tensorflow
/
recommenders
mirror of https://github.com/tensorflow/recommenders.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
recommenders/CHANGELOG.md

6.4 KiB
Raw Permalink Blame History

Changelog

[unreleased][unreleased]

[0.7.6][2025-11-26]

Changed

  • Add tf-keras (Keras 2) to requirements.txt and pip_install.sh.

[0.7.5][2025-11-25]

Changed

  • Updated release test script to use export TF_USE_LEGACY_KERAS=1. This is a no-op for the TFRS library but should allow us to push new releases to PyPI.

[0.7.4][2025-11-04]

Added

  • Add tfrs.layers.feature_multiplexing.UnifiedEmbedding and tutorial.

[0.7.3][2023-02-02]

Changed

  • The Retrieval task now accepts a list of factorized metrics instead of a single optional metric.

Added

  • tfrs.experimental.optimizers.ClippyAdagrad: a new optimizer based on tf.keras.optimizers.Adagrad that is able to improve training stability.
  • tfrs.metrics.FactorizedTopK now accepts sample weights which are used to compute weighted top k metrics.

[0.7.2][2022-09-28]

  • Improved support for using TPUEmbedding under parameter server strategy.

[0.7.0][2022-07-07]

A number of changes to make factorized top-K metric computation more accurate and less prone to user error.

Changed

  • tfrs.layers.embedding.TPUEmbedding now supports input features with dynamic shape. batch_size argument is deprecated and no longer required.

  • tfrs.layers.embedding.TPUEmbedding now supports running on different versions of TPU.

  • Pinned TensorFlow to >= 2.9.0 which works with Scann 1.2.7.

  • tfrs.tasks.Ranking.call now accepts a compute_batch_metrics argument to allow switching off batch metric computation. Following this change, 'compute_metrics'argument does not impact computation of batch metrics.

Breaking changes

  • tfrs.metrics.FactorizedTopK requires the candidate ids for positive candidates to be supplied when using approximate top-K sources. Each top-K layer now has an exact method to broadcast its ability to return exact or approximate top-K results.
  • Removed metrics constructor parameter for tfrs.metrics.FactorizedTopK. FactorizedTopK only makes sense with top-k metrics, and this change enforces this.
  • Replaced the k constructor argument in tfrs.metrics.FactorizedTopK with ks: a list of k values at which to compute the top k metric.

Changed

  • The tfrs.metrics.FactorizedTopK metric can now compute candidate-id based metrics when given the true_candidate_ids argument in its call method.

Added

  • The Retrieval task now also accepts a loss_metrics argument.

[0.6.0][2021-08-23]

Changed

  • Pinned TensorFlow to >= 2.6.0, which works with Scann 1.2.3.

Breaking changes

  • TopK layer indexing API changed. Indexing with datasets is now done via the index_from_dataset method. This change reduces the possibility of misaligning embeddings and candidate identifiers when indexing via indeterministic datasets.

[0.5.2][2021-07-15]

Fixed

Added

  • Added batch_metrics to tfrs.tasks.Retrieval for measuring how good the model is at picking out the true candidate for a query from other candidates in the batch.
  • Added tfrs.experimental.layers.embedding.PartialTPUEmbedding layer, which uses tfrs.layers.embedding.TPUEmbedding for large embedding lookups and tf.keras.layers.Embedding for smaller embedding lookups.

[0.5.1][2021-05-14]

Changed

[0.5.0][2021-05-06]

Changed

  • Fixed the bug in tfrs.layers.loss.SamplingProbablityCorrection that logits should subtract the log of item probability.
  • tfrs.experimental.optimizers.CompositeOptimizer: an optimizer that composes multiple individual optimizers which can be applied to different subsets of the model's variables.
  • tfrs.layers.dcn.Cross and DotInteraction layers have been moved to tfrs.layers.feature_interaction package.

Added

  • tfrs.experimental.models.Ranking, an experimental pre-built model for ranking tasks. Can be used as DLRM like model with Dot Product feature interaction or DCN like model with Cross layer.

[0.4.0][2021-01-20]

Added

  • TopK layers now come with a query_with_exclusions method, allowing certain candidates to be excluded from top-k retrieval.
  • TPUEmbedding Keras layer for accelerating embedding lookups for large tables with TPU.

Changed

  • factorized_top_k.Streaming layer now accepts a query model, like other factorized_top_k layers.

  • Updated ScaNN to 1.2.0, which requires TensorFlow 2.4.x. When not using ScaNN, any TF >= 2.3 is still supported.

[0.3.2][2020-12-22]

Changed

  • Pinned TensorFlow to >= 2.3 when ScaNN is not being installed. When ScaNN is being installed, we pin on >= 2.3, < 2.4. This allows users to use TFRS on TF 2.4 when they are not using ScaNN.

[0.3.1][2020-12-22]

Changed

  • Pinned TensorFlow to 2.3.x and ScaNN to 1.1.1 to ensure TF and ScaNN versions are in lockstep.

[0.3.0][2020-11-18]

Added

  • Deep cross networks: efficient ways of learning feature interactions.
  • ScaNN integration: efficient approximate maximum inner product search for fast retrieval.

[0.2.0][2020-10-15]

Added

  • tfrs.tasks.Ranking.call now accepts a compute_metrics argument to allow switching off metric computation.
  • tfrs.tasks.Ranking now accepts label and prediction metrics.
  • Add metrics setter/getters on tfrs.tasks.Retrieval.

Breaking changes

  • Corpus retrieval metrics and layers have been reworked.

    tfrs.layers.corpus.DatasetTopk has been removed, tfrs.layers.corpus.DatasetIndexedTopK renamed to tfrs.layers.factorized_top_k.Streaming, tfrs.layers.ann.BruteForce renamed to tfrs.layers.factorized_top_k.BruteForce. All top-k retrieval layers (BruteForce, Streaming) now follow a common interface.

Changed

  • Dataset parallelism enabled by default in DatasetTopK and DatasetIndexedTopK layers, bringing over 2x speed-ups to evaluations workloads.
  • evaluate_metrics argument to tfrs.tasks.Retrieval.call renamed to compute_metrics.