I've designed a variational autoencoder (VAE) that clusters sequential time series data.
To evaluate the performance of VAE on labeled data, First, I run KMeans on the raw data and compare the generated labels with the true labels using Adjusted Mutual Info Score (AMI). Then, after the model is trained, I pass validation data to it, run KMeans on latent vectors, and compare the generated labels with the true labels of validation data using AMI. Finally, I compare the two AMI scores with each other to see if KMeans has better performance on the latent vectors than the raw data.
My question is this: How can we evaluate the performance of VAE when the data is unlabeled?
I know we can run KMeans on the raw data and generate labels for it, but in this case, since we consider the generated labels as true labels, how can we compare the performance of KMeans on the raw data with KMeans on the latent vectors?
Note: The model is totally unsupervised. Labels (if exist) are not used in the training process. They're used only for evaluation.
In unsupervised learning you evaluate the performance of a model by either using labelled data or visual analysis. In your case you do not have labelled data, so you would need to do analysis. One way to do this is by looking at the predictions. If you know how the raw data should be labelled, you can qualitatively evaluate the accuracy. Another method is, since you are using KMeans, is to visualize the clusters. If the clusters are spread apart in groups, that is usually a good sign. However, if they are closer together and overlapping, the labelling of vectors in the respective areas may be less accurate. Alternatively, there may be some sort of a metric that you can use to evaluate the clusters or come up with your own.
Related
I'm training a CNN (one using a series of ConvTranspose2D in pytorch) that uses input data from JSON to constitute an image. Unlike natural language, the input data can be in any order, as it contains info about various sprites in a scene.
In my first attempts to train the model, I didn't change the order of the input data (meaning, on each epoch, each sprite was represented in the same place in the input data). The model learned for about 10 epochs, but then there started to be divergence between the training loss (which continued to go down) and the test loss. So classic overfitting.
I tried to solve this by doing a form of data augmentation where the output data (in this case an image) stayed the same but I shuffled the order of the input data. As I have around 400 sprites, the maximum shuffling is 400!, so theoretically this can vastly expand the amount of training data. For example, instead of 100k JSON documents corresponding to 100K images, by shuffling the order of sprites in the input data, you have 400!*100000 training data points. In practice of course this amount of data is impractical, so I went with around 2m data points for an initial test. The issue I ran into here was that the model was not learning at all - after getting to a certain loss very quickly (after the first few mini-batches), it didn't learn at all for around 4 epochs. So classic underfitting.
Like Goldilocks, I'd like to find "just right" between the initial overfitting and subsequent underfitting. I'm wondering other strategies I could try out. One idea I had was letting the model train on a predetermined order of sprites (the overfitting case) and then, once overfitting starts (ie two straight epochs with divergence between the test and training loss) shuffling the data. I can also play with changing the model, although it can only be so big because of constraints with the hardware and the fact that inference needs to happen in under 20ms.
Are there any papers or techniques that are recommended in this scenario where data augmentation can lead to vastly more data points but results in a model ceasing to learn? Thanks in advance for any tips!
I am trying to save a bunch of trained random forest classifiers in order to reuse them later. For this, I am trying to use pickle or joblib. The problem I encounter is, that the saved files get huge. This seems to be correlated to the amount of data that I use for training (which is several 10-millions of samples per forest, leading to dumped files in the order of up to 20GB!).
Is the RF classifier itself saving the training data in its structure? If so, how could I take the structure apart and only save the necessary parameters for later predictions? Sadly, I could not find anything on the subject of size yet.
Thanks for your help!
Baradrist
Here's what I did in a nutshell:
I trained the (fairly standard) RF on a large dataset and saved the trained forest afterwards, trying both pickle and joblib (also with the compress-option set to 3).
X_train, y_train = ... some data
classifier = RandomForestClassifier(n_estimators=24, max_depth=10)
classifier.fit(X_train, y_train)
pickle.dump(classifier, open(path+'classifier.pickle', 'wb'))
or
joblib.dump(classifier, path+'classifier.joblib', compress=True)
Since the saved files got quite big (5GB to nearly 20GB, compressed aprox. 1/3 of this - and I will need >50 such forests!) and the training takes a while, I experimented with different subsets of the training data. Depending on the size of the train set, I found different sizes for the saved classifier, making me believe that information about the training is pickled/joblibed as well. This seems unintuitive to me, as for predictions, I only need the information of all the trained weak predictors (decision trees) which should be steady and since the number of trees and the max depth is not too high, they should also not take up that much space. And certainly not more due to a larger training set.
