The Actor Mimic paper talks about implementing an action-masking procedure. I quote
While playing a certain game, we
mask out AMN action outputs that are not valid for that game and take the softmax over only the subset of valid actions
Does anyone have an idea about how this action masking can be implemented in say Tensorflow? In specifc, how would one take a softmax only over specified subset of actions?
Say you have a valid state tensor which contains ones and zeros.
is_valid = [1, 0, 1, ...]
and then you have an actions tensor on which you want to take the softmax over those values which are valid. You could do the following.
(tf.exp(actions) * is_valid) / (tf.reduce_sum(tf.exp(actions) * is_valid) + epsilon)
In this case the is_valid is masking out the invalid values in the sum. I would also add a small epsilon to the division for the sake of numerical stability so you can never divide by zero.
You should rely on the built in softmax function. i.e. you should first mask the invalid action in your tensor by using a boolean_mask and then apply the softmax function.
(The solution provided by chasep255 has numerical issues.)
Related
I am using Pytorch to training some neural networks. The part I am confused about is:
prediction = myNetwork(img_batch)
max_act = prediction.max(1)[0].sum()
loss = softcrossentropy_loss - alpha * max_act
In the above codes, "prediction" is the output tensor of "myNetwork".
I hope to maximize the larget output of "prediction" over a batch.
For example:
[[-1.2, 2.0, 5.0, 0.1, -1.5] [9.6, -1.1, 0.7, 4,3, 3.3]]
For the first prediction vector, the 3rd element is the larget, while for the second vector, the 1st element is the largets. And I want to maximize "5.0+9.6", although we cannot know what index is the larget output for a new input data.
In fact, my training seems to be successful, because the "max_act" part was really increased, which is the desired behavior to me. However, I heard some discussion about whether max() operation is differentiable or not:
Some says, mathmatically, max() is not differentiable.
Some says, max() is just an identity function to select the largest element, and this largest element is differentiable.
So I got confused now, and I am worried if my idea of maximizing "max_act" is wrong from the beginning.
Could someone provide some guidance if max() operation is differentiable in Pytorch?
max is differentiable with respect to the values, not the indices. It is perfectly valid in your application.
From the gradient point of view, d(max_value)/d(v) is 1 if max_value==v and 0 otherwise. You can consider it as a selector.
d(max_index)/d(v) is not really meaningful as it is a discontinuous function, with only 0 and undefined as possible gradients.
Quantization schemes are generally non-differentiable because they pass through the threshold, such as round or sign function. It means that we can not get the gradient of trainable variables due to the nature of chain rule.
Instead, we can use a trick called 'straight-through-estimator', which enable us to back-propagating the gradient of individual trainable variables.
One such method is tf.fake_quant_with_min_max_vars, The advantages of this format are that it can represent arbitrary magnitudes of ranges, they don’t have to be symmetrical, it can represent signed and unsigned values, and the linear spread makes doing multiplications straightforward.Blog, Paper.
So, my question is, can we differentiate the fake_quant function? And if so, does this function apply 'straight-through-estimator'?
I did a little bit of this with some snippet code
x = tf.cast(np.random.normal(0,1,(10,10), tf.float32)
x_q = tf.fake_quant_with_min_max_vars(x, min=tf.reduce_min(x), max=tf.reduce_max(x), num_bits=3)
grad = tf.gradients(x_q, x)
In that case, almost every grad have value 1(i.e, gradient 1), which means it pass through the gradient itself.
However, sometimes a few samples have gradient 0, or other constant, such as 2, 3, 4...
Am I missing what's going on?
To be clear, I am referring to "self-attention" of the type described in Hierarchical Attention Networks for Document Classification and implemented many places, for example: here. I am not referring to the seq2seq type of attention used in encoder-decoder models (i.e. Bahdanau), although my question might apply to that as well... I am just not as familiar with it.
Self-attention basically just computes a weighted average of RNN hidden states (a generalization of mean-pooling, i.e. un-weighted average). When there are variable length sequences in the same batch, they will typically be zero-padded to the length of the longest sequence in the batch (if using dynamic RNN). When the attention weights are computed for each sequence, the final step is a softmax, so the attention weights sum to 1.
However, in every attention implementation I have seen, there is no care taken to mask out, or otherwise cancel, the effects of the zero-padding on the attention weights. This seems wrong to me, but I fear maybe I am missing something since nobody else seems bothered by this.
