengio, Hugo Larochelle, Dumitru Erhan, Zero-data learning of new tasks national conference on artificial intelligence. pp. 646- 651 ,(2008)
Tomas Mikolov, Andrea Frome, Greg S. Corrado, Samy Bengio, Mohammad Norouzi, Yoram Singer, Jonathon Shlens, Jeffrey Dean, Zero-Shot Learning by Convex Combination of Semantic Embeddings international conference on learning representations. ,(2014)
Bernardino Romera-Paredes, Philip H. S. Torr, An embarrassingly simple approach to zero-shot learning international conference on machine learning. pp. 2152- 2161 ,(2015) , 10.1007/978-3-319-50077-5_2
Thomas Mensink, Jakob Verbeek, Florent Perronnin, Gabriela Csurka, Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Computer Vision – ECCV 2012. ,vol. 7573, pp. 488- 501 ,(2012) , 10.1007/978-3-642-33709-3_35
Ruslan Salakhutdinov, Antonio Torralba, Josh Tenenbaum, Learning to share visual appearance for multiclass object detection CVPR 2011. pp. 1481- 1488 ,(2011) , 10.1109/CVPR.2011.5995720
Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, Bernt Schiele, Evaluation of output embeddings for fine-grained image classification computer vision and pattern recognition. pp. 2927- 2936 ,(2015) , 10.1109/CVPR.2015.7298911
Marcus Rohrbach, Michael Stark, Bernt Schiele, Evaluating knowledge transfer and zero-shot learning in a large-scale setting CVPR 2011. pp. 1641- 1648 ,(2011) , 10.1109/CVPR.2011.5995627
Ilya Sutskever, Geoffrey Hinton, Alex Krizhevsky, Ruslan Salakhutdinov, Nitish Srivastava, Dropout: a simple way to prevent neural networks from overfitting Journal of Machine Learning Research. ,vol. 15, pp. 1929- 1958 ,(2014)
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei, ImageNet: A large-scale hierarchical image database computer vision and pattern recognition. pp. 248- 255 ,(2009) , 10.1109/CVPR.2009.5206848
Richard Socher, Milind Ganjoo, Andrew Ng, Christopher D Manning, Zero-Shot Learning Through Cross-Modal Transfer neural information processing systems. ,vol. 26, pp. 935- 943 ,(2013)