Zobrazeno 1 - 10
of 605
pro vyhledávání: '"Lu Weigang"'
Publikováno v:
Guan'gai paishui xuebao, Vol 40, Iss 11, Pp 73-78 (2021)
【Objective】 Hydraulic loss is a great concern in designing hydraulic apparatus and the objective of this paper is to investigate how to reduce it in the outlet conduit so as to improve the performance of shaft tubular pump. 【Method】 The analy
Externí odkaz:
https://doaj.org/article/d7c2b58628fc4d29a6c73392a2ae99e4
Publikováno v:
AAAI 2025
Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio $\lambda$ in the image domain. Recently, the concept of mixup has been adapted to the graph domain through node-centri
Externí odkaz:
http://arxiv.org/abs/2412.08144
Publikováno v:
Guan'gai paishui xuebao, Vol 40, Iss 4, Pp 52-59 (2021)
【Background】 Shaft tubular pump is a new pumping device with its generator installed in an open shaft, which is moisture-proof and has good ventilation. It has several advantages including easy operation and maintenance, low cost, and simple stru
Externí odkaz:
https://doaj.org/article/bf3efe0e6b5e49658d527cf0e1ac9cd7
Entity alignment (EA) is to identify equivalent entities across different knowledge graphs (KGs), which can help fuse these KGs into a more comprehensive one. Previous EA methods mainly focus on aligning a pair of KGs, and to the best of our knowledg
Externí odkaz:
http://arxiv.org/abs/2408.00662
Publikováno v:
KDD 2024
Graph Neural Networks (GNNs) have revolutionized graph-based machine learning, but their heavy computational demands pose challenges for latency-sensitive edge devices in practical industrial applications. In response, a new wave of methods, collecti
Externí odkaz:
http://arxiv.org/abs/2405.14307
Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. However, due to the uneven location distribution of labeled nodes in the graph, labeled nodes are only accessible to a small port
Externí odkaz:
http://arxiv.org/abs/2312.13032
Autor:
Lu, Weigang, Guan, Ziyu, Zhao, Wei, Yang, Yaming, Lv, Yuanhai, Xing, Lining, Yu, Baosheng, Tao, Dacheng
Pseudo Labeling is a technique used to improve the performance of semi-supervised Graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a longstand
Externí odkaz:
http://arxiv.org/abs/2302.09532
Recent self-supervised pre-training methods on Heterogeneous Information Networks (HINs) have shown promising competitiveness over traditional semi-supervised Heterogeneous Graph Neural Networks (HGNNs). Unfortunately, their performance heavily depen
Externí odkaz:
http://arxiv.org/abs/2210.10462
Publikováno v:
IEEE Signal Processing Letters 2022
In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the ground-truth dot maps which are marked around the center of human heads. D
Externí odkaz:
http://arxiv.org/abs/2206.08084
Publikováno v:
In Environmental Technology & Innovation November 2024 36