How deeply does Graph Neural Networks in Action cover similarity matrix?

Explains matrix construction and nearest-item ranking, but defers the underlying cosine-similarity mathematics.

Similarity matrix

As explained in Graph Neural Networks in Action

A similarity matrix is a matrix whose entries quantify the similarity between pairs of items or representations.

A similarity matrix is a tabular structure whose entries quantify similarity between every pair of items. For node embeddings, cosine similarity compares all nodes and supports nearest-neighbor product recommendations. section 3.1.5

A practical recommendation workflow proceeds as follows:

Run the trained graph neural network in evaluation mode to produce node embeddings. section 3.1.5
Compute pairwise cosine similarities across the embeddings. section 3.1.5
Select a product row, sort similarities in descending order, and map the resulting node indices to product IDs. section 3.1.5

Product bundle generation

For a selected Marceline vinyl figure, the matrix ranks six nearby product embeddings to create a loosely related Toy & Games bundle. section 3.1.5

gcn_similarity_matrix = cosine_similarity(gcn_embeddings.cpu().numpy())

This listing constructs the matrix with scikit-learn from CPU-converted node embeddings. section 3.1.5

How Graph Neural Networks in Action covers it

Cover of Graph Neural Networks in Action

liveBook manning.com

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

Also explained in

liveBook manning.com

Data Without LabelsAn affinity matrix is a matrix whose entries quantify pairwise similarities or affinities between data points.
liveBook manning.com

Natural Language Processing in Action, Second EditionA similarity matrix is a square matrix whose entries quantify pairwise similarity between objects.

Compare how 3 books explain similarity matrix →

Related concepts

spectral clusteringused by · Spectral clustering is a clustering method that partitions data using eigenvectors of a graph-based affinity representation rather than only geometric location.
cosine similarityuses · Cosine similarity measures the directional alignment of two nonzero vectors as the cosine of the angle between them, equivalently their dot product divided by the product of their magnitudes.
user-item interaction matrixused by · A user-item interaction matrix is a matrix whose rows represent users, columns represent items, and entries encode their interactions, preferences, or ratings.
adjacency matrixalternative to · An adjacency matrix is a square matrix whose rows and columns represent graph vertices and whose entries indicate edges or encode edge weights between vertex pairs.
embeddingproduced by · A numerical vector representation of an item or input that encodes features or relationships useful for computational tasks.

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.