For example, consider a sequence of length 2, zero-padded to length 5. Ultimately this leads to the attention weights being computed as the softmax of a similarly 0-padded vector, e.g.:
weights = softmax([0.1, 0.2, 0, 0, 0]) = [0.20, 0.23, 0.19, 0.19, 0.19]
and because exp(0)=1, the zero-padding in effect "waters down" the attention weights. This can be easily fixed, after the softmax operation, by multiplying the weights with a binary mask, i.e.
mask = [1, 1, 0, 0, 0]
and then re-normalizing the weights to sum to 1. Which would result in:
weights = [0.48, 0.52, 0, 0, 0]
When I do this, I almost always see a performance boost (in the accuracy of my models - I am doing document classification/regression). So why does nobody do this?
For a while I considered that maybe all that matters is the relative values of the attention weights (i.e., ratios), since the gradient doesn't pass through the zero-padding anyway. But then why would we use softmax at all, as opposed to just exp(.), if normalization doesn't matter? (plus, that wouldn't explain the performance boost...)
Great question! I believe your concern is valid and zero attention scores for the padded encoder outputs do affect the attention. However, there are few aspects that you have to keep in mind:
There are different score functions, the one in tf-rnn-attention uses simple linear + tanh + linear transformation. But even this score function can learn to output negative scores. If you look at the code and imagine inputs consists of zeros, vector v is not necessarily zero due to bias and the dot product with u_omega can boost it further to low negative numbers (in other words, plain simple NN with a non-linearity can make both positive and negative predictions). Low negative scores don't water down the high scores in softmax.
Due to bucketing technique, the sequences within a bucket usually have roughly the same length, so it's unlikely to have half of the input sequence padded with zeros. Of course, it doesn't fix anything, it just means that in real applications negative effect from the padding is naturally limited.
You mentioned it in the end, but I'd like to stress it too: the final attended output is the weighted sum of encoder outputs, i.e. relative values actually matter. Take your own example and compute the weighted sum in this case:
the first one is 0.2 * o1 + 0.23 * o2 (the rest is zero)
the second one is 0.48 * o1 + 0.52 * o2 (the rest is zero too)
Yes, the magnitude of the second vector is two times bigger and it isn't a critical issue, because it goes then to the linear layer. But relative attention on o2 is just 7% higher, than it would have been with masking.
What this means is that even if the attention weights won't do a good job in learning to ignore zero outputs, the end effect on the output vector is still good enough for the decoder to take the right outputs into account, in this case to concentrate on o2.
Hope this convinces you that re-normalization isn't that critical, though probably will speed-up learning if actually applied.
BERT implementation applies a padding mask for calculating attention score.
Adds 0 to the non-padding attention score and adds -10000 to padding attention scores. the e^-10000 is very small w.r.t to other attention score values.
attention_score = [0.1, 0.2, 0, 0, 0]
mask = [0, 0, -10000, -10000] # -10000 is a large negative value
attention_score += mask
weights = softmax(attention_score)
I'm currently trying to implement a custom loss function (precision) with a binary outcome but Tensorflow backend refuses to use round function which is necessary to be used in order to generate a '0' or '1'.
As far as I have investigated, this is because Tensorflow defines the gradient of the round as None and the loss function can't return None.
I have currently implemented this custom loss to create as close as is possible '0' or '1' in R Keras interface.
precision_loss<-function(y_true,y_pred){
y_pred_pos = K$clip(y_pred, 0, 1)
#Custom sigmoid to generate '0' '1'
y_pred_pos = K$maximum(0,K$minimum(1,(y_pred_pos+0.0625)/0.125))
y_pred_neg = 1 - y_pred_pos
y_pos = K$clip(y_true, 0, 1)
#Custom sigmoid to generate '0' '1'
y_pos = K$maximum(0,K$minimum(1,(y_pos+0.0625)/0.125))
y_neg = 1 - y_pos
#Generate confusion matrix counts
tp = K$sum(y_pos*y_pred_pos)
tn = K$sum(y_neg*y_pred_neg)
fp = K$sum(y_neg*y_pred_pos)
fn = K$sum(y_pos*y_pred_neg)
return(1-(tp/(tp+fp+K$epsilon())))
}
Notice the "sigmoid" : K$maximum(0,K$minimum(1,(y_pos+0.0625)/0.125))
What I wanted to implement is a workaround for this one:
precision_loss<-function(y_true, y_pred){
y_pred_pos = K$round(K$clip(y_pred, 0, 1))
y_pred_neg = 1 - y_pred_pos
y_pos = K$round(K$clip(y_true, 0, 1))
y_neg = 1 - y_pos
#Generate confusion matrix counts
tp = K$sum(K$clip(y_pos * y_pred_pos,0,1))
tn = K$sum(K$clip(y_neg * y_pred_neg,0,1))
fp = K$sum(K$clip(y_neg * y_pred_pos,0,1))
fn = K$sum(K$clip(y_pos * y_pred_neg,0,1))
return(1-(tp/(tp+fp+K$epsilon())))
}
Some of you have an alternative implementation without using round to generate binary outcomes in the loss function?
