PPT-Inductive Representation Learning on Large Graphs

William L Hamilton Rex Ying Jure Leskovec Keshav Balasubramanian Outline Main goal generating node embeddings Survey of past methods GCNs GraphSAGE Algorithm Optimization and learning Aggregators. Associate Dean for Academic and Student Affairs Forum. Christine Kelly. November 28, 2012. History. BS . ChE. , University of Arizona. Process Engineer, Tate and Lyle. PhD . ChE. , University of Tennessee. . Learning. for. . Word, Sense, Phrase, Document and Knowledge. Natural . Language Processing . Lab. , Tsinghua . University. Yu Zhao. , Xinxiong Chen, Yankai Lin, Yang Liu. Zhiyuan Liu. , Maosong Sun. Chapter Three. Born to think – people simply cannot keep themselves from comparing and contrasting things, actions, feelings, and … you name it!. Inductive thinking is probably the basis for most forms of higher-order mental processes.. Isabelle Stanton, UC Berkeley. Gabriel . Kliot. , Microsoft Research XCG. Modern graph datasets are huge. The web graph had over a trillion links in 2011. Now?. . facebook. has “more than 901 million users with average degree 130”. based. . Knowledge. . Representation. . Formalism. . designed. for the . Meaning. -. Text. . Theory. & . Application to . Lexicographic. . Definitions. in the RELIEF . project. Maxime Lefrançois, Fabien . http://hunch.net/~mltf. John Langford. Microsoft Research. Machine Learning in the present. Get a large amount of labeled data . . where . . Learn a predictor . Use the predictor.. The Foundation: Samples + Representation + Optimization. Continued.. . There are four basic forms of graph:. The statistical line graph. The bar graph. The pie graph. Introduction. When verbal (spoken) . problems involving a certain situation is presented visually before . Psychology 209. February . 1, 2013. The Concept of a Distributed Representation. Instead of assuming that an object (concept, etc) is represented in the mind by a single unit, we consider the possibility that it could be represented by patterns of activation over populations of units.. Richard C. Wilson. Dept. of Computer Science. University of York. Graphs and Networks. Graphs . and. networks . are all around us. ‘Simple’ networks. 10s to 100s of vertices. Graphs and networks. Richard C. Wilson. Dept. of Computer Science. University of York. Graphs and Networks. Graphs . and. networks . are all around us. ‘Simple’ networks. 10s to 100s of vertices. Graphs and networks. IST597: Foundations of Deep Learning. The Pennsylvania State . University. Thanks to . Sargur. N. Srihari, . Rukshan. . Batuwita. , . Yoshua. . Bengio. Manual & Exhaustive Search. Manual Search. Topic 3. 4/15/2014. Huy V. Nguyen. 1. outline. Deep learning overview. Deep v. shallow architectures. Representation learning. Breakthroughs. Learning principle: greedy layer-wise training. Tera. . scale: data, model, . April 20, 2018. 4/20/18. CompSci 201, Spring 2018, Graphs. 1. Y . is for . …. Y2K. Bits are cheap?. Yahoo!. The importance of browsing. YAML, YACC. Yet another. Yao’s minimax principle. Randomized algorithms & their limits. Lingxiao Ma. . †. , Zhi Yang. . †. , Youshan Miao. ‡. , Jilong Xue. ‡. , Ming Wu. ‡. , Lidong Zhou. ‡. , . Yafei. Dai. . †. †. . Peking University. ‡ . Microsoft Research. USENIX ATC ’19, Renton, WA, USA.