HPGM: High Performance Graph Mining
More and larger network data sets emerge every year, causing a growing interest in large-scale graph mining. However, exploring and exploiting these large graphs represents a novel challenge, both in terms of knowledge discovery and parallel computation. In order to understand what processes are currently feasible, HPC and AI researchers must collaborate in the design of mining algorithms, processing models and optimization techniques. To help in that regard, the HPGM workshop intends to bring together researchers tackling the same problems from different perspectives; life and earth science researchers working on network related problems, AI researchers designing graph mining tools, and HPC researchers developing efficient graph processing methodologies.
- Toyotaro Suzumura, IBM T.J.Watson Research Center
- Ulises Cortés, UPC - Barcelona TECH
- Dario Garcia-Gasulla, Barcelona Supercomputing Center, BSC
Open AccessThis paper presents a distributed, streaming graph parti- tioner, Graph Streaming Partitioner (GraSP), which makes partition decisions as each vertex is read from memory, sim- ulating an online algorithm that must process ...
Open AccessConstruction of a nearest neighbor graph is often a neces- sary step in many machine learning applications. However, constructing such a graph is computationally expensive, es- pecially when the data is high dimensional. ...
Open AccessIn graph theory the diameter is an important topological metric for understanding size and density of a graph. Unfortunately, the graph diameter is computationally di cult to measure for even moderately-sized graphs, ...