This repo contains official implementation for HyLa (HYperbolic LAplacian features), described in the paper Laplacian Features for Learning with Hyperbolic Space. Our HyLa feature, when used together ...

Official PyTorch implementation of the paper "Rethinking the compositionality of point clouds through regularization in the hyperbolic space" (NeurIPS 2022) TL;DR: We propose a new regularization ...

In this work, we propose Taxonomy-Oriented Poincaré-regularized Incremental-Class Segmentation (TOPICS) that learns feature embeddings in hyperbolic space following explicit taxonomy-tree structures.

Euclidean Space,Exponential Map,Final Representation,Gated Recurrent Unit,Graph Attention,Graph Attention Network,Graph Convolution,Graph Convolutional Network,Graph Neural Networks,Graph ...