A plot showing a model's performance measure, such as loss, across training epochs.
A learning curve plots a model’s performance measure across training epochs. Plot training and validation loss together to see whether learning improves on both datasets or begins to overfit. section 3.1.4
Read the curves as a practical training diagnostic:
Expect both losses to decline as the model learns. section 3.1.4
Treat a validation loss minimum followed by rising loss, while training loss continues falling, as classic overfitting. section 3.1.4
Save the model instance with the lowest validation loss rather than automatically using the final epoch. section 3.1.4
Record training and validation losses during each epoch, then visualize them to adjust training decisions. section 3.1.3
How Graph Neural Networks in Action covers it
How deep it goes
Interprets declining curves, divergence, and validation-loss minima, but defers overfitting remedies to later treatment.
Examples
Compares GCN and GraphSAGE curves, highlighting validation divergence near epoch 20 and selecting the lowest-validation-loss checkpoint.
What it assumes
Assumes epoch-based training with separate training and validation data, while defining loss as a measure of prediction quality.
What you can do after
Diagnose overfitting from plotted losses and retain the model checkpoint with the best validation performance.
How it connects
Connects training loss, validation loss, overfitting, model training, generalization, F1 score, and log loss.
training datasetuses · A collection of examples or observations supplied to a learning procedure to fit or adapt a model or learn its patterns or parameters.
evaluation datasetuses · An evaluation dataset is a collection of examples or test cases, often with expected or judged outcomes, designated to assess a model or system against defined criteria.
objective functionmeasures · An objective function assigns values to candidate solutions, predictions, or parameter settings according to a criterion to be minimized or maximized.
overfittingmeasures · Overfitting is a modeling condition in which a model fits patterns or idiosyncrasies in its training data too closely and consequently generalizes poorly to new data.
underfittingmeasures · A modeling failure in which insufficient capacity or training prevents a model from capturing relevant patterns in the data, resulting in poor performance even on training data.
performancemeasures · Performance is the measurable effectiveness or operational behavior of a system under specified conditions, assessed through relevant qualities such as task results, speed, responsiveness, throughput, or resource use.
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.
