poincareEmbeddings: Poincare-embeddings

In hwchang1201/poincare.embeddings: R-package implementation of Poincaré Embeddings for Learning Hierarchical Representations.

Description

This function is aggregated the functions to give the outputs, 2-D plot(if theta_dim = 2), ranking and MAP. Please refer to 'vignette' to find detailed implementation.

Usage

poincareEmbeddings(dataset_tree, theta_dim = 2, N_epoch = 50,
  lr = 0.01, n_neg = 5)

Arguments

dataset_tree	- A tree-shape dataset from "data.tree"
theta_dim	- The dimension of the embedding space.
N_epoch	- The number of epochs.
lr	- The learning rate.
n_neg	- The number of negative samples for each iteration.

Value

Ranking : The ranking of the true related entity.

MAP : Mean average precision.

A 2-dimension plot only if theta_dim = 2.

Examples

statistics_adv_yaml <- yaml::yaml.load(statistics_adv)
statistics_adv_tree <- data.tree::as.Node(statistics_adv_yaml)
poincareEmbeddings(statistics_adv_tree, theta_dim = 2, N_epoch = 200, lr = 0.005, n_neg = 10)

hwchang1201/poincare.embeddings documentation built on Dec. 9, 2019, 1:30 p.m.