Multilayer Perceptron

This parameter defines the maximum number of epochs for the training. Independent of the model’s quality, the training will terminate after these many epochs. Note, that the training can also stop earlier if the loss converged (see Patience and Tolerance.

Setting this parameter can be useful to limit the training time for a model. Restricting the computational budget can serve the purpose of regularization and mitigate overfitting, which becomes a risk with a large number of epochs.

This parameter defines the minimum number of epochs for the training. Independent of the model’s quality, the training will at least run this many epochs.

Setting this parameter can be useful to avoid early stopping, but also increases the minimal training time of a model.

This parameter defines the maximum number of unproductive consecutive epochs. An epoch is unproductive if it does not improve the training loss by at least a tolerance fraction of the current loss.

Assuming the training ran for minEpochs, this parameter defines when the training converges.

Setting this parameter can lead to a more robust training and avoid early termination similar to minEpochs. However, a high patience can result in running more epochs than necessary.

In our experience, reasonable values for patience are in the range 1 to 3.

This parameter defines when an epoch is considered unproductive and together with patience defines the convergence criteria for the training. An epoch is unproductive if it does not improve the training loss by at least a tolerance fraction of the current loss.

A lower tolerance results in more sensitive training with a higher probability to train longer. A high tolerance means a less sensitive training and hence resulting in more epochs counted as unproductive.

When updating the weights, we move in the direction dictated by the Adam optimizer based on the loss function’s gradients. How much we move per weights update, you can configure via the learningRate parameter.

This parameter defines how many training examples are grouped in a single batch.

The gradients are computed concurrently on the batches using concurrency many threads. At the end of an epoch the gradients are summed and scaled before updating the weights. The batchSize does not affect the model quality, but can be used to tune for training speed. A larger batchSize increases the memory consumption of the computation.

This parameter defines the influence of the regularization term in the loss function. While the regularization can avoid overfitting, a high value can even lead to underfitting. The minimal value is zero, where the regularization term has no effect at all.

This parameter defines the shape of the neural network. Each entry represents the number of neurons in a layer. The length of the list defines the number of hidden layers. Deeper and larger networks can theoretically approximate high degree surfaces better, at the expense of having more weights (and biases) that need to be trained.

This parameter introduces the concept of class weights, studied in 'Focal Loss for Dense Object Detection' by T. Lin et al. It is often called balanced cross entropy. It assigns a weight to each class in the cross-entropy loss function, thus allowing the model to treat different classes with varying importance. It is defined for each example as:

where at denotes the class weight of the true class.pt denotes the probability of the true class.

For class-imbalanced problems, the class weights are often set to the inverse of class frequencies to improve the inductive bias of the model on minority classes.

This parameter introduces the concept of focal loss, again studied in 'Focal Loss for Dense Object Detection' by T. Lin et al. When focusWeight is a value greater than zero, the loss function changes from standard Cross-Entropy Loss to Focal Loss. It is defined for each example as:

where pt denotes the probability of the true class. The focusWeight parameter is the exponent noted as g.

Increasing focusWeight will guide the model towards trying to fit "hard" misclassified examples. A hard misclassified example is an example for which the model has a low predicted probability for the true class. In the above equation, the loss will be exponentially higher for low-true-class-probability examples, thus tuning the model towards trying to fit them, at the expense of potentially being less confident on "easy" examples.

In class-imbalanced datasets, the minority class(es) are typically harder to classify correctly. Read more about class imbalance for Link Prediction in Class Imbalance.