May 2024
·
4 Reads
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
May 2024
·
4 Reads
September 2023
·
8 Reads
·
2 Citations
July 2023
·
20 Reads
·
3 Citations
IEEE Transactions on Image Processing
Graph embedding aims at learning vertex representations in a low-dimensional space by distilling information from a complex-structured graph. Recent efforts in graph embedding have been devoted to generalizing the representations from the trained graph in a source domain to the new graph in a different target domain based on information transfer. However, when the graphs are contaminated by unpredictable and complex noise in practice, this transfer problem is quite challenging because of the need to extract helpful knowledge from the source graph and to reliably transfer knowledge to the target graph. This paper puts forward a two-step correntropy-induced Wasserstein GCN (graph convolutional network, or CW-GCN for short) architecture to facilitate the robustness in cross-graph embedding. In the first step, CW-GCN originally investigates correntropy-induced loss in GCN, which places bounded and smooth losses on the noisy nodes with incorrect edges or attributes. Consequently, helpful information are extracted only from clean nodes in the source graph. In the second step, a novel Wasserstein distance is introduced to measure the difference in marginal distributions between graphs, avoiding the negative influence of noise. Afterwards, CW-GCN maps the target graph to the same embedding space as the source graph by minimizing the Wasserstein distance, and thus the knowledge preserved in the first step is expected to be reliably transferred to assist the target graph analysis tasks. Extensive experiments demonstrate the significant superiority of CW-GCN over state-of-the-art methods in different noisy environments.
June 2023
·
3 Reads
Proceedings of the AAAI Conference on Artificial Intelligence
Driving under the influence (DUI) is one of the main causes of traffic accidents, often leading to severe life and property losses. Setting up sobriety checkpoints on certain roads is the most commonly used practice to identify DUI-drivers in many countries worldwide. However, setting up checkpoints according to the police's experiences may not be effective for ignoring the strategic interactions between the police and DUI-drivers, particularly when inspecting resources are limited. To remedy this situation, we adapt the classic Stackelberg security game (SSG) to a new SSG-DUI game to describe the strategic interactions in catching DUI-drivers. SSG-DUI features drivers' bounded rationality and social knowledge sharing among them, thus realizing improved real-world fidelity. With SSG-DUI, we propose OPRADI, a systematic approach for advising better strategies in setting up checkpoints. We perform extensive experiments to evaluate it in both simulated environments and real-world contexts, in collaborating with a Chinese city's police bureau. The results reveal its effectiveness in improving police's real-world operations, thus having significant practical potentials.
May 2023
·
13 Reads
... Increasing the time span of the input data can improve prediction performance (Jia et al. 2022). Additional approaches such as personalized dynamic graph networks and hierarchical graph recurrent networks have also been developed to tackle the spatiotemporal complexities of SST prediction (Zhang et al. 2023;Yang et al. 2023). These methods exemplify the ongoing advancements in the utilization of machine learning, deep learning, and statistical models to enhance the accuracy of SST prediction. ...
September 2023
... First, multiple tasks could be trained together to produce one model to deal with all training tasks without finetuning on each specific task Yan et al. 2023;Zou et al. 2023a). Second, generalist training strategies have been proposed to enable models to handle new tasks in a zero-shot manner (Abdollahzadeh et al. 2023;Wang et al. 2023a). For example, SegGPT utilized the generalist Painter framework (Wang et al. 2023b) to realize in-context learning for image segmentation (Wang et al. 2023c). ...
July 2023
IEEE Transactions on Image Processing