2 citations · 3 across the 9 of their papers we have counts for
5 papers · 1 filter
Relational Compression: A Framework for Relational Fidelity in Constrained Representations
Yaniv Shulman
What should a compressed representation preserve when the information of interest lies in relationships among elements rather than in the elements themselves? We formulate relation…
MABLE: Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning
Yaniv Shulman, Shaghayegh Akbarpour, Jack B. Muir
We propose MABLE (Masked Autoencoding with Bi-Lipschitz Decoding for Embeddings and Graph Metric Learning), a self-supervised framework for learning node and graph embeddings from…
Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations
Yaniv Shulman
Quantization based model compression serves as high performing and fast approach for inference that yields models which are highly compressed when compared to their full-precision…
SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
Yaniv Shulman
Deep learning methods for graphs have seen rapid progress in recent years with much focus awarded to generalising Convolutional Neural Networks (CNN) to graph data. CNNs are typica…
Dynamic Time Warp Convolutional Networks
Yaniv Shulman
Where dealing with temporal sequences it is fair to assume that the same kind of deformations that motivated the development of the Dynamic Time Warp algorithm could be relevant al…