Few-Shot Learning with Graph Neural Networks

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot learning models. Besides providing improved numerical performance, our framework is easily extended to variants of few-shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based models to operate well on 'relational' tasks.

[1]  F. Scarselli,et al.  A new model for learning in graph domains , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[2]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ah Chung Tsoi,et al.  The Graph Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Joan Bruna,et al.  Spectral Networks and Locally Connected Networks on Graphs , 2013, ICLR.

[6]  Alán Aspuru-Guzik,et al.  Convolutional Networks on Graphs for Learning Molecular Fingerprints , 2015, NIPS.

[7]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[8]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[9]  Joan Bruna,et al.  Deep Convolutional Networks on Graph-Structured Data , 2015, ArXiv.

[10]  Gregory R. Koch,et al.  Siamese Neural Networks for One-Shot Image Recognition , 2015 .

[11]  Daan Wierstra,et al.  Meta-Learning with Memory-Augmented Neural Networks , 2016, ICML.

[12]  Richard S. Zemel,et al.  Gated Graph Sequence Neural Networks , 2015, ICLR.

[13]  Rob Fergus,et al.  Learning Multiagent Communication with Backpropagation , 2016, NIPS.

[14]  Vijay S. Pande,et al.  Molecular graph convolutions: moving beyond fingerprints , 2016, Journal of Computer-Aided Molecular Design.

[15]  Razvan Pascanu,et al.  Interaction Networks for Learning about Objects, Relations and Physics , 2016, NIPS.

[16]  Oriol Vinyals,et al.  Matching Networks for One Shot Learning , 2016, NIPS.

[17]  Xavier Bresson,et al.  Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering , 2016, NIPS.

[18]  Samy Bengio,et al.  Order Matters: Sequence to sequence for sets , 2015, ICLR.

[19]  Pieter Abbeel,et al.  Meta-Learning with Temporal Convolutions , 2017, ArXiv.

[20]  Pierre Vandergheynst,et al.  Geometric Deep Learning: Going beyond Euclidean data , 2016, IEEE Signal Process. Mag..

[21]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[22]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[23]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[24]  Joan Bruna,et al.  Community Detection with Graph Neural Networks , 2017 .

[25]  Amos J. Storkey,et al.  Towards a Neural Statistician , 2016, ICLR.

[26]  Aurko Roy,et al.  Learning to Remember Rare Events , 2017, ICLR.

[27]  Joshua B. Tenenbaum,et al.  A Compositional Object-Based Approach to Learning Physical Dynamics , 2016, ICLR.

[28]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

[29]  Ambedkar Dukkipati,et al.  Generative Adversarial Residual Pairwise Networks for One Shot Learning , 2017, ArXiv.

[30]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[31]  Todd M. Gureckis,et al.  Question Asking as Program Generation , 2017, NIPS.

[32]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.