All in all, I suspect that the structure is containing more than I need. Yet, I couldn't find a good answer on how to exclude these parts from it and save only the necessary information for my future predictions.
I ran into a similar issue and I also thought in the beginning that the model was saving unnecessary information or that the serialization was introducing some redundancy. It turns out in fact that decision trees are indeed memory hungry structures that consists of multiple arrays of length given by the total number of nodes. Nodes in general grow with the size of data (and parameters like max_depth cannot effectively used to limit growth since the reasonable values still have room to generate huge number of nodes). See details in this answer but the gist is:
a single decision tree can easy grow to a few MBs (example above has a 5MB decision tree for 100K data and a 50MB decision tree for 1M data)
a random forest commonly contains at least 100 such decision tree and for the example above you would have models in the range of 0.5/5GB
compression is usually not enough to reduce to reasonable sizes (1/2, 1/3 are usual ranges)
Other notes:
using a different algorithm models might remain of a more manageable size (e.g. with xgboost I saw much smaller serialized models)
it is probably possible to "prune" some of the data used by decision trees if you only plan it to reuse it for prediction. In particular I imagine the array of impurity and possible those on n_samples might not be needed but I have not checked.
with respect to you hypothesis that the random forest is saving the data on which it is trained: not it is not and the data itself would likely be one or more order of magnitude smaller than the final model
so in principle another strategy if you have a reproducible training pipeline could be to save the data instead of the model and retrain on purpose, but this is only possible if you can spare the time to retrain (for example if in a use case where you have a long running service which has the model in memory and you serialize the model in order to have a backup for when the model goes down)
there are probably also other options to limit growth of random forest, the best one I have found until now is in this answer, where the suggestion is to work with min_samples_leaf to set it as a percentage of data
In Kaggle competitions, we have a train and test dataset. So we usually develop a model on the training dataset and evaluate it with a test dataset that is unseen for the algorithm. I was wondering what is the best method for validation of a regression problem if just one dataset is given to us without any test dataset. I think there might be two approaches:
At the first step, after importing the dataset, it is converted to train and test datasets, with this approach the test set will not see by the algorithm until the last step. After performing preprocessing and feature engineering, we can use cross-validation techniques on the training dataset or use train-test-split to improve the error of our model. Finally, the quality of the model can be checked by the unseen data.
Also, I saw that for regression problems, some data scientists use the whole dataset for testing and validation, I mean they use all the data at the same time.
Could you please help me with which strategy is better? Especially, when the recruiter gives us just a dataset and asks us to develop a model to predict the target variable.
Thanks,
Med
You must divide the Data set in to two parts : Training and validation datasets.
Then train your model on to the training data set. Validate the model on validation data set. The more data you have the better your model can be fitted. Quality checking of the model can be done with validation data set split earlier. You can also check the quality of your model by accuracy and scoring parameters.
When checking the quality of the model you can create your own custom data set which is similar to the values of the original data set.
When on Kaggle, the competition is about to be closed, they will release the actual test data set on which the result of the model is ranked.
The reason is that when you have more data, the algorithm will have more feature label pair to train and validate. This will increase the efficiency of the model.
Approach 2 described in the question is better.
Also, I saw that for regression problems, some data scientists use the
whole data set for testing and validation, I mean they use all the data
at the same time.
Approach one is not preferred as in a competitive platform your model has to perform better. So having lesser training and validation data can affect the accuracy.
Divide your One dataset into a Training dataset and Testing dataset.
While training your model divide your Training dataset into training, validation,and testing and run the model and check the accuracy & save the model.
Import the save model and predict the testing dataset.
