3. CONFIDENTIAL
Today’s Paper
Paper Stats
• Guys from FAIR
• Sumitted to arXiv at May 26, 2017
https://arxiv.org/abs/1705.08039
• Sumitted to NIPS2017?
Key Contributions
• Introducing hyperbolic geometry
(Poincaré disk model) into word/graph
embeddings paradigm
• Automatically capture hierarchical
structure of data
• Achieved incredible better results than
previous works.
7. CONFIDENTIAL
Embed nouns in WordNets such that related nouns
are close in embedded space
Taxonomy Embedding
7
http://www.nltk.org/book_1ed/ch02.html
8. CONFIDENTIAL
Embed nodes in given graph such that missing
links are well-reconstructed
Graph Link Prediction
8
http://ml.cs.tsinghua.edu.cn/~jiaming/publications/
10. CONFIDENTIAL
• Geometry with negative curvature
• Many models (realizations):
- Poincaré half space model
- Poincaré disk model
…
each is isometric
Hyperbolic Geometry
10
11. CONFIDENTIAL
• Defined on upper half space
with metric
• Distance btw points is
Poincaré Half Space Model
11
13. CONFIDENTIAL
• A realization of hyperbolic geometry
• Defined on
equipped with metric of
• Distance btw points is
Poincaré Disk Model
13
M.C. Escher's Circle Limit III, 1959
15. CONFIDENTIAL
• Euclidean space is too narrow to embed
hierarchical (tree) structures
Why not Euclidean Space?
15
Surface Area
/ # of leaf nodes
Volume
/ # of nodes
Euclidean Ball O(R^n) O(R^n)
b-ary tree O(b^R) O(b^R)
※ R=radius of ball or depth of tree
16. CONFIDENTIAL
• b-array tree can be interpreted as discrete
analogue of Poincaré disk
Why Hyperbolic Space?
16
17. CONFIDENTIAL
• Hyperbolic space is far more appropriate than
Euclidean space to represent hierarchical
structure
• Many equivalent models
- Poincaré half space model
- Poincaré disk model
…
Conclusion Here
17
18. CONFIDENTIAL
• R. Kleinberg, “Geographic routing using hyperbolic
spaces”, 2007
• M. Boguna et al., “Sustaining the internet with
hyperbolic mapping”, 2010
• P. D. Hoff et al., “Latent space approaches to social
network analysis”, 2016
• A. B. Adcock et al., “Tree-like structure in large social
and information networks’, 2013
• D. Krioukov et al., “Hyperbolic geometry of complex
networks”, 2010
Prior Works around hyperbolic geometry
applications
18
22. CONFIDENTIAL
Embed nouns in WordNets such that related nouns
are close in embedded space
Taxonomy Embedding
22
http://www.nltk.org/book_1ed/ch02.html
26. CONFIDENTIAL
Embed nodes in given graph such that missing
links are well-reconstructed
Graph Link Prediction
26
http://ml.cs.tsinghua.edu.cn/~jiaming/publications/
29. CONFIDENTIAL
• Poincaré embeddings automatically capture
hierarchical structure from data
• Riemannian SGD provides the way to optimize
Poincaré embeddings
• Achieved quite good results on word/graph
embedding tasks
Summary
29