Hashing layer

Hashing class

tf.keras.layers.Hashing(num_bins, mask_value=None, salt=None, **kwargs)

Implements categorical feature hashing, also known as "hashing trick".

This layer transforms single or multiple categorical inputs to hashed output. It converts a sequence of int or string to a sequence of int. The stable hash function uses tensorflow::ops::Fingerprint to produce the same output consistently across all platforms.

This layer uses FarmHash64 by default, which provides a consistent hashed output across different platforms and is stable across invocations, regardless of device and context, by mixing the input bits thoroughly.

If you want to obfuscate the hashed output, you can also pass a random salt argument in the constructor. In that case, the layer will use the SipHash64 hash function, with the salt value serving as additional input to the hash function.

Example (FarmHash64)

>>> layer = tf.keras.layers.Hashing(num_bins=3)
>>> inp = [['A'], ['B'], ['C'], ['D'], ['E']]
>>> layer(inp)
<tf.Tensor: shape=(5, 1), dtype=int64, numpy=
  array([[1],
         [0],
         [1],
         [1],
         [2]])>

Example (FarmHash64) with a mask value

>>> layer = tf.keras.layers.Hashing(num_bins=3, mask_value='')
>>> inp = [['A'], ['B'], [''], ['C'], ['D']]
>>> layer(inp)
<tf.Tensor: shape=(5, 1), dtype=int64, numpy=
  array([[1],
         [1],
         [0],
         [2],
         [2]])>

Example (SipHash64)

>>> layer = tf.keras.layers.Hashing(num_bins=3, salt=[133, 137])
>>> inp = [['A'], ['B'], ['C'], ['D'], ['E']]
>>> layer(inp)
<tf.Tensor: shape=(5, 1), dtype=int64, numpy=
  array([[1],
         [2],
         [1],
         [0],
         [2]])>

Example (Siphash64 with a single integer, same as salt=[133, 133])

>>> layer = tf.keras.layers.Hashing(num_bins=3, salt=133)
>>> inp = [['A'], ['B'], ['C'], ['D'], ['E']]
>>> layer(inp)
<tf.Tensor: shape=(5, 1), dtype=int64, numpy=
  array([[0],
         [0],
         [2],
         [1],
         [0]])>

Arguments

  • num_bins: Number of hash bins. Note that this includes the mask_value bin, so the effective number of bins is (num_bins - 1) if mask_value is set.
  • mask_value: A value that represents masked inputs, which are mapped to index 0. Defaults to None, meaning no mask term will be added and the hashing will start at index 0.
  • salt: A single unsigned integer or None. If passed, the hash function used will be SipHash64, with these values used as an additional input (known as a "salt" in cryptography). These should be non-zero. Defaults to None (in that case, the FarmHash64 hash function is used). It also supports tuple/list of 2 unsigned integer numbers, see reference paper for details.
  • **kwargs: Keyword arguments to construct a layer.

Input shape

A single or list of string, int32 or int64 Tensor, SparseTensor or RaggedTensor of shape (batch_size, ...,)

Output shape

An int64 Tensor, SparseTensor or RaggedTensor of shape (batch_size, ...). If any input is RaggedTensor then output is RaggedTensor, otherwise if any input is SparseTensor then output is SparseTensor, otherwise the output is Tensor.

Reference