I have a very complex LSTM based neural network model which I'm training on Quora Duplicate Question pairs. There are approximately 400 000 sentence pairs in the original dataset. It would take a lot of processing power and computation time to train on the entire (or 80%) dataset. Would it be unwise if I choose a random subset of the dataset (say 8000 pairs only) for training and 2000 for testing? Would it have a severe impact on the performance? Is always "more the data, better the model" true?
As a Rule of Thumb, Deep Neural Networks usually benefit from more data.
If you have a well described model and properly engineered your inputs, you will lose if you chose a smaller subset of your dataset.
However, you could always evaluate this by using metrics. Check how your loss decreases at every sample size, starting from your 8000 pairs.
For big problems, you always have to keep in mind that computation time is usually also big.
The following is how I understand the point of parameter sharing in RNNs:
In regular feed-forward neural networks, every input unit is assigned an individual parameter, which means that the number of input units (features) corresponds to the number of parameters to learn. In processing e.g. image data, the number of input units is the same over all training examples (usually constant pixel size * pixel size * rgb frames).
However, sequential input data like sentences can come in highly varying lengths, which means that the number of parameters will not be the same depending on which example sentence is processed. That is why parameter sharing is necessary for efficiently processing sequential data: it makes sure that the model always has the same input size regardless of the sequence length, as it is specified in terms of transition from one state to another. It is thus possible to use the same transition function with the same weights (input to hidden weights, hidden to output weights, hidden to hidden weights) at every time step. The big advantage is that it allows generalization to sequence lengths that did not appear in the training set.
My questions are:
Is my understanding of RNNs, as summarized above, correct?
In the actual code example in Keras I looked at for LSTMs, they padded the sentences to equal lengths before all. By doing so, doesn't this wash away the whole purpose of parameter sharing in RNNs?
Parameter Sharing
Being able to efficiently process sequences of varying length is not the only advantage of parameter sharing. As you said, you can achieve that with padding. The main purpose of parameter sharing is a reduction of the parameters that the model has to learn. This is the whole purpose of using a RNN.
If you would learn a different network for each time step and feed the output of the first model to the second etc. you would end up with a regular feed-forward network. For a number of 20 time steps, you would have 20 models to learn. In Convolutional Nets, parameters are shared by the Convolutional Filters because when we can assume that there are similar interesting patterns in different regions of the picture (for example a simple edge). This drastically reduces the number of parameters we have to learn. Analogously, in sequence learning we can often assume that there are similar patterns at different time steps. Compare 'Yesterday I ate an apple' and 'I ate an apple yesterday'. These two sentences mean the same, but the 'I ate an apple' part occurs on different time steps. By sharing parameters, you only have to learn what that part means once. Otherwise, you'd have to learn it for every time step, where it could occur in your model.
There is a drawback to sharing the parameters. Because our model applies the same transformation to the input at every time step, it now has to learn a transformation that makes sense for all time steps. So, it has to remember, what word came in which time step, i.e. 'chocolate milk' should not lead to the same hidden and memory state as 'milk chocolate'. But this drawback is small compared to using a large feed-forward network.
Padding
As for padding the sequences: the main purpose is not directly to let the model predict sequences of varying length. Like you said, this can be done by using parameter sharing. Padding is used for efficient training - specifically to keep the computational graph during training low. Without padding, we have two options for training:
We unroll the model for each training sample. So, when we have a sequence of length 7, we unroll the model to 7 time steps, feed the sequence, do back-propagation through the 7 time steps and update the parameters. This seems intuitive in theory. But in practice, this is inefficient, because TensorFlow's computational graphs don't allow recurrency, they are feedforward.
The other option is to create the computational graphs before starting training. We let them share the same weights and create one computational graph for every sequence length in our training data. But when our dataset has 30 different sequence lengths this means 30 different graphs during training, so for large models, this is not feasible.
This is why we need padding. We pad all sequences to the same length and then only need to construct one computational graph before starting training. When you have both very short and very long sequence lengths (5 and 100 for example), you can use bucketing and padding. This means, you pad the sequences to different bucket lengths, for example [5, 20, 50, 100]. Then, you create a computational graph for each bucket. The advantage of this is, that you don't have to pad a sequence of length 5 to 100, as you would waste a lot of time on "learning" the 95 padding tokens in there.