arXiv subjects

Minh Phu Vuong

Publications and source records attributed to Minh Phu Vuong.

3 recordsLinked to original sources

arXiv2025

SDT-GNN: Streaming-based Distributed Training Framework for Graph Neural Networks

Recently, distributed GNN training frameworks, such as DistDGL and PyG, have been developed to enable training GNN models on large graphs by leveraging multiple GPUs in a distributed manner. Despite these advances, their memory requirements are still excessively high, thereby hindering GNN training on large graphs using commodity workstations. In this paper, we propose SDT-GNN, a streaming-based distributed GNN training framework. Unlike the existing frameworks that load the entire graph in memory, it takes a stream of edges as input for graph partitioning to reduce the memory requirement for partitioning. It also enables distributed GNN training even when the aggregated memory size of GPUs is smaller than the size of the graph and feature data. Furthermore, to improve the quality of partitioning, we propose SPRING, a novel streaming partitioning algorithm for distributed GNN training. We demonstrate the effectiveness and efficiency of SDT-GNN on seven large public datasets. SDT-GNN has up to 95% less memory footprint than DistDGL and PyG without sacrificing the prediction accuracy. SPRING also outperforms state-of-the-art streaming partitioning algorithms significantly.

cs.LG↗

arXiv2025

FairAD: Computationally Efficient Fair Graph Clustering via Algebraic Distance

Due to the growing concern about unsavory behaviors of machine learning models toward certain demographic groups, the notion of 'fairness' has recently drawn much attention from the community, thereby motivating the study of fairness in graph clustering. Fair graph clustering aims to partition the set of nodes in a graph into $k$ disjoint clusters such that the proportion of each protected group within each cluster is consistent with the proportion of that group in the entire dataset. It is, however, computationally challenging to incorporate fairness constraints into existing graph clustering algorithms, particularly for large graphs. To address this problem, we propose FairAD, a computationally efficient fair graph clustering method. It first constructs a new affinity matrix based on the notion of algebraic distance such that fairness constraints are imposed. A graph coarsening process is then performed on this affinity matrix to find representative nodes that correspond to $k$ clusters. Finally, a constrained minimization problem is solved to obtain the solution of fair clustering. Experiment results on the modified stochastic block model and six public datasets show that FairAD can achieve fair clustering while being up to 40 times faster compared to state-of-the-art fair graph clustering algorithms.

cs.LG↗

arXiv2025

Effective Delayed Patching for Transient Malware Control on Networks

Patching nodes is an effective network defense strategy for malware control at early stages, and its performance is primarily dependent on how accurately the infection propagation is characterized. In this paper, we aim to design a novel patching policy based on the susceptible-infected epidemic network model by incorporating the influence of patching delay--the type of delay that has been largely overlooked in designing patching policies in the literature, while being prevalent in practice. We first identify 'critical edges' that form a boundary to separate the most likely infected nodes from the nodes which would still remain healthy after the patching delay. We next leverage the critical edges to determine which nodes to be patched in light of limited patching resources at early stages. To this end, we formulate a constrained graph partitioning problem and use its solution to identify a set of nodes to patch or vaccinate under the limited resources, to effectively prevent malware propagation from getting through the healthy region. We numerically validate that our patching policy significantly outperforms other baseline policies in protecting the healthy nodes under limited patching resources and in the presence of patching delay.

cs.NI↗