Glossary term
Glossary term
Foundations
A feature whose values are predominately zero or empty. For example, a feature containing a single 1 value and a million 0 values is sparse. In contrast, a dense feature has values that are predominantly not zero or empty.
In machine learning, a surprising number of features are sparse features. Categorical features are usually sparse features. For example, of the 300 possible tree species in a forest, a single example might identify just a maple tree. Or, of the millions of possible videos in a video library, a single example might identify just "Casablanca."
In a model, you typically represent sparse features with one-hot encoding. If the one-hot encoding is big, you might put an embedding layer on top of the one-hot encoding for greater efficiency.
Created for this library
An ad-tech team uses sparse features like advertiser ID and ad creative ID with embedding tables in its click model.
A search-quality team uses sparse features like query terms and document IDs in its ranker via learned embedding tables.
A retail recommender team uses sparse features like product ID and category ID with embeddings in its scoring model.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License