@prefix rdf: . @prefix sl: . @prefix skos: . @prefix rdfs: . @prefix tag: . @prefix foaf: . @prefix dc: . tag:graph_embeddings a sl:Tag ; skos:prefLabel "Graph Embeddings" . tag:arxiv_doc a sl:Tag ; skos:prefLabel "Arxiv Doc" . tag:jure_leskovec a sl:Tag ; rdfs:isDefinedBy ; sl:comment "Co-Author of [Node2Vec](/tag/node2vec) paper\r\n" ; skos:broader tag:nlp_girls_and_guys , tag:ai_girls_and_guys ; skos:prefLabel "Jure Leskovec" ; skos:related tag:stanford , tag:node2vec ; foaf:page tag:jure_leskovec.html . tag:lm_link_prediction a sl:Tag ; skos:prefLabel "LM + Link Prediction" . tag:nlp_stanford a sl:Tag ; skos:prefLabel "NLP@Stanford" . tag:chris_manning a sl:Tag ; skos:prefLabel "Chris Manning" . dc:title "[1607.00653] node2vec: Scalable Feature Learning for Networks" ; sl:comment "> algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node's network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations." ; sl:creationDate "2020-08-08" ; sl:tag tag:node2vec , tag:jure_leskovec , tag:arxiv_doc . dc:title "Stanford CS224W GraphML Tutorials – Medium" ; sl:creationDate "2023-05-18" ; sl:tag tag:jure_leskovec , tag:ai_stanford . tag:kg_and_nlp a sl:Tag ; skos:prefLabel "Knowledge Graphs and NLP" . tag:neo4j a sl:Tag ; skos:prefLabel "Neo4j" . tag:nlp_girls_and_guys a sl:Tag ; skos:prefLabel "NLP girls and guys" . tag:stanford a sl:Tag ; skos:prefLabel "Stanford" . dc:title "[2210.09338] Deep Bidirectional Language-Knowledge Graph Pretraining" ; sl:comment "> DRAGON (Deep Bidirectional\r\nLanguage-Knowledge Graph Pretraining), a self-supervised method to pretrain\r\na deeply joint language-knowledge foundation model from text and KG at scale.\r\n> \r\n> Specifically, our model takes pairs of text segments and relevant KG subgraphs\r\nas input and bidirectionally fuses information from both modalities." ; sl:creationDate "2022-10-23" ; sl:tag tag:nlp_stanford , tag:lm_link_prediction , tag:kg_and_nlp , tag:jure_leskovec , tag:chris_manning , tag:arxiv_doc . tag:node2vec a sl:Tag ; skos:prefLabel "Node2Vec" . tag:thewebconf_2018 a sl:Tag ; skos:prefLabel "TheWebConf 2018" . dc:title "TUTORIAL: Representation Learning on Networks - TheWebConf 2018" ; sl:comment "Network representation learning (NRL): Approaches that automatically learn to encode network structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction\r\n\r\n**Goal of representation learning for networks: efficient task-independant feature learning for ML in networks.** But it's hard. DL toolbox are designed for single sequences or grids (for instance CNN for images, RNN or word2vec are fixed size), but networks are far more complex!\r\n\r\nfrom the abstract: \r\n\r\n> In this tutorial, we will cover key advancements in NRL over the last decade, with an emphasis on fundamental advancements made in the last two years. We will discuss classic matrix factorization-based methods (e.g., Laplacian eigenmaps), random-walk based algorithms (e.g., DeepWalk and node2vec), as well as very recent advancements in graph convolutional networks (GCNs). We will cover methods to embed individual nodes (see [node embeddings](/tag/node_embeddings)) as well as approaches to embed entire (sub)graphs, and in doing so, we will present a unified framework for NRL.\r\n\r\n" ; sl:creationDate "2018-05-05" ; sl:tag tag:thewebconf_2018 , tag:jure_leskovec , tag:graph_embeddings . tag:ai_girls_and_guys a sl:Tag ; skos:prefLabel "AI girls and guys" . tag:ai_stanford a sl:Tag ; skos:prefLabel "AI@Stanford" . dc:title "Bringing traditional ML to your Neo4j Graph with node2vec | Dave Voutila" ; sl:comment "New in Neo4j Graph Data Science library (v1.3): [Graph Embeddings](tag:graph_embeddings)." ; sl:creationDate "2020-08-06" ; sl:tag tag:node2vec , tag:neo4j , tag:jure_leskovec , tag:graph_embeddings .