Subspace Adversarial Training

Li, Tao; Wu, Yingwen; Chen, Sizhe; Fang, Kun; Huang, Xiaolin

doi:10.48550/arxiv.2111.12229

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…use smooth induced adversarial regularity to improve model robustness while optimizing the proximity algorithm to avoid catastrophic forgetting. Li et al [ 39 ] propose subspace adversarial training (Sub-AT) which constrains AT (adversarial training) in a carefully extracted subspace. it successfully solves both overfitting problems and greatly improves Robustness.…”

Section: Related Workmentioning

confidence: 99%

Rumor detection based on Attention Graph Adversarial Dual Contrast Learning

Zhang,

Liu,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

It is becoming harder to tell rumors from non-rumors as social media becomes a key news source, which invites malicious manipulation that could do harm to the public’s health or cause financial loss. When faced with situations when the session structure of comment sections is deliberately disrupted, traditional models do not handle them adequately. In order to do this, we provide a novel rumor detection architecture that combines dual comparison learning, adversarial training, and attention filters. We suggest the attention filter module to achieve the filtering of some dangerous comments as well as the filtering of some useless comments, allowing the nodes to enter the GAT graph neural network with greater structural information. The adversarial training module (ADV) simulates the occurrence of malicious comments through perturbation, giving the comments some defense against malicious comments. It also serves as a hard negative sample to aid double contrast learning (DCL), which aims to learn the differences between various comments, and incorporates the final loss in the form of a loss function to strengthen the model. According to experimental findings, our AGAD (Attention Graph Adversarial Dual Contrast Learning) model outperforms other cutting-edge algorithms on a number of rumor detection tasks. The code is available at https://github.com/icezhangGG/AGAD.git.

show abstract

Section: Related Workmentioning

confidence: 99%