Advanced search

Found 3 essays matching the above criteria.

  1. 1. Dynamic Graph Embedding on Event Streams with Apache Flink

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Massimo Perini; [2019]
    Keywords : Dynamic Graph; Representation Learning; Stream; Real-Time Data Processing; Scalable Graph Processing; Graph Neural Network; Experience Replay; Grafi dinamici; Representation Learning; Flussi di dati; Elaborazione in tempo reale; Elaborazione di grafi scalabile; Reti neurali per grafi; Experience Replay; Dynamisk graf; Representationsinlärning; ström; databehandling i realtid; skalbar grafbehandling; grafiskt neuralt nätverk; erfarenhetsåterspelning;

    Abstract : Graphs are often considered an excellent way of modeling complex real-world problems since they allow to capture relationships between items. Because of their ubiquity, graph embedding techniques have occupied research groups, seeking how vertices can be encoded into a low-dimensional latent space, useful to then perform machine learning. READ MORE

  3. 2. An Evaluation of TensorFlow as a Programming Framework for HPC Applications

    University essay from KTH/Beräkningsvetenskap och beräkningsteknik (CST); KTH/Parallelldatorcentrum, PDC

    Author : Wei Der Chien; [2018]
    Keywords : HPC; GPU; TensorFlow;

    Abstract : In recent years, deep-learning, a branch of machine learning gained increasing popularity due to their extensive applications and performance. At the core of these application is dense matrix-matrix multiplication. Graphics Processing Units (GPUs) are commonly used in the training process due to their massively parallel computation capabilities. READ MORE

  4. 3. Scalable Streaming Graph Partitioning

    University essay from KTH/Skolan för informations- och kommunikationsteknik (ICT)

    Author : Seyed Mohammadreza Seyed Khamoushi; [2017]
    Keywords : streaming graph; vertex-cut partitioning; graph partitioning; distributed hash table;

    Abstract : Large-scale graph-structured datasets are growing at an increasing rate. Social network graphs are an example of these datasets. Processing large-scale graphstructured datasets are central to many applications ranging from telecommunication to biology and has led to the development of many parallel graph algorithms. READ MORE