Neural Information Processing Systems http://nips.cc/

In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets.

We introduce Natural Neural Networks, a novel family of algorithms that speed up convergence by adapting their internal representation during training to improve conditioning of the Fisher matrix. In particular, we show a specific example that employs a simple and efficient reparametrization of the neural network weights by implicitly whitening the representation obtained at each layer, while preserving the feed-forward computation of the network. Such networks can be trained efficiently via the proposed Projected Natural Gradient Descent algorithm (PRONG), which amortizes the cost of these reparametrizations over many parameter updates and is closely related to the Mirror Descent online learning algorithm. We highlight the benefits of our method on both unsupervised and supervised learning tasks, and showcase its scalability by training on the large-scale ImageNet Challenge dataset.

Learning curves are an important diagnostic tool that provide researchers and practitioners with insight into a learner's generalization behavior [Shalev-Shwartz and Ben-David, 2014].

Many real datasets are hierarchically structured.

Neural Information Processing Systems http://nips.cc/