English

Time2Vec: Learning a Vector Representation of Time

Machine Learning 2019-07-12 v1

Abstract

Time is an important feature in many applications involving events that occur synchronously and/or asynchronously. To effectively consume time information, recent studies have focused on designing new architectures. In this paper, we take an orthogonal but complementary approach by providing a model-agnostic vector representation for time, called Time2Vec, that can be easily imported into many existing and future architectures and improve their performances. We show on a range of models and problems that replacing the notion of time with its Time2Vec representation improves the performance of the final model.

Keywords

Cite

@article{arxiv.1907.05321,
  title  = {Time2Vec: Learning a Vector Representation of Time},
  author = {Seyed Mehran Kazemi and Rishab Goel and Sepehr Eghbali and Janahan Ramanan and Jaspreet Sahota and Sanjay Thakur and Stella Wu and Cathal Smyth and Pascal Poupart and Marcus Brubaker},
  journal= {arXiv preprint arXiv:1907.05321},
  year   = {2019}
}
R2 v1 2026-06-23T10:18:43.987Z