# 機械学習勉強会 第1回

2020-02-15 (Sat) 14:00 - 17:30 @都内某所

## テーマ

ポアンカレ埋め込み。下記の論文を読む。

- Maximilian Nickel, Douwe Kiela. [Poincaré Embeddings for Learning Hierarchical Representations](https://arxiv.org/abs/1705.08039)

### 関連文献

- ABEJA Tech Blog. [双曲空間でのMachine Learningの最近の進展](https://tech-blog.abeja.asia/entry/hyperbolic_ml_2019)
- ABEJA Tech Blog. [異空間への埋め込み！Poincare Embeddingsが拓く表現学習の新展開](https://tech-blog.abeja.asia/entry/poincare-embeddings)
- Gunosy データ分析ブログ. [双曲空間ではじめるレコメンデーション](https://data.gunosy.io/entry/poincare_embedding_for_recommendations)

### 論文概要

abstract は以下の通り。

> 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.

## 次回の予定

2020-03前半開催を予定。

### テーマ

word2vecについて。下記の論文を読む。

- https://arxiv.org/abs/1301.3781
- https://arxiv.org/abs/1411.2738

### 宿題事項

- 論文 読む箇所の担当を決める
- Due 2/23
- Introと極端に短い箇所以外は担当を決めて読む
- 担当は議論のファシリテーションにつとめる
- Introは各自読むこと

### 今後やりたいこと

- 数式読みたい
- 実際に動くコードでデモできたら良いよね