index.md

Keras Recommenders

Star

Keras Recommenders is a library for building recommender systems on top of Keras 3. Keras Recommenders works natively with TensorFlow, JAX, or PyTorch. It provides a collection of building blocks which help with the full workflow of creating a recommender system. As it's built on Keras 3, models can be trained and serialized in any framework and re-used in another without costly migrations.

This library is an extension of the core Keras API; all high-level modules receive that same level of polish as core Keras. If you are familiar with Keras, congratulations! You already understand most of Keras Recommenders.

Quick Links

• API documentation

• Examples

Installation

Keras Recommenders is available on PyPI as keras-rs:

pip install keras-rs

To try out the latest version of Keras Recommenders, you can use our nightly package:

pip install keras-rs-nightly

Read Getting started with Keras for more information on installing Keras 3 and compatibility with different frameworks.

Quickstart

Train your own cross network

Choose a backend:

import os
os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!

Import KerasRS and other libraries:

import keras
import keras_rs
import numpy as np

Define a simple model using the FeatureCross layer:

vocabulary_size = 32
embedding_dim = 6

inputs = keras.Input(shape=(), name='indices', dtype="int32")
x0 = keras.layers.Embedding(
    input_dim=vocabulary_size,
    output_dim=embedding_dim
)(inputs)
x1 = keras_rs.layers.FeatureCross()(x0, x0)
x2 = keras_rs.layers.FeatureCross()(x0, x1)
output = keras.layers.Dense(units=10)(x2)
model = keras.Model(inputs, output)

Compile the model:

model.compile(
    loss=keras.losses.MeanSquaredError(),
    optimizer=keras.optimizers.Adam(learning_rate=3e-4)
)

Call model.fit() on dummy data:

batch_size = 2
x = np.random.randint(0, vocabulary_size, size=(batch_size,))
y = np.random.random(size=(batch_size,))
model.fit(x, y=y)

Use ranking losses and metrics

If your task is to rank items in a list, you can make use of the ranking losses and metrics which KerasRS provides. Below, we use the pairwise hinge loss and track the nDCG metric:

model.compile(
    loss=keras_rs.losses.PairwiseHingeLoss(),
    metrics=[keras_rs.metrics.NDCG()],
    optimizer=keras.optimizers.Adam(learning_rate=3e-4),
)

Configuring your backend

If you have Keras 3 installed in your environment (see installation above), you can use Keras Recommenders with any of JAX, TensorFlow and PyTorch. To do so, set the KERAS_BACKEND environment variable. For example:

export KERAS_BACKEND=jax

Or in Colab, with:

import os
os.environ["KERAS_BACKEND"] = "jax"

import keras_rs

Compatibility

We follow Semantic Versioning, and plan to provide backwards compatibility guarantees both for code and saved models built with our components. While we continue with pre-release 0.y.z development, we may break compatibility at any time and APIs should not be considered stable.

Citing Keras Recommenders

If Keras Recommenders helps your research, we appreciate your citations. Here is the BibTeX entry:

@misc{kerasrecommenders2024,
  title={KerasRecommenders},
  author={Hertschuh, Fabien and Chollet, Fran\c{c}ois and Sharma, Abheesht and others},
  year={2024},
  howpublished={\url{https://github.com/keras-team/keras-rs}},
}