Recently, hyperbolic deep neural networks (HDNNs) have been gaining momentum as the
deep representations in the hyperbolic space provide high fidelity embeddings with few …

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation
ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to …

Hyperbolic space can naturally embed hierarchies, unlike Euclidean space. Hyperbolic
Neural Networks (HNNs) exploit such representational power by lifting Euclidean features …

Federated learning (FL) collaboratively models user data in a decentralized way. However,
in the real world, non-identical and independent data distributions (non-IID) among clients …

Hyperbolic space can naturally embed hierarchies that often exist in real-world data and
semantics. While high dimensional hyperbolic embeddings lead to better representations …

Recognizing expressions from dynamic facial videos can find more natural affect states of
humans, and it becomes a more challenging task in real-world scenes due to pose …

Learning fine-grained embeddings from coarse labels is a challenging task due to limited
label granularity supervision, ie, lacking the detailed distinctions required for fine-grained …

Hyperbolic spaces have been quite popular in the recent past for representing hierarchically
organized data. Further, several classification algorithms for data in these spaces have been …

Adversarial examples are inputs to machine learning models that an attacker has
intentionally designed to confuse the model into making a mistake. Such examples pose a …

Many high-dimensional and large-volume data sets of practical relevance have hierarchical
structures induced by trees, graphs or time series. Such data sets are hard to process in …