Zobrazeno 1 - 10
of 1 075
pro vyhledávání: '"Zhou, Ao"'
Class imbalance significantly impacts the performance of multi-label classifiers. Oversampling is one of the most popular approaches, as it augments instances associated with less frequent labels to balance the class distribution. Existing oversampli
Externí odkaz:
http://arxiv.org/abs/2408.13078
Autor:
Zhou, Ao, Yang, Jianlei, Qi, Yingjie, Qiao, Tong, Shi, Yumeng, Duan, Cenlin, Zhao, Weisheng, Hu, Chunming
Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based learning tasks such as point cloud processing due to their state-of-the-art (SOTA) performance. Nevertheless, the research community has primarily focused on improving mod
Externí odkaz:
http://arxiv.org/abs/2408.12840
As Large Language Models (LLMs) push the boundaries of AI capabilities, their demand for data is growing. Much of this data is private and distributed across edge devices, making Federated Learning (FL) a de-facto alternative for fine-tuning (i.e., F
Externí odkaz:
http://arxiv.org/abs/2408.11304
The discovery of drug-target interactions (DTIs) plays a crucial role in pharmaceutical development. The deep learning model achieves more accurate results in DTI prediction due to its ability to extract robust and expressive features from drug and t
Externí odkaz:
http://arxiv.org/abs/2404.10561
Autor:
Qiao, Tong, Yang, Jianlei, Qi, Yingjie, Zhou, Ao, Bai, Chen, Yu, Bei, Zhao, Weisheng, Hu, Chunming
Graph Neural Networks (GNNs) succeed significantly in many applications recently. However, balancing GNNs training runtime cost, memory consumption, and attainable accuracy for various applications is non-trivial. Previous training methodologies suff
Externí odkaz:
http://arxiv.org/abs/2404.09544
The key to device-edge co-inference paradigm is to partition models into computation-friendly and computation-intensive parts across the device and the edge, respectively. However, for Graph Neural Networks (GNNs), we find that simply partitioning wi
Externí odkaz:
http://arxiv.org/abs/2404.05605
Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample is randomly selected with equa
Externí odkaz:
http://arxiv.org/abs/2403.18192
The scalar mesons are established for a long time, but their nature is still an open question. In this paper, we investigate the potential of categorizing their $SU(3)_f$ representations via $J/\psi\to SV$ and $\gamma S$, offering a criterion that ma
Externí odkaz:
http://arxiv.org/abs/2403.07701
Communication overhead is a significant bottleneck in federated learning (FL), which has been exaggerated with the increasing size of AI models. In this paper, we propose FedRDMA, a communication-efficient cross-silo FL system that integrates RDMA in
Externí odkaz:
http://arxiv.org/abs/2403.00881
In the wake of the rapid deployment of large-scale low-Earth orbit satellite constellations, exploiting the full computing potential of Commercial Off-The-Shelf (COTS) devices in these environments has become a pressing issue. However, understanding
Externí odkaz:
http://arxiv.org/abs/2401.03435