QR kód

An Empirical Study of Self-Supervised Learning with Wasserstein Distance

In this study, we consider the problem of self-supervised learning (SSL) utilizing the 1-Wasserstein distance on a tree structure (a.k.a., Tree-Wasserstein distance (TWD)), where TWD is defined as the L1 distance between two tree-embedded vectors. In SSL methods, the cosine similarity is often utili...

Celý popis

Uloženo v:
Hlavní autoři: Makoto Yamada, Yuki Takezawa, Guillaume Houry, Kira Michaela Düsterwald, Deborah Sulem, Han Zhao, Yao-Hung Tsai
Médium: Artigo
Jazyk:Inglês
Vydáno: MDPI AG 2024-10-01
Edice:Entropy
Témata:
optimal transport
Wasserstein distance
self-supervised learning
On-line přístup:https://www.mdpi.com/1099-4300/26/11/939
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Podobné jednotky