Weihai Lu

Weihai Lu

Auto-generated profile, based on publicly available information

Weihai Lu

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 October 2024
Verified
Conference Paper
Open access
YTYu Tong
Yu Tong
WLWeihai Lu
Weihai Lu
ZZZhe Zhao
Zhe Zhao
SLSong Lai
Song Lai
TSTong Shi
Tong Shi
Recently, automatic multi-domain fake news detection has attracted widespread attention. Many methods achieve domain adaptation by modeling domain category gate networks and domain-invariant features. However, existing multi-domain fake news detection faces three main challenges: (1) Inter-domain modal semantic deviation, where similar texts and images carry different meanings across various domains. (2) Inter-domain modal dependency deviation, where the dependence on different modalities varies across domains. (3) Inter-domain knowledge dependency deviation, where the reliance on cross-domain knowledge and domain-specific knowledge differs across domains. To address these issues, we propose a Multi-modal Multi-Domain Fake News Detection Model (MMDFND). MMDFND incorporates domain embeddings and attention mechanisms into a progressive hierarchical extraction network to achieve domain-adaptive domain-related knowledge extraction. Furthermore, MMDFND utilizes Stepwise Pivot Transformer networks and adaptive instance normalization to effectively utilize information from different modalities and domains. We validate the effectiveness of MMDFND through comprehensive comparative experiments on two real-world datasets and conduct ablation experiments to verify the effectiveness of each module, achieving state-of-the-art results on both datasets. The source code is available at https://github.com/yutchina/MMDFND.

11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
WLWeihai Lu
Weihai Lu
YTYu Tong
Yu Tong
ZYZhiqiu Ye
Zhiqiu Ye
Recently, multi-domain fake news detection has garnered increasing attention in academia. In particular, the integration of multimodal information into multi-domain fake news detection has emerged as a highly promising research direction. However, this field faces three main challenges: (1) Inaccurate domain identification, where predefined explicit identifiers fail to adapt to the inherent complexity of data; (2) Imbalanced multi-domain data distribution, which may induce negative transfer effects; and (3) Variable multi-domain modal contributions, indicating domain-specific differences in how various modalities influence news veracity assessments. To address these issues, we propose the Domain-Aware Multi-Modal Multi-View Fake News Detection (DAMMFND) framework. DAMMFND effectively extracts more accurate domain information through Domain Disentanglement, while simultaneously mitigating negative transfer between domains. Furthermore, DAMMFND introduces a Domain-Aware Multi-View Discriminator and a Domain-Enhanced Multi-view Decision Layer, which accurately quantify the contribution of domain information to multimodal, multi-view decision-making processes. Extensive experiments conducted on two real-world datasets demonstrate that the proposed model outperforms state-of-the-art baselines.




27 October 2025
Verified
Conference Paper
Open access
YTYu Tong
Yu Tong
WLWeihai Lu
Weihai Lu
XCXiaoxi Cui
Xiaoxi Cui
YMYifan Mao
Yifan Mao
ZZZhejun Zhao
Zhejun Zhao