Graph neural networks (GNNs) have demonstrated a significant success in various graph
learning tasks, from graph classification to anomaly detection. There recently has emerged a …

We formulate the manifold learning problem as the problem of finding an operator that maps
any point to a close neighbor that lies on a “hidden” k-dimensional manifold. We call this …

Evaluating the quality of learned representations without relying on a downstream task
remains one of the challenges in representation learning. In this work, we present Geometric …

Variational auto-encoders (VAEs) are deep generative models used for unsupervised
learning, however their standard version is not topology-aware in practice since the data …

Capitalizing on the intuitive premise that shape characteristics are more robust to
perturbations, we bridge adversarial graph learning with the emerging tools from …

Auto-encoder models that preserve similarities in the data are a popular tool in
representation learning. In this paper we introduce several auto-encoder models that …

Abstract Variational Auto-Encoders (VAEs) are one of the most famous deep generative
models. After showing that standard VAEs may not preserve the topology, that is the shape …

Auto-encoder models that preserve similarities in the data are a popular tool in
representation learning. In this paper we introduce several auto-encoder models that …