Poincaré Embeddings for Learning Hierarchical Representations · HackerPapers discussions

Poincaré Embeddings for Learning Hierarchical Representations — mentioned by VHRanger

Thu, 25 Apr 2024 12:47:37 GMT

These exotic (non linear algebra based) embedding representations are often slow to take off unless they have an obvious use case. The other one that I've always been curious of is Poincarré Embeddings [1] - where the embedding also has a hierarchical representation of the space. There's issues with these becoming popular: 1. Querying the embeddings requires more math knowledge than just "lol cosine similarity". This also requires to write code for the query 2. You can often easily match the performance with regular embeddings by just adding dimensions and training more. So the advantage of…

Paper and discussion history. A mention is not an endorsement.

Poincaré Embeddings for Learning Hierarchical Representations — mentioned by andyxor

Wed, 10 Feb 2021 19:07:59 GMT

that's funny, I was just reading on "Hyperbolic geometry of the olfactory space", it maps nicely to hierarchical knowledge representation: https://advances.sciencemag.org/content/4/8/eaaq1458 also see Tatyana Sharpee' argument for hyperbolic geometry in neural circuits: https://www.sciencedirect.com/science/article/abs/pii/S09594... the paper from 2010 that popularized its applications: "Hyperbolic Geometry of Complex Networks": https://arxiv.org/abs/1006.5169 A related work "Poincare embeddings for learning hierarchical representations" from 2017 is well known in "graph embeddings" space…

Paper and discussion history. A mention is not an endorsement.

Poincaré Embeddings for Learning Hierarchical Representations — mentioned by boltzmannbrain

Thu, 01 Aug 2019 16:38:11 GMT

Equations wrong in the original Poincare embeddings paper https://arxiv.org/abs/1705.08039 ? Do you recall which? And thanks for sharing your Lorentz implementation!

Paper and discussion history. A mention is not an endorsement.

Poincaré Embeddings for Learning Hierarchical Representations — mentioned by boltzmannbrain

Thu, 01 Aug 2019 00:48:55 GMT

Authors learn embeddings in a Poincaré space rather than Euclidean, better for hierarchical relationships. The reference paper is a good read: Nickel & Kiela '17 "Poincaré Embeddings for Learning Hierarchical Representations", https://arxiv.org/abs/1705.08039

Paper and discussion history. A mention is not an endorsement.

Poincaré Embeddings for Learning Hierarchical Representations — HN submission

Mon, 09 Oct 2017 22:34:08 GMT

Show HN: Implementation of Poincaré Embeddings(Facebook Research) in Numpy

The implementation is at: https://github.com/nishnik/poincare_embeddings Corresponding blog post: https://medium.com/towards-data-science/facebook-research-ju... Corresponding paper: https://arxiv.org/abs/1705.08039 This paper explores Poincare disk model instead of Euclidean space for embedding hierarchical data

6 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Poincaré Embeddings for Learning Hierarchical Representations — HN submission

Fri, 02 Jun 2017 23:11:49 GMT

Poincaré Embeddings for Learning Hierarchical Representations

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.