Log-softmax function

As explained in Graph Neural Networks in Action

A function that applies logarithms to softmax-normalized scores to produce log probabilities over classes.

How Graph Neural Networks in Action covers it

How deep it goes

Defines the activation and demonstrates its placement and training use, without deriving logarithmic or softmax internals.

Examples

Uses SimpleGNN on the books_gml dataset for three-label node classification, with randomized or N2V node features.

What it assumes

Assumes familiarity with GNN layers, node embeddings, class labels, and a supervised training loop.

What you can do after

Apply it via PyTorch in a GNN forward pass and train predictions over masked nodes.

How it connects

Connects GNN embeddings, graph convolution, node classification, training masks, and classification loss.

liveBookmanning.com

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

Related concepts

• softmaxalternative to · Softmax is a function that exponentiates a vector of scores and normalizes the results into nonnegative values that sum to one.
• graph neural networkconfigures · A graph neural network is a neural-network model that learns representations or predictions from graph-structured data by combining information from connected entities.
• cross entropy lossused by · Cross-entropy loss measures the expected negative log probability that a predicted distribution assigns to outcomes drawn from a target distribution.

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.