Zobrazeno 1 - 10
of 733
pro vyhledávání: '"Chen, Kaixuan"'
Mini-batch Graph Transformer (MGT), as an emerging graph learning model, has demonstrated significant advantages in semi-supervised node prediction tasks with improved computational efficiency and enhanced model robustness. However, existing methods
Externí odkaz:
http://arxiv.org/abs/2407.09904
Graph Neural Networks (GNNs) have emerged as a prominent framework for graph mining, leading to significant advances across various domains. Stemmed from the node-wise representations of GNNs, existing explanation studies have embraced the subgraph-s
Externí odkaz:
http://arxiv.org/abs/2407.01979
Autor:
Liu, Shunyu, Luo, Wei, Zhou, Yanzhen, Chen, Kaixuan, Zhang, Quan, Xu, Huating, Guo, Qinglai, Song, Mingli
Transmission interface power flow adjustment is a critical measure to ensure the security and economy operation of power systems. However, conventional model-based adjustment schemes are limited by the increasing variations and uncertainties occur in
Externí odkaz:
http://arxiv.org/abs/2405.15831
Offline reinforcement learning endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the out-of-distribution pr
Externí odkaz:
http://arxiv.org/abs/2403.07262
Autor:
Deng, Zhaoang, Li, Zhenhua, Liu, Jie, Bian, Chuyao, Li, Jiaqing, Gan, Ranfeng, Chen, Zihao, Chen, Kaixuan, Guo, Changjian, Liu, Liu, Yu, Siyuan
The advancement of artificial intelligence demands flexible multimodal data processing with high throughput and energy efficiency. Photonic integrated circuits (PIC) has demonstrated promising potentials in terms of low latency and low power consumpt
Externí odkaz:
http://arxiv.org/abs/2403.04216
Autor:
Chen, Kaixuan, Luo, Wei, Liu, Shunyu, Wei, Yaoquan, Zhou, Yihe, Qing, Yunpeng, Zhang, Quan, Song, Jie, Song, Mingli
In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections. Specifically, o
Externí odkaz:
http://arxiv.org/abs/2401.02771
In traditional deep learning algorithms, one of the key assumptions is that the data distribution remains constant during both training and deployment. However, this assumption becomes problematic when faced with Out-of-Distribution periods, such as
Externí odkaz:
http://arxiv.org/abs/2309.04296
Autor:
Wang, Yuwen, Liu, Shunyu, Chen, Kaixuan, Zhu, Tongtian, Qiao, Ji, Shi, Mengjie, Wan, Yuanyu, Song, Mingli
Graph Lottery Ticket (GLT), a combination of core subgraph and sparse subnetwork, has been proposed to mitigate the computational cost of deep Graph Neural Networks (GNNs) on large input graphs while preserving original performance. However, the winn
Externí odkaz:
http://arxiv.org/abs/2308.02916
Publikováno v:
Nanophotonics, Vol 13, Iss 21, Pp 3985-3993 (2024)
Integrated miniature spectrometers have impacts in industry, agriculture, and aerospace applications due to their unique advantages in portability and energy consumption. Although existing on-chip spectrometers have achieved breakthroughs in key perf
Externí odkaz:
https://doaj.org/article/19036d278cd04aad8fe9329778d48e04
We present an investigation into the transferability of pseudopotentials (PPs) with a nonlinear core correction (NLCC) using the Goedecker, Teter, and Hutter (GTH) protocol across a range of pure GGA, meta-GGA and hybrid functionals, and their impact
Externí odkaz:
http://arxiv.org/abs/2307.09717