Community detection and its variations is one of the typically employed approaches for analyzing graph data originating from various diverse fields. In this paper, we focus on a particular approach for community detection capitalizing on hyperbolic network embedding, which is aimed at analyzing large data graphs. In order to enable its scaling to arbitrary sized data sets and respective data graphs, we extend it by incorporating a graph database approach. This allows for handling a larger number of nodes and edges in the data graph. Also, we turn our focus on the discovery and visualization of communities in Resource Description Framework (RDF) data, namely over linked datasets from diverse areas, explaining how our approach can accommodate relevant analysis. We demonstrate the applicability of the new approach over both real-world and artificially generated datasets showing its feasibility in producing correct results, while being able to scale seamlessly in large datasets. The approach can be used for multi-lateral analysis of feature-rich graph data, originating from diverse sources, enabling the discovery of hidden correlations through the hyperbolic network embedding.

Modern large-scale computing deployments consist of complex applications running over machine clusters. An important issue in these is the offering of elasticity, i.e., the dynamic allocation of resources to applications to meet fluctuating workload demands. Threshold based approaches are typically employed, yet they are difficult to configure and optimize. Approaches based on reinforcement learning have been proposed, but they require a large number of states in order to model complex application behavior. Methods that adaptively partition the state space have been proposed, but their partitioning criteria and strategies are sub-optimal. In this work we present MDP_DT, a novel full-model based reinforcement learning algorithm for elastic resource management that employs adaptive state space partitioning. We propose two novel statistical criteria and three strategies and we experimentally prove that they correctly decide both where and when to partition, outperforming existing approaches. We experimentally evaluate MDP_DT in a real large scale cluster over variable not-encountered workloads and we show that it takes more informed decisions compared to static and model-free approaches, while requiring a minimal amount of training data.