2020

On Learning Sets of Symmetric Elements

Maron, Haggai, Litany, Or, Chechik, Gal et al.

Understand

Learning from unordered sets is a fundamental learning setup, recently attracting increasing attention.

Research in this area has focused on the case where elements of the set are represented by feature vectors, and far less emphasis has been given to the common case where set elements themselves adhere to their own symmetries.
That case is relevant to numerous applications, from deblurring image bursts to multi-view 3D shape recognition and reconstruction.
In this paper, we present a principled approach to learning sets of general symmetric elements.

Built on

Gauge equivariant convolutional networks and the icosahedral cnn
Original
Cohen, T. S., Weiler, M., Kicanaoglu, B., and Welling, M · 1902
Earlier work this paper cites.
Universal invariant and equivariant graph neural networks
Original
Keriven, N. and Peyré, G · 1905
Earlier work this paper cites.
Provably powerful graph networks
Original
Maron, H., Ben-Hamu, H., Serviansky, H., and Lipman, Y · 1905
Earlier work this paper cites.
Introduction to topology and modern analysis
Simmons, G. F · 1963
Earlier work this paper cites.
Approximation by superpositions of a sigmoidal function
Cybenko, G · 1989
Earlier work this paper cites.
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., and White, H · 1989
Earlier work this paper cites.
Steerable CNNs
Original
Cohen, T. S. and Welling, M · 1990
Earlier work this paper cites.
Signature verification using a” siamese” time delay neural network
Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., and Shah, R · 1994
Earlier work this paper cites.
Representation theory and invariant neural networks
Wood, J. and Shawe-Taylor, J · 1996
Earlier work this paper cites.
Algebraic signal processing theory: Foundation and 1-d time
Puschel, M. and Moura, J. M · 2008
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L · 2009
Earlier work this paper cites.
Ucf101: A dataset of 101 human actions classes from videos in the wild
Original
Soomro, K., Zamir, A. R., and Shah, M · 2012
Earlier work this paper cites.
Representation theory: a first course , volume 129
Fulton, W. and Harris, J · 2013
Earlier work this paper cites.
Adam: A method for stochastic optimization
Original
Kingma, D. P. and Ba, J · 2014
Earlier work this paper cites.
Sequence to sequence learning with neural networks
Sutskever, I., Vinyals, O., and Le, Q · 2014
Earlier work this paper cites.
Batch normalization: Accelerating deep network training by reducing internal covariate shift
Original
Ioffe, S. and Szegedy, C · 2015
Earlier work this paper cites.
U-net: Convolutional networks for biomedical image segmentation
Ronneberger, O., Fischer, P., and Brox, T · 2015
Earlier work this paper cites.
Multi-view convolutional neural networks for 3d shape recognition
Su, H., Maji, S., Kalogerakis, E., and Learned-Miller, E · 2015
Earlier work this paper cites.
Order matters: Sequence to sequence for sets
Original
Vinyals, O., Bengio, S., and Kudlur, M · 2015
Earlier work this paper cites.
Exploiting cyclic symmetry in convolutional neural networks
Original
Dieleman, S., De Fauw, J., and Kavukcuoglu, K · 2016
Earlier work this paper cites.
Towards a neural statistician
Original
Edwards, H. and Storkey, A · 2016
Earlier work this paper cites.

