TY - JOUR
T1 - Fuzzy Detection System for Rumors through Explainable Adaptive Learning
AU - Guo, Zhiwei
AU - Yu, Keping
AU - Jolfaei, Alireza
AU - Bashir, Ali Kashif
AU - Almagrabi, Alaa Omran
AU - Kumar, Neeraj
N1 - Publisher Copyright:
© 1993-2012 IEEE.
PY - 2021/12/1
Y1 - 2021/12/1
N2 - Nowadays, rumor spreading has gradually evolved into a kind of organized behaviors, accompanied with strong uncertainty and fuzziness. However, existing fuzzy detection techniques for rumors focused their attention on supervised scenarios that require expert samples with labels for training. Thus, they are not able to well handle the unsupervised scenarios where labels are unavailable. To bridge such gap, this article proposed a fuzzy detection system for rumors through explainable adaptive learning. Specifically, its core is a graph embedding-based generative adversarial network (Graph-GAN) model. First of all, it constructs fine-grained feature spaces via graph-level encoding. Furthermore, it introduces continuous adversarial training between a generator and a discriminator for unsupervised decoding. The two-stage scheme not only solves the fuzzy rumor detection under unsupervised scenarios, but also improves robustness of the unsupervised training. Empirically, a set of experiments are carried out based on three real-world datasets. Compared with seven benchmark methods in terms of four metrics, the results of the Graph-GAN reveal a proper performance, which averagely exceeds baselines by 5-10%.
AB - Nowadays, rumor spreading has gradually evolved into a kind of organized behaviors, accompanied with strong uncertainty and fuzziness. However, existing fuzzy detection techniques for rumors focused their attention on supervised scenarios that require expert samples with labels for training. Thus, they are not able to well handle the unsupervised scenarios where labels are unavailable. To bridge such gap, this article proposed a fuzzy detection system for rumors through explainable adaptive learning. Specifically, its core is a graph embedding-based generative adversarial network (Graph-GAN) model. First of all, it constructs fine-grained feature spaces via graph-level encoding. Furthermore, it introduces continuous adversarial training between a generator and a discriminator for unsupervised decoding. The two-stage scheme not only solves the fuzzy rumor detection under unsupervised scenarios, but also improves robustness of the unsupervised training. Empirically, a set of experiments are carried out based on three real-world datasets. Compared with seven benchmark methods in terms of four metrics, the results of the Graph-GAN reveal a proper performance, which averagely exceeds baselines by 5-10%.
KW - Cyberspace security
KW - fuzzy detection system
KW - generative adversarial learning (GAL)
KW - graph embedding (GE)
UR - http://www.scopus.com/inward/record.url?scp=85099730335&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099730335&partnerID=8YFLogxK
U2 - 10.1109/TFUZZ.2021.3052109
DO - 10.1109/TFUZZ.2021.3052109
M3 - Article
AN - SCOPUS:85099730335
VL - 29
SP - 3650
EP - 3664
JO - IEEE Transactions on Fuzzy Systems
JF - IEEE Transactions on Fuzzy Systems
SN - 1063-6706
IS - 12
ER -