Embedding hub

Embedding hub is a vector database for machine-learning embeddings, and quite similar to Milvus.For the support of neighbor operations, partitioning, versioning and access control, we can use Embedding hub for the embedding vector use cases.

What’s an embedding?

Before Learning embeddings, understanding the basic requirements of a machine learning model is necessary . Specifically, most machine learning algorithms can only take low-dimensional numerical data as inputs.

Each of the input features is the numeric in the neural network .That is in the  domains such as recommender systems, it transforms non-numeric variables into numbers and vectors.Which represent items by a product ID; however, neural networks treat numerical inputs as continuous variables. That means higher numbers are “greater than” lower numbers. It also sees numbers that are similar as being similar items. This makes perfect sense for a field like “age” but is nonsensical when the numbers represent a categorical variable. Prior to embeddings, one of the most common methods used was one-hot encoding.

One-Hot Encoding

One-hot encoding was a common method for representing categorical variables. This unsupervised technique maps a single category to a vector and generates a binary representation. The actual process is simple. We create a vector with a size equal to the number of categories, with all the values set to 0. We then set the row or rows associated with the given ID or IDs to 1.

This technically works in turning a category into a couple of continuous variables, but we literally end up with a huge vector of 0s with a single or a handful of 1’s. This simplicity comes with drawbacks. For variables with many unique categories, it creates an unmanageable number of dimensions. Since each item is technically equidistant in vector space, it omits context around similarity. In vector space, categories with little variance are not any closer together than those with high variance. 

There is no way of evaluating the relationship between two entities. It generates more one-to-one mappings, or attempts to group them and look for similarities. This requires extensive work and manual labeling that’s typically infeasible.

Then create a denser representation of the categories and maintain some of the implicit relationship information between items. We need a way to reduce the number of categorical variables so we can place items of similar categories closer together. That’s exactly what an Embedding is.

Embeddings solve the encoding problem

Embeddings are dense numerical representations of real-world objects and relationships, expressed as a vector. The vector space quantifies the semantic similarity between categories. Embedding vectors that are close to each other are considered similar. Sometimes, they are used directly for “Similar items to this” section in an e-commerce store. Other times, embeddings are passed to other models. In those cases, the model can share learnings across similar items rather than treating them as two completely unique categories, as is the case with one-hot encodings. For this reason, embeddings can be used to accurately represent sparse data like clickstreams, text, and e-commerce purchases as features to downstream models. On the other hand, embeddings are much more expensive to compute than one-hot encodings and are far less interpretable.

How are Embeddings created

A common way to create an embedding requires to first set up a supervised machine learning problem. As a side-effect, training that model encodes categories into embedding vectors. For example, set up a model that predicts the next movie a user will watch based on what they are watching now. An embedding will factorize the input into a vector and that vector will be used to predict the next movie. This means that similar vectors are movies that are commonly watched after similar movies. This makes for a great representation to be used for personalization. So even though we are solving a supervised problem, often called the surrogate problem, the actual creation of embeddings is an unsupervised process.

Defining a surrogate problem is an art, and dramatically affects the behavior of the embeddings. For example, YouTube’s recommender team realized that using the “predict the next video a user is going to click on” resulted in clickbait becoming recommended. They moved to “predict the next video and how long they are going to watch it” as a surrogate problem and achieved far better results.


Milvus was created  with a singular goal: store, index, and manage massive embedding vectors generated by deep neural networks and other machine learning (ML) models.

As a database specifically designed to handle queries over input vectors, it is capable of indexing vectors on a trillion scale. Unlike existing relational databases which mainly deal with structured data following a predefined pattern, Milvus is designed from the bottom-up to handle embedding vectors converted from unstructured data.

As the Internet grew and evolved, unstructured data became more and more common, including emails, papers, IoT sensor data, Facebook photos, protein structures, and much more. In order for computers to understand and process unstructured data, these are converted into vectors using embedding techniques. Milvus stores and indexes these vectors. Milvus is able to analyze the correlation between two vectors by calculating their similarity distance. If the two embedding vectors are very similar, it means that the original data sources are similar as well.

Computer Vision

In computer vision, embeddings are often used as a way to translate between different contexts. For example, if training a self-driving car, we can transform the image from the car into an embedding and then decide what to do based on that embedded context. By doing so, we can perform transfer learning. We can take a generated image from a game like Grand Theft Auto, turn it into an embedding in the same vector space, and train the driving model without having to feed it tons of expensive, real-world images. Tesla is doing this in practice today.

How embeddings are operationalized today

Moving embeddings out of labs and into real world systems, has surfaced real gaps in the current data infrastructure capabilities. For example, traditional databases and caches don’t support operations like nearest neighbor lookups. Specialized approximate nearest neighbor indices lack durable storage and other features required for full production use. MLOps systems lack dedicated methods to manage versioning, access, and training for embeddings. Modern ML systems need an embedding store: a database built from the ground up around the machine learning workflow with embeddings.

Getting embeddings into production isn’t easy. The most common ways we’ve seen embeddings operationalized today are via Redis, Postgres, and S3 + Annoy/FAISS. 


Embeddings are a critical part of the data science toolkit, and continue to gain in popularity. Embeddings have allowed teams to break the state of the art in multiple disciplines from NLP to recommender systems. As they grow in popularity, a lot more focus will go into operationalizing them in real-world systems. 

For more details contact info@vafion.com

Follow us on Social media  : Twitter |  Facebook | Instagram | Linkedin

Similar Posts:

    No similar blogs

Related Posts

Stay UpdatedSubscribe and Get the latest updates from Vafion