Zobrazeno 1 - 10
of 795
pro vyhledávání: '"Zhou, Dawei"'
Many real-world graphs frequently present challenges for graph learning due to the presence of both heterophily and heterogeneity. However, existing benchmarks for graph learning often focus on heterogeneous graphs with homophily or homogeneous graph
Externí odkaz:
http://arxiv.org/abs/2407.10916
Autor:
Hoggenmuller, Marius, Tomitsch, Martin, Parker, Callum, Nguyen, Trung Thanh, Zhou, Dawei, Worrall, Stewart, Nebot, Eduardo
The advent of cyber-physical systems, such as robots and autonomous vehicles (AVs), brings new opportunities and challenges for the domain of interaction design. Though there is consensus about the value of human-centred development, there is a lack
Externí odkaz:
http://arxiv.org/abs/2406.08733
Although most graph neural networks (GNNs) can operate on graphs of any size, their classification performance often declines on graphs larger than those encountered during training. Existing methods insufficiently address the removal of size informa
Externí odkaz:
http://arxiv.org/abs/2406.04601
Adversarial training (AT) trains models using adversarial examples (AEs), which are natural images modified with specific perturbations to mislead the model. These perturbations are constrained by a predefined perturbation budget $\epsilon$ and are e
Externí odkaz:
http://arxiv.org/abs/2406.00685
Spatiotemporal time series is the foundation of understanding human activities and their impacts, which is usually collected via monitoring sensors placed at different locations. The collected data usually contains missing values due to various failu
Externí odkaz:
http://arxiv.org/abs/2403.11960
Inspired by recent experimental synthesis of the two-dimensional Janus material MoSH, we have performed extensive first-principles calculations to investigate the characteristics of all possible Janus two-dimensional transition metal hydrosulfides (J
Externí odkaz:
http://arxiv.org/abs/2401.15577
Deep neural networks are vulnerable to adversarial samples. Adversarial fine-tuning methods aim to enhance adversarial robustness through fine-tuning the naturally pre-trained model in an adversarial training manner. However, we identify that some la
Externí odkaz:
http://arxiv.org/abs/2401.14707
Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust features, r
Externí odkaz:
http://arxiv.org/abs/2310.03358
Autor:
Liu, Liangchen, Wang, Nannan, Zhou, Dawei, Gao, Xinbo, Liu, Decheng, Yang, Xi, Liu, Tongliang
This paper targets a novel trade-off problem in generalizable prompt learning for vision-language models (VLM), i.e., improving the performance on unseen classes while maintaining the performance on seen classes. Comparing with existing generalizable
Externí odkaz:
http://arxiv.org/abs/2309.07866
Rare categories abound in a number of real-world networks and play a pivotal role in a variety of high-stakes applications, including financial fraud detection, network intrusion detection, and rare disease diagnosis. Rare category analysis (RCA) ref
Externí odkaz:
http://arxiv.org/abs/2307.09858