Hash: 2a4789e89fa38481cf06d8f82af0c552

Mastering Graph Machine Learning - Implement Cutting-Edge Models with PyTorch Geometric, DGL, and LLMs #1009946

di Imad Muratspahic

Muratspahic Imad

(Ancora nessuna recensione) Scrivi una recensione
11,49€

Leggi l'anteprima

Ebook accessibile. Per approfondire leggi qui
Build, train, and deploy graph neural networks with the two dominant frameworks — then take them to the frontier where graphs meet large language models.
Graph-structured data is everywhere: social networks, molecules, road systems, transaction ledgers, knowledge bases, and recommenders. Mastering Graph Machine Learning is the practitioner's guide to learning directly on that structure using PyTorch Geometric and DGL.
Across 30 hands-on chapters, you will move from foundations to production:
Core GNN architectures — GCN, GraphSAGE, GAT, GIN, and graph autoencoders, each with runnable code
Advanced methods — spectral filters, graph transformers, heterogeneous and temporal graphs, and techniques to fight over-smoothing and over-squashing
PyTorch Geometric deep dive — Data objects, custom datasets, NeighborLoader, mixed precision, and profiling at million-node scale
DGL deep dive — update_all, custom message functions, and edge-gated layers
LLMs meet graphs — text-attributed graphs, GraphRAG over knowledge graphs, and three concrete recipes for combining LLMs with GNNs
Real applications — molecular property prediction with RDKit, LightGCN recommenders, fraud detection on transaction graphs, traffic forecasting, and anomaly detection
Production — evaluation harnesses, inductive and temporal splits, FastAPI serving, embedding caches, and monitoring
Aggiunta al carrello in corso… L'articolo è stato aggiunto

Con l'acquisto di libri digitali il download è immediato: non ci sono costi di spedizione

Altre informazioni:

ISBN:
9784576519012
Formato:
ebook
Editore:
Muratspahic Imad
Anno di pubblicazione:
2026
Dimensione:
188 KB
Protezione:
watermark
Lingua:
Inglese
Autori:
Imad Muratspahic
accessible:
true