{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11966832","patent":{"patent_number":"US-11966832","title":"Structured graph convolutional networks with stochastic masks for network embeddings","assignee":null,"inventors":[],"filing_date":"2021-07-02T00:00:00.000Z","publication_date":"2024-04-23T00:00:00.000Z","cpc_codes":["G06N","G06N","G06N","G06N","G06N","G06Q","G06Q","G06Q"],"num_claims":20,"abstract":"A method includes receiving a first data set comprising embeddings of first and second types, generating a fixed adjacency matrix from the first dataset, and applying a first stochastic binary mask to the fixed adjacency matrix to obtain a first subgraph of the fixed adjacency matrix. The method also includes processing the first subgraph through a first layer of a graph convolutional network (GCN) to obtain a first embedding matrix, and applying a second stochastic binary mask to the fixed adjacency matrix to obtain a second subgraph of the fixed adjacency matrix. The method includes processing the first embedding matrix and the second subgraph through a second layer of the GCN to obtain a second embedding matrix, and then determining a plurality of gradients of a loss function, and modifying the first stochastic binary mask and the second stochastic binary mask using at least one of the plurality of gradients."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Structured graph convolutional networks with stochastic masks for network embeddings","description":"A method includes receiving a first data set comprising embeddings of first and second types, generating a fixed adjacency matrix from the first dataset, and applying a first stochastic binary mask to","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11966832","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11966832","citation_suggestion":"Patentable. \"Structured graph convolutional networks with stochastic masks for network embeddings\" (US-11966832). https://patentable.app/patents/US-11966832","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11966832","json":"https://patentable.app/api/llm-context/US-11966832","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T08:34:11.460Z"}