Graph patterns represented as vectors
Kaspar Riesen’s book examines graph-based pattern recognition through vector-space embeddings. It presents the dissimilarity-space representation as a way to map graphs into real vector spaces, connecting graph data with methods developed for feature vectors. The volume’s central concern is the trade-off between graphs’ representational capacity and a representation designed for computational efficiency and mathematical convenience. Its focus makes the book a specialized treatment of how graphs can be classified and clustered within established pattern-recognition frameworks.
Good fit for readers who enjoy
- Researchers and students in pattern recognition or artificial intelligence
- Readers working with graph data and classification or clustering methods
- Those interested in vector-space representations of structured data
Themes
Graph-based pattern recognitionDissimilarity-space representationVector-space embeddingClassification and clustering
Based on publisher information and book metadata.