PD: In custom metrics function the round is allowed
In order to build a binary loss function, it wouldn't be enough to just build the custom loss function itself. You would also have to pre-define the gradients.
Your high-dimensional loss function would be zero for some points and one for all others. For all non-continuous points in this space, it would be impossible to analytically compute a gradient (i.e. the concept of a gradient doesn't even exist for such points), so you would have to just define one. And for all the continuous points in this space (e.g. an open set in which all loss values are 1), the gradient would exist, but it would be zero, so you would also have to pre-define the gradient values, otherwise your weights wouldn't move at all.
That means either way you would have to define your own custom "gradient" computation function that replaces Keras' (i.e. TensorFlow's) automatic differentiation engine for that particular node in the graph (the loss function node).
You could certainly achieve this by modifying your local copy of Keras or TensorFlow, but nothing good can come from it.
Also, even if you managed to do this, consider this: If your loss function returns only 0 or 1, that means it can only distinguish between two states: The model's prediction is either 100% correct (0 loss) or it is not 100% correct (1 loss). The magnitude of the gradient would have to be the same for all non-100% cases. Is that a desirable property?
Your quasi-binary sigmoid solution has the same problem: The gradient will be almost zero almost everywhere, and in the few points where it won't be almost zero, it will be almost infinity. If you try to train a model with that loss function, it won't learn anything.
As you noticed a custom loss function need to be based on functions which have their gradients defined (in order to minimise the loss function), which is not necessary for a simple metric. Some functions like “round” and “sign” are difficult to use in loss function since their gradients are either null all the time or infinite which is not helpful for minimisation. That’s probably why their gradients are not defined, by default.
Then, you have two options:
Option 1: you use the round function but you need to add your custom gradient for round, to substitute it in backend.
Option 2: you define another loss function without using round
You chose option 2, which is the best option I think. But your “sigmoid” is very linear, so probably, not a good approximation of your “round” function. You could use an actual sigmoid which is slower due to the use of exponential but you could obtain a similar result with a modified softsign:
max_gradient=100
K$maximum(0,K$minimum(1,0.5*(1+(max_gradient*y_pos)/(1+ max_gradient*abs(y_pos)))))
The max_gradient coefficient can be used to make your edge more sharp, around 0.5. It defines the maximum gradient at 0.5.
In tensorflow.contrib.seq2seq's AttentionWrapper, what does "depth" refer to as stated in the attention_layer_size documentation? When the documentation says to "use the context as attention" if the value is None, what is meant by "the context"?
In Neural Machine Translation by Jointly Learning to Align and Translate they give a description of the (Bahdanau) attention mechanism; essentially what happens is that you compute scalar "alignment scores" a_1, a_2, ..., a_n that indicate how important each element of your encoded input sequence is at a given moment in time (i.e. which part of the input sentence you should pay attention to right now in the current timestep).
Assuming your (encoded) input sequence that you want to "pay attention"/"attend over" is a sequence of vectors denoted as e_1, e_2, ..., e_n, the context vector at a given timestep is the weighted sum over all of these as determined by your alignment scores:
context = c := (a_1*e_1) + (a_2*e_2) + ... + (a_n*e_n)
(Remember that the a_k's are scalars; you can think of this as an "averaged-out" letter/word in your sentence --- so ideally if your model is trained well, the context looks most similar to the e_i you want to pay attention to the most, but bears a little bit of resemblance to e_{i-1}, e_{i+1}, etc. Intuitively, think of a "smeared-out" input element, if that makes any sense...)
Anyway, if attention_layer_size is not None, then it specifies the number of hidden units in a feedforward layer within your decoder that is used to mix this context vector with the output of the decoder's internal RNN cell to get the attention value. If attention_layer_size == None, it just uses the context vector above as the attention value, and no mixing of the internal RNN cell's output is done. (When I say "mixing", I mean that the context vector and the RNN cell's output are concatenated and then projected to the dimensionality that you specify by setting attention_layer_size.)
The relevant part of the implementation is at this line and has a description of how it's computed.
Hope that helps!