I came across this research paper released by YouTube, on how they use deep learning neural networks for recommendations. It's located here: https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/45530.pdf

In the paper, the candidate generation neural network model outputs a softmax with 256 dimensions, which acts as an "output embedding" of each of the 1M video classes.

How is this possible to implement in tensorflow, for example? Isn't softmax supposed to be only 1-Dimensional. If the model outputs an "embedding" like this, as they say it does, how would the training data's labels be formatted as 256-dimensional? In other words, how do they compute the 256-dimensional vector for each of the videos in their training dataset?

Thank you so much for your time and help, guys!


1 Answer 1


You are confusing "dimensions" with "order of tensor". A softmax with 256 different categories is a 256 dimensional vector, but is also a tensor with order 1 (whilst a matrix is a tensor of order 2). The paper is using the technical terms correctly, so the 256 dimensional vector is just a normal vector with 256 scalar entries.

Therefore a 256-dimensional softmax in TensorFlow is typically an output layer that looks something like this:

y = tf.nn.softmax(tf.matmul(h, W) + b)

where h is the last hidden layer, W is the weight matrix n x 256, and b is the bias 1 x 256 vector.

In the paper, the candidate generation neural network model outputs a softmax with 256 dimensions, which acts as an "output embedding" of each of the 1M video classes

That is a description of the training process that compresses 1M different inputs to 256-dimensional output for use as an embedding for recommendation matches. The softmax is at the output, and as far as I can see is just a normal softmax classifier output as seen in many other classifier networks (except the result is not technically being used to classify anything). I am not clear on what supervision data was used or on what the input representation was. However, I don't think it likely that 1M "classes" ever appear as e.g. 1-hot encoding, because that would not scale out usefully to the many other millions of videos - the point of the embedding is to turn disparate features of the videos into something that be used as a similarity measure, that can be run on any video stored in YouTube.

  • $\begingroup$ Hi, thanks for your help Neil! In the paper, it says that they are applying a softmax over 1M classes (each of which is a youtube video). However, they say that the final output layer also acts as an "output embedding layer," with dimension 256 (which means that each class has an "embedding" vector of size 256). So, wouldn't the weights and biases be of shape n x num_classes, and not n x 256? Pls correct me if wrong. Thanks! $\endgroup$ Commented Apr 8, 2017 at 21:15
  • $\begingroup$ Also, would the weights of the softmax layer, which you have provided as an example, represent the embeddings for the different classes. If so, can we use these embeddings to find similar classes in an N-dimensional space, as they do in the original layer? Thanks @neil-slater $\endgroup$ Commented Apr 8, 2017 at 21:23
  • $\begingroup$ I have skim-read the paper, and see no indication that the embedding is anything other than a normal softmax as I described. I could not realistically re-create the full architecture from that paper myself so perhaps I have missed something. However, the "millions of classes" looks to me like a problem statement, and not a reference to the network architecture. As far as I can see, the network uses a normal softmax with 256 classes (as a "summary"), it is other parts of the architecture and pipeline which help it upscale to match from such a large number of candidate videos. $\endgroup$ Commented Apr 8, 2017 at 21:29
  • 1
    $\begingroup$ Hi, it's on page 4, Section 3.5, first few lines of that section. Also, it says that they do a softmax over millions of classes (each of which is a youtube video), which is why they use a sampled softmax during training in the first place (as computing full softmax for a million+ classes will be unfeasible). Really thanks for taking the time to help me! You're awesome! $\endgroup$ Commented Apr 8, 2017 at 21:31
  • 1
    $\begingroup$ on the paper it says the following (directly quoted): "To efficiently train such a model with millions of classes, we rely on a technique to sample negative classes from the background distribution (“candidate sampling”) and then correct for this sampling via importance weighting [10]." From this statement, it does seem that they're training a model with millions of classes, right? Thanks $\endgroup$ Commented Apr 8, 2017 at 23:23

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.