基于对抗图增强对比学习的虚假新闻检测

PDF(4110 KB)

中文信息学报 ›› 2023, Vol. 37 ›› Issue (6) : 137-146.

情感分析与社会计算

基于对抗图增强对比学习的虚假新闻检测

陈卓敏¹,王莉¹,朱小飞²,王子康³

作者信息 +

Fake News Detection Based on Adversarial Graph Enhanced Contrastive Learning

CHEN Zhuomin¹, WANG Li¹, ZHU Xiaofei², WANG Zikang³

Author information +

History +

摘要

随着互联网的快速发展,社交媒体成为了新闻发布和传播的主要平台,如何准确识别虚假新闻已成为研究热点。现有的基于深度学习的虚假新闻检测方法在面对噪声和敌对信息时缺乏鲁棒性。为了应对这一挑战,该文提出了一种对抗图增强对比学习的方法,该方法引入对抗对比学习,使模型抓住少量但充分的信息完成增强图与原始图之间的互信息最大化,在进行训练时重点捕捉有用信息。同时,该模型还利用了特征增强器和图表示对比学习进行图表示增强,加强特征学习。在两个公共数据集上进行的实验表明,该模型在现有基线上达到了最优的性能。

Abstract

Existing deep learning-based fake news detection methods are defected in dealing with face of noise and hostile information. This paper proposes an adversarial graph-enhanced contrastive learning method to address this issue. It introduces adversarial contrastive learning so that the model can maximize the mutual information between the enhanced graph and the original graph. Specifically, this model also applies a feature enhancer to the graph representation contrastive learning. Experimental results on two public datasets show that the proposed model achieves state-of-the-art performance.

导出引用

陈卓敏,王莉,朱小飞,王子康. 基于对抗图增强对比学习的虚假新闻检测. 中文信息学报. 2023, 37(6): 137-146

CHEN Zhuomin, WANG Li, ZHU Xiaofei, WANG Zikang. Fake News Detection Based on Adversarial Graph Enhanced Contrastive Learning. Journal of Chinese Information Processing. 2023, 37(6): 137-146

参考文献

[1] 陈慧敏,金思辰,林微,等. 新冠疫情相关社交媒体谣言传播量化分析[J].计算机研究与发展,2021,58(7): 1366-1384.
[2] 祖坤琳,赵铭伟,郭凯,等. 新浪微博谣言检测研究[J]. 中文信息学报, 2017, 31(3): 198-204.
[3] CASTILLO C, MENDOZA M, POBLETE B. Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web, 2011: 675-684.
[4] KWON S, CHA M, JUNG K, et al. Prominent features of rumor propagation in online social media[C]//Proceedings of IEEE 13th International Conference on Data Mining. 2013: 1103-1108.
[5] YANG F, LIU Y, YU X, et al. Automatic detection of rumor on sina weibo[C]//Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics, 2012: 1-7.
[6] MA J, GAO W, MITRA P, et al. Detecting rumors from microblogs with recurrent neural networks[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016: 3818-3824.
[7] MA J, GAO W, WONG K F. Rumor detection on twitter with tree-structured recursive neural networks[C]//Proceedings of Association for Computational Linguistics, 2018.
[8] YU F, LIU Q, WU S, et al. A Convolutional approach for misinformation identification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017: 3901-3907.
[9] BIAN T, XIAO X, XU T, et al. Rumor detection on social media with bi-directional graph convolutional networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(01): 549-556.
[10] 周东浩,韩文报. DiffRank: 一种新型社会网络信息传播检测算法[J].计算机学报,2014,37(4): 884-893.
[11] HE Z, LI C, ZHOU F, et al. Rumor detection on social media with event augmentations[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021: 2020-2024.
[12] VAIBHAV R M, ANNASAMY E H. HOVY. Do sentence interactions matter?: Leveraging sentence level representations for fake news classification[C]//Proceedings of the 13th Workshop on Graph-Based Methods for Natural Language Processing, 2019: 134-139.
[13] YU F, LIU Q, WU S, et al. A convolutional approach for misinformation identification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017: 3901-3907.
[14] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations, 2017.
[15] CHEN T, KORNBLITH S, NOROUZI M, et al. A simple framework for contrastive learning of visual representations[C]///Proceedings of International Conference on Machine Learning, 2020: 1597-1607.
[16] WU H, MA T, WU L, et al. Unsupervised reference-free summary quality evaluation via contrastive learning[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2020: 3612-3621.
[17] CAI H, CHEN H, SONG Y, et al. Group-wise contrastive learning for neural dialogue generation[C]//Proceedings of the Association for Computational Linguistics, 2020: 793-802.
[18] BARBER P, JOST J T, NAGLER J, et al. Tweeting from left to right: Is online political communication more than an echo chamber?[J]. Psychological Science, 2015, 26(10): 1531-1542.
[19] SURESH S, LI P, HAO C, et al. Adversarial graph augmentation to improve graph contrastive learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 15920-15933.
[20] BRODY S, ALON U, YAHAV E. How attentive are graph attention networks?[C]//Proceeding of the 10th International Conference on Learning Representations, 2022.
[21] ROBINS G, PATTISON P, KALISH Y, et al. An introduction to exponential random graph (p) models for social Networks[J]. Social Networks, 2007, 29(2): 173-191.
[22] JANG E, GU S, POOLE B. Categorical reparameterization with gumbel-softmax[C]//Proceedings of the 5th International Conference on Learning Representations, 2017.
[23] POOLE B, OZAIR S, VAN DEN OORD A, et al. On variational bounds of mutual information[C]//Proceedings of International Conference on Machine Learning, 2019: 5171-5180.
[24] ZHAO L, AKOGLU L. Pairnorm: Tackling oversmoothing in GNNS[C]//Proceeding of the 8th International Conference on Learning Representations, 2020.
[25] LIU W, WEN Y, YU Z, et al. Large-margin softmax loss for convolutional neural networks[C]//Proceedings of the 33rd International Conference on Machine Learning, 2016.
[26] MA J, GAO W, WEI Z, et al. Detect rumors using time series of social context information on microblogging websites[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, 2015: 1751-1754.
[27] CASTILLO C, MENDOZA M, POBLETE B. Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web, 2011: 675-684.
[28] LIU Y, WU Y F. Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.

基金

国家自然科学基金(U22A20167);国家重点研究与发展计划(2021YFB3300503);重庆市自然科学基金(CSTB2022NSCQ-MSX1672);重庆市教育委员会科学技术研究计划重大项目(KJZD-M202201102)

PDF(4110 KB)

1770

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金



Issue Date
2023-08-15