Author name cluster

Yukun Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2026 Journal Article

Graph convolutional network reconstruction with high-order node information for community detection

Yukun Wang
XianYong Li
YaJun Du
Dong Huang
XiaoLiang Chen
Zhicheng Dong
Yujie Zhang

Community detection is typically used to understand the community structures within networks. Most community detection methods are limited to capturing only the nodes’ first-order and second-order neighbor information. To utilize nodes’ high-order neighbor information, we propose a graph convolutional network reconstruction with high-order node information for community detection (GCNRH). Since the existing shallow graph convolutional network is difficult to capture high-order information, the GCNRH model introduces a graph convolutional network with a biaffine attention mechanism to establish a fast association of remote nodes. It utilizes the biaffine attention mechanism to capture the higher-order node information and learns the potential representation of nodes by reconstructing the modularity matrix. It also adopts a self-supervised training method to optimize the learning process. Extensive experiments on 12 real-world datasets demonstrate the superior performance of GCNRH in community detection. In particular, the modularity and normalized mutual information values of the GCNRH model improve by 0. 48%–30. 92% and 3. 8%–19. 3% on the Facebook dataset, respectively. Finally, visualizations of community divisions on different-scale networks show the effectiveness of the GCNRH model.

Details DOI

EAAI Journal 2025 Journal Article

A modeled study of driver visual attention driven by driving tasks

Chuan Xu
Bo Jiang
Yukun Wang
Yan Su

Visual attention is an indispensable component of driving, enabling drivers to swiftly identify critical objects within complex and dynamic traffic environments. Despite its significance, existing visual attention models predominantly focus on static or idealized driving scenarios, limiting their ability to capture attention distribution patterns in real-world, dynamic environments. Furthermore, most of these models rely heavily on data-driven approaches, extracting features exclusively from visual image data, while neglecting the profound influence of “the driver, the vehicle, and the road environment”. Consequently, these models frequently fail to effectively address the intricacies of practical driving scenarios. To bridge these gaps, this study introduces a driver visual attention prediction model that comprehensively incorporates the driving task, driver experience, and the impact of dynamic visual scenes. The proposed model leverages the advanced learning capabilities of Convolutional Neural Networks (CNN) and Vision Transformer (ViT), coupled with sequence modeling mechanisms, to effectively capture the nuanced attention allocation patterns of drivers in complex driving contexts. The model is meticulously designed to adapt to dynamically evolving driving task requirements. Experimental results demonstrate that the proposed model outperforms state-of-the-art (SOTA) visual attention prediction models across multiple benchmark evaluation metrics on the DR(eye)VE dataset, particularly excelling in dynamic driving conditions. Moreover, generalization experiments were conducted on the BDD-A and TDV datasets validate the model’s robustness and applicability across varied driving tasks and dynamic conditions.

Details DOI

AAAI Conference 2019 Conference Paper

Adversarial Learning for Weakly-Supervised Social Network Alignment

Chaozhuo Li
Senzhang Wang
Yukun Wang
Philip Yu
Yanbo Liang
Yun Liu
Zhoujun Li

Nowadays, it is common for one natural person to join multiple social networks to enjoy different kinds of services. Linking identical users across multiple social networks, also known as social network alignment, is an important problem of great research challenges. Existing methods usually link social identities on the pairwise sample level, which may lead to undesirable performance when the number of available annotations is limited. Motivated by the isomorphism information, in this paper we consider all the identities in a social network as a whole and perform social network alignment from the distribution level. The insight is that we aim to learn a projection function to not only minimize the distance between the distributions of user identities in two social networks, but also incorporate the available annotations as the learning guidance. We propose three models SNNAu, SNNAb and SNNAo to learn the projection function under the weakly-supervised adversarial learning framework. Empirically, we evaluate the proposed models over multiple datasets, and the results demonstrate the superiority of our proposals.

PDF Details