arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1705.08039cs.AIcs.LGstat.ML
收藏

学习层次表示的Poincaré嵌入

Poincaré Embeddings for Learning Hierarchical Representations

Facebook AI Research(脸书人工智能研究院)

Maximilian Nickel, Douwe Kiela

摘要:

表示学习已成为从文本和图形等符号数据中学习的宝贵方法。然而,虽然复杂的符号数据集通常表现出潜在的层次结构,但最先进的方法通常在欧几里得向量空间中学习嵌入,这并不考虑此属性。为此,我们引入了一种新的方法来学习符号数据的层次表示,通过将它们嵌入到双曲空间中,或者更准确地说,嵌入到n维庞加莱球中。由于底层的双曲几何,这使我们能够通过同时捕获层次和相似性来学习符号数据的简约表示。我们引入了一个有效的算法来学习嵌入的基础上黎曼优化和实验表明,庞加莱嵌入优于欧几里得嵌入显着的数据与潜在的层次结构,无论是在表示能力和泛化能力方面。

英文摘要:

Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs. However, while complex symbolic datasets often exhibit a latent hierarchical structure, state-of-the-art methods typically learn embeddings in Euclidean vector spaces, which do not account for this property. For this purpose, we introduce a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows us to learn parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. We introduce an efficient algorithm to learn the embeddings based on Riemannian optimization and show experimentally that Poincaré embeddings outperform Euclidean embeddings significantly on data with latent hierarchies, both in terms of representation capacity and in terms of generalization ability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