Time2Vec: Learning a Vector Representation of Time
This provides a general solution for integrating time features into ML models, benefiting applications with synchronous or asynchronous events, though it is incremental as it builds on existing representation learning approaches.
The paper tackles the problem of effectively incorporating time information in machine learning models by introducing Time2Vec, a model-agnostic vector representation for time, and shows that using this representation improves model performance across various architectures and problems.
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.