Search

Graph neural networks have been shown successful in recent years. While different GNN architectures and training systems have been developed, GNN training on large-scale real-world graphs still remains challenging. Existing distributed systems load the entire graph in memory for graph partitioning, requiring a huge memory space to process large graphs and thus hindering GNN training on such large graphs using commodity workstations. In this paper, we propose CATGNN, a cost-efficient and scalable distributed GNN training system which focuses on scaling GNN training to billion-scale or larger graphs under limited computational resources. Among other features, it takes a stream of edges as input, instead of loading the entire graph in memory, for partitioning. We also propose a novel streaming partitioning algorithm named SPRING for distributed GNN training. We verify the correctness and effectiveness of CATGNN with SPRING on 16 open datasets. In particular, we demonstrate that CATGNN can handle the largest publicly available dataset with limited memory, which would have been infeasible without increasing the memory space. SPRING also outperforms state-of-the-art partitioning algorithms significantly, with a 50% reduction in replication factor on average.

In this paper, we study the problem of minimizing the spread of a viral epidemic when immunization takes a non-negligible amount of time to take into effect. Specifically, our problem is to determine which set of nodes to be vaccinated when vaccines take a random amount of time in order to maximize the total reward, which is the expected number of saved nodes. We first provide a mathematical analysis for the reward function of vaccinating an arbitrary number of nodes when there is a single source of infection. While it is infeasible to obtain the optimal solution analytically due to the combinatorial nature of the problem, we establish that the problem is a monotone submodular maximization problem and develop a greedy algorithm that achieves a $(1\!-\!1/e)$-approximation. We further extend the scenario to the ones with multiple infection sources and discuss how the greedy algorithm can be applied systematically for the multiple-source scenarios. We finally present extensive simulation results to demonstrate the superiority of our greedy algorithm over other baseline vaccination strategies., Comment: IFIP Networking 2023

We study the problem of floor identification for radiofrequency (RF) signal samples obtained in a crowdsourced manner, where the signal samples are highly heterogeneous and most samples lack their floor labels. We propose GRAFICS, a graph embedding-based floor identification system. GRAFICS first builds a highly versatile bipartite graph model, having APs on one side and signal samples on the other. GRAFICS then learns the low-dimensional embeddings of signal samples via a novel graph embedding algorithm named E-LINE. GRAFICS finally clusters the node embeddings along with the embeddings of a few labeled samples through a proximity-based hierarchical clustering, which eases the floor identification of every new sample. We validate the effectiveness of GRAFICS based on two large-scale datasets that contain RF signal records from 204 buildings in Hangzhou, China, and five buildings in Hong Kong. Our experiment results show that GRAFICS achieves highly accurate prediction performance with only a few labeled samples (96% in both micro- and macro-F scores) and significantly outperforms several state-of-the-art algorithms (by about 45% improvement in micro-F score and 53% in macro-F score)., Comment: Accepted by IEEE ICDCS 2022