ContrastiveLossLayer

✖
`ContrastiveLossLayer`

[Experimental]

✖

represents a loss layer that computes a loss based on a distance metric and a target that specifies whether the distance should be minimized or maximized.

✖

ContrastiveLossLayer[margin]

specifies a distance above which the loss is zero for True targets.

Details and Options

ContrastiveLossLayer is typically used in conjunction with NetPairEmbeddingOperator in order to learn an embedding from an input into a vector space, such that similar inputs cluster together in the vector space and dissimilar inputs are separated.
ContrastiveLossLayer exposes the following ports for use in NetGraph etc.:
"Input" a real number representing a distance

"Target" True if the distance should be maximized, False if it should be minimized

"Loss" a real number
ContrastiveLossLayer[margin] computes the following loss:

ContrastiveLossLayer[…][<|"Input"in,"Target"target|>] explicitly computes the loss from applying the layer.
ContrastiveLossLayer[…][<|"Input"{in₁,in₂,…},"Target"{target₁,target₂,…}|>] explicitly computes losses for each of the in_i and target_i.
When given a NumericArray as input, the output will be a NumericArray.
ContrastiveLossLayer is typically used inside NetGraph to construct a training network for a learned embedding.
A ContrastiveLossLayer[…] can be provided as the third argument to NetTrain when training a specific network.
When appropriate, ContrastiveLossLayer is automatically used by NetTrain if an explicit loss specification is not provided.
Options[ContrastiveLossLayer] gives the list of default options to construct the layer. Options[ContrastiveLossLayer[…]] gives the list of default options to evaluate the layer on some data.
Information[ContrastiveLossLayer[…]] gives a report about the layer.
Information[ContrastiveLossLayer[…],prop] gives the value of the property prop of ContrastiveLossLayer[…]. Possible properties are the same as for NetGraph.

Examples

open allclose all

Basic Examples (2)Summary of the most common use cases

Create a ContrastiveLossLayer with a given margin:

In[1]:=1

✖

https://wolfram.com/xid/0bcm5x1pjnedlarrpmt8y-s0idy5

Out[1]=1

Create a ContrastiveLossLayer:

In[1]:=1

✖

https://wolfram.com/xid/0bcm5x1pjnedlarrpmt8y-s5sily

Out[1]=1

Apply it to some data:

In[2]:=2

✖

https://wolfram.com/xid/0bcm5x1pjnedlarrpmt8y-0n9a3o

Out[2]=2

If the target is True, the loss is nonzero only when the input distance is less than the default margin of 0.5:

In[3]:=3

✖

https://wolfram.com/xid/0bcm5x1pjnedlarrpmt8y-o5h7ml

Out[3]=3

If the target is False, the loss is proportional to the input distance:

In[4]:=4

✖

https://wolfram.com/xid/0bcm5x1pjnedlarrpmt8y-2oxpuu

Out[4]=4

Applications (1)Sample problems that can be solved with this function

Train a multilayer perceptron to embed a synthetic dataset based only on its topology. First, create the training data on a spiral-like manifold that is dense in the plane:

In[1]:=1