Similar

Semi-supervised classification with graph convolutional networks
Original
Kipf, T. N. and Welling, M · 2016
Cited alongside, same era.
Deep learning with sets and point clouds
Original
Ravanbakhsh, S., Schneider, J., and Poczos, B · 2016
Cited alongside, same era.
Dynamic FAUST: Registering human bodies in motion
Bogo, F., Romero, J., Pons-Moll, G., and Black, M. J · 2017
Cited alongside, same era.
3d object classification and retrieval with spherical cnns
Original
Esteves, C., Allen-Blanchette, C., Makadia, A., and Daniilidis, K · 2017
Cited alongside, same era.
3d shape segmentation with projective convolutional networks
Kalogerakis, E., Averkiou, M., Maji, S., and Chaudhuri, S · 2017
Cited alongside, same era.
Deep functional maps: Structured prediction for dense shape correspondence
Litany, O., Remez, T., Rodolà, E., Bronstein, A., and Bronstein, M · 2017
Cited alongside, same era.
Automatic differentiation in pytorch
Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., and Lerer, A · 2017
Cited alongside, same era.
Pointnet: Deep learning on point sets for 3d classification and segmentation
Qi, C. R., Su, H., Mo, K., and Guibas, L. J · 2017
Cited alongside, same era.
Equivariance through parameter-sharing
Original
Ravanbakhsh, S., Schneider, J., and Poczos, B · 2017
Cited alongside, same era.
Harmonic networks: Deep translation and rotation equivariance
Worrall, D. E., Garbin, S. J., Turmukhambetov, D., and Brostow, G. J · 2017
Cited alongside, same era.
Deep sets
Zaheer, M., Kottur, S., Ravanbakhsh, S., Poczos, B., Salakhutdinov, R. R., and Smola, A. J · 2017
Cited alongside, same era.
Places: A 10 million image database for scene recognition
Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., and Torralba, A · 2017
Cited alongside, same era.

Then

(probably) concave graph matching
Maron, H. and Lipman, Y · 2018
Later among the works it cites.
Weisfeiler and leman go neural: Higher-order graph neural networks
Original
Morris, C., Ritzert, M., Fey, M., Hamilton, W. L., Lenssen, J. E., Rattan, G., and Grohe, M · 2018
Later among the works it cites.
Janossy pooling: Learning deep permutation-invariant functions for variable-size inputs
Original
Murphy, R. L., Srinivasan, B., Rao, V., and Ribeiro, B · 2018
Later among the works it cites.
Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds
Original
Thomas, N., Smidt, T., Kearnes, S., Yang, L., Li, L., Kohlhoff, K., and Riley, P · 2018
Later among the works it cites.
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data
Original
Weiler, M., Geiger, M., Welling, M., Boomsma, W., and Cohen, T · 2018
Later among the works it cites.
3d g-cnns for pulmonary nodule detection
Original
Winkels, M. and Cohen, T. S · 2018
Later among the works it cites.
Cubenet: Equivariance to 3d rotation and translation
Worrall, D. and Brostow, G · 2018
Later among the works it cites.
Universal approximations of invariant maps by neural networks
Original
Yarotsky, D · 2018
Later among the works it cites.
Incidence networks for geometric deep learning
Original
Albooyeh, M., Bertolini, D., and Ravanbakhsh, S · 2019
Later among the works it cites.
On the equivalence between graph isomorphism testing and function approximation with gnns
Original
Chen, Z., Villar, S., Chen, L., and Bruna, J · 2019
Later among the works it cites.
Equivariant multi-view networks
Esteves, C., Xu, Y., Allen-Blanchette, C., and Daniilidis, K · 2019
Later among the works it cites.
Fast graph representation learning with pytorch geometric
Original
Fey, M. and Lenssen, J. E · 2019
Later among the works it cites.
Deep models for relational databases
Original
Graham, D. and Ravanbakhsh, S · 2019
Later among the works it cites.
Permutation-invariant feature restructuring for correlation-aware image set-based recognition
Original
Liu, X., Guo, Z., Li, S., Kong, L., Jia, P., You, J., and Kumar, B · 2019
Later among the works it cites.
A simple proof of the universality of invariant/equivariant graph neural networks, 2019
Maehara, T. and NT, H · 2019
Later among the works it cites.
On universal equivariant set networks
Original
Segol, N. and Lipman, Y · 2019
Later among the works it cites.
Multiview aggregation for learning category-specific shape reconstruction
Original
Sridhar, S., Rempe, D., Valentin, J., Bouaziz, S., and Guibas, L. J · 2019
Later among the works it cites.
On the limitations of representing functions on sets
Original
Wagstaff, E., Fuchs, F. B., Engelcke, M., Posner, I., and Osborne, M · 2019
Later among the works it cites.
How powerful are graph neural networks?
Xu, K., Hu, W., Leskovec, J., and Jegelka, S · 2019
Later among the works it cites.
Convolutional conditional neural processes
Gordon, J., Bruinsma, W. P., Foong, A. Y. K., Requeima, J., Dubois, Y., and Turner, R. E · 2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…