Cross entropy loss

As explained in Graph Neural Networks in Action

CrossEntropyLoss is a PyTorch loss module that measures classification error from logits and target class labels.

For a multiclass node-classification model, loss gives a way to track prediction error: lower is better. Log loss is used alongside F1 score to compare GCN and GraphSAGE models. The reported scores are evaluation results; they do not show how to configure PyTorch’s CrossEntropyLoss module or what inputs to pass to it. section 3.1.4

Use loss at two points in the workflow:

• Plot training and validation loss after each epoch. If training loss keeps falling while validation loss rises, the model is overfitting; retain the model instance with the lowest validation loss. section 3.1.4
• Compare validation-set log loss with F1 score. A single score need not settle model choice: prediction requirements and the consequences of errors matter. section 3.1.4 section 3.2.1

Choosing a neighborhood aggregation

With mean, sum, and max aggregation in GraphSAGE, max has both the highest F1 score (0.7449) and lowest log loss (2.1039). A later list-aggregation comparison is less straightforward: the standard list raises F1 to 0.7484 but also raises log loss to 2.622. Check both measures rather than treating an F1 improvement as an across-the-board gain. section 3.2.1 section 3.2.2

Figure 3.1 Training and validation loss curves for the GCN model (left) and GraphSAGE model (right) trained in this section. The divergence of the validation from the training curve signals over-fitting, where the model learns the training data too well and at the expense of generalizing to new data.

The training and validation curves make the point where falling training loss stops indicating better generalization visible. section 3.1.4

How Graph Neural Networks in Action covers it

How deep it goes

Works through loss curves and metric comparisons, but does not specify CrossEntropyLoss inputs, implementation, or a mathematical derivation.

Examples

Compares GCN and GraphSAGE validation scores, then contrasts mean, sum, max, and list aggregation results.

What it assumes

Introduces loss as a measure of prediction quality while assuming a trained classification model with training and validation results.

What you can do after

Evaluate/understand model trade-offs by reading validation-loss curves and comparing log loss with F1 score.

How it connects

Connects log loss to F1 score, validation loss, overfitting, GCN, GraphSAGE, and neighborhood aggregation.

liveBookmanning.com

Read Graph Neural Networks in Action on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA classification loss that measures the mismatch between a predicted probability distribution over classes and the target distribution.
• 

  liveBookmanning.com
  Grokking Machine LearningA multiclass classification loss that compares one-hot class labels with predicted class probabilities using cross-entropy.
• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA differentiable classification loss that measures the mismatch between predicted and target probability distributions.
• 

  liveBookmanning.com
  Learn Generative AI with PyTorchA loss measure that compares predicted token distributions with the target next tokens for multiclass sequence prediction.
• 

  liveBookmanning.com
  Build a Large Language Model (From Scratch)A measure of how far a language model's predicted token distribution is from the target token distribution, used to score predictions during training and evaluation.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second EditionA loss value based on cross-entropy, used here as the quantity minimized during training.
• 

  liveBookmanning.com
  Knowledge Graphs and LLMs in ActionCross-entropy loss is a classification loss that penalizes incorrect probability assignments by comparing predicted probabilities with target labels.
• 

  liveBookmanning.com
  Reinforcement Learning from Human FeedbackCross-entropy is the expected negative log probability assigned by one distribution to outcomes drawn from another distribution.
• 

  liveBookmanning.com
  Machine Learning System DesignA classification loss that penalizes incorrect probabilistic predictions using the negative logarithm of the probability assigned to the true class.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA classification loss that measures the mismatch between predicted probability distributions and true token labels.
• 

  liveBookmanning.com
  How Large Language Models WorkA cross-entropy loss function measures the discrepancy between a target probability distribution and a model's predicted probability distribution.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)Categorical cross-entropy loss measures the discrepancy between predicted class probabilities and the ground-truth class in multicategory classification.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AICrossEntropyLoss is a PyTorch loss-function module that combines class-logit normalization with negative log-likelihood for classification.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionLog loss is a probabilistic prediction metric based on the negative logarithm of the probability assigned to the observed target.
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionCategorical cross-entropy is a multiclass classification loss that measures the negative log-likelihood of the target class under predicted class probabilities and expects categorically encoded labels.
• 

  liveBookmanning.com
  Build a Reasoning Model (From Scratch)A loss function that measures the average negative log probability assigned to the correct target tokens.
• 

  liveBookmanning.com
  Experimentation for EngineersA loss metric that measures the discrepancy between a probability distribution predicted by a model and the observed outcome distribution.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionCross-entropy loss is a prediction-error measure computed as the negative logarithm of the probability assigned to the correct outcome.

Compare how 19 books explain cross entropy loss →

Related concepts

• classifieraddresses · A classifier is a predictive computational model that assigns inputs to one or more discrete classes or categories.
• negative log-likelihoodequivalent to · Negative log-likelihood is the negative logarithm of the likelihood a probabilistic model assigns to observed data, commonly used as an objective or loss to minimize.
• focal lossincludes · Focal loss is a classification loss that downweights well-classified examples and emphasizes difficult or misclassified examples, especially under class imbalance.
• uncertaintymeasures · Uncertainty is incomplete knowledge or confidence about a value, state, interpretation, behavior, or outcome.
• likelihoodequivalent to · A likelihood is the probability of observed data under a specified probabilistic model, regarded as a function of candidate hypotheses or parameter values.

This explainer was generated by Manning's knowledge graph from the text of Graph Neural Networks in Action. The section links point to the parts of the book it draws on.