Zobrazeno 1 - 10
of 311
pro vyhledávání: '"YAN, Mingyu"'
Graph neural networks (GNNs) have emerged as go-to models for node classification in graph data due to their powerful abilities in fusing graph structures and attributes. However, such models strongly rely on adequate high-quality labeled data for tr
Externí odkaz:
http://arxiv.org/abs/2412.11983
Design space exploration (DSE) enables architects to systematically evaluate various design options, guiding decisions on the most suitable configurations to meet specific objectives such as optimizing performance, power, and area. However, the growi
Externí odkaz:
http://arxiv.org/abs/2410.18368
Heterogeneous Graph Neural Networks (HGNNs) have expanded graph representation learning to heterogeneous graph fields. Recent studies have demonstrated their superior performance across various applications, including medical analysis and recommendat
Externí odkaz:
http://arxiv.org/abs/2408.15089
Autor:
Wu, Meng, Qiu, Jingkai, Yan, Mingyu, Li, Wenming, Zhang, Yang, Zhang, Zhimin, Ye, Xiaochun, Fan, Dongrui
Heterogeneous graph neural networks (HGNNs) are essential for capturing the structure and semantic information in heterogeneous graphs. However, existing GPU-based solutions, such as PyTorch Geometric, suffer from low GPU utilization due to numerous
Externí odkaz:
http://arxiv.org/abs/2408.08490
Characterizing graph neural networks (GNNs) is essential for identifying performance bottlenecks and facilitating their deployment. Despite substantial work in this area, a comprehensive survey on GNN characterization is lacking. This work presents a
Externí odkaz:
http://arxiv.org/abs/2408.01902
Owing to their remarkable representation capabilities for heterogeneous graph data, Heterogeneous Graph Neural Networks (HGNNs) have been widely adopted in many critical real-world domains such as recommendation systems and medical analysis. Prior to
Externí odkaz:
http://arxiv.org/abs/2407.11790
Heterogeneous Graph Neural Networks (HGNNs) have recently demonstrated great power in handling heterogeneous graph data, rendering them widely applied in many critical real-world domains. Most HGNN models leverage attention mechanisms to significantl
Externí odkaz:
http://arxiv.org/abs/2406.00988
Graph Neural Networks (GNNs) have emerged as potent models for graph learning. Distributing the training process across multiple computing nodes is the most promising solution to address the challenges of ever-growing real-world graphs. However, curr
Externí odkaz:
http://arxiv.org/abs/2405.06247
Autor:
Xue, Runzhen, Yan, Mingyu, Han, Dengke, Teng, Yihan, Tang, Zhimin, Ye, Xiaochun, Fan, Dongrui
Heterogeneous Graph Neural Networks (HGNNs) have broadened the applicability of graph representation learning to heterogeneous graphs. However, the irregular memory access pattern of HGNNs leads to the buffer thrashing issue in HGNN accelerators. In
Externí odkaz:
http://arxiv.org/abs/2404.04792
Autor:
Liu, Xin, Zhang, Yuxiang, Wu, Meng, Yan, Mingyu, He, Kun, Yan, Wei, Pan, Shirui, Ye, Xiaochun, Fan, Dongrui
Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e., graph data augmentation and attack. Surprisingly, both veins of edge
Externí odkaz:
http://arxiv.org/abs/2403.07943