LGMLAug 2, 2020

A Foliated View of Transfer Learning

arXiv:2008.00546v11 citations
AI Analysis

This work addresses a theoretical gap in transfer learning for researchers, but it appears incremental as it builds on existing concepts without demonstrating broad impact.

The paper tackled the lack of a foundational description of transfer learning by defining task relatedness and proposing foliations as a mathematical framework to represent relationships between tasks, without providing concrete experimental results or numbers.

Transfer learning considers a learning process where a new task is solved by transferring relevant knowledge from known solutions to related tasks. While this has been studied experimentally, there lacks a foundational description of the transfer learning problem that exposes what related tasks are, and how they can be exploited. In this work, we present a definition for relatedness between tasks and identify foliations as a mathematical framework to represent such relationships.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes