Reinforcement Subgraph Reasoning for Fake News Detection

Ruichao Yang; Xiting Wang; Yiqiao Jin; Chaozhuo Li; Jianxun Lian; Xing Xie

doi:10.1145/3534678.3539277

Reinforcement Subgraph Reasoning for Fake News Detection

Ruichao Yang, Xiting Wang^*, Yiqiao Jin, Chaozhuo Li, Jianxun Lian, Xing Xie

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

59 Citations (Scopus)

Abstract

The wide spread of fake news has caused serious societal issues. We propose a subgraph reasoning paradigm for fake news detection, which provides a crystal type of explainability by revealing which subgraphs of the news propagation network are the most important for news verification, and concurrently improves the generalization and discrimination power of graph-based detection models by removing task-irrelevant information. In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. We also design a curriculum-based optimization method to ensure better convergence and train the two parts in an end-to-end manner.

Original language	English
Title of host publication	KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Editors	Aidong Zhang, Huzefa Rangwala
Publisher	Association for Computing Machinery (ACM)
Pages	2253-2262
Number of pages	10
ISBN (Electronic)	9781450393850
DOIs	https://doi.org/10.1145/3534678.3539277
Publication status	Published - 14 Aug 2022
Event	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 - Washington, DC, United States Duration: 14 Aug 2022 → 18 Aug 2022 https://kdd.org/kdd2022/index.html https://dl.acm.org/doi/proceedings/10.1145/3534678

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022
Country/Territory	United States
City	Washington, DC
Period	14/08/22 → 18/08/22
Internet address	https://kdd.org/kdd2022/index.html https://dl.acm.org/doi/proceedings/10.1145/3534678

User-Defined Keywords

explainability
fake news
social network
subgraph reasoning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1145/3534678.3539277

Cite this

Yang, R., Wang, X., Jin, Y., Li, C., Lian, J., & Xie, X. (2022). Reinforcement Subgraph Reasoning for Fake News Detection. In A. Zhang, & H. Rangwala (Eds.), KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 2253-2262). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery (ACM). https://doi.org/10.1145/3534678.3539277

Yang, Ruichao ; Wang, Xiting ; Jin, Yiqiao et al. / Reinforcement Subgraph Reasoning for Fake News Detection. KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. editor / Aidong Zhang ; Huzefa Rangwala. Association for Computing Machinery (ACM), 2022. pp. 2253-2262 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{6f7c2d11d5df48738611ced9b7df120e,

title = "Reinforcement Subgraph Reasoning for Fake News Detection",

abstract = "The wide spread of fake news has caused serious societal issues. We propose a subgraph reasoning paradigm for fake news detection, which provides a crystal type of explainability by revealing which subgraphs of the news propagation network are the most important for news verification, and concurrently improves the generalization and discrimination power of graph-based detection models by removing task-irrelevant information. In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. We also design a curriculum-based optimization method to ensure better convergence and train the two parts in an end-to-end manner.",

keywords = "explainability, fake news, social network, subgraph reasoning",

author = "Ruichao Yang and Xiting Wang and Yiqiao Jin and Chaozhuo Li and Jianxun Lian and Xing Xie",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computing Machinery.; 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022 ; Conference date: 14-08-2022 Through 18-08-2022",

year = "2022",

month = aug,

day = "14",

doi = "10.1145/3534678.3539277",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery (ACM)",

pages = "2253--2262",

editor = "Zhang, {Aidong } and Rangwala, {Huzefa }",

booktitle = "KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

address = "United States",

url = "https://kdd.org/kdd2022/index.html, https://dl.acm.org/doi/proceedings/10.1145/3534678",

}

Yang, R, Wang, X, Jin, Y, Li, C, Lian, J & Xie, X 2022, Reinforcement Subgraph Reasoning for Fake News Detection. in A Zhang & H Rangwala (eds), KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (ACM), pp. 2253-2262, 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022, Washington, DC, United States, 14/08/22. https://doi.org/10.1145/3534678.3539277

Reinforcement Subgraph Reasoning for Fake News Detection. / Yang, Ruichao; Wang, Xiting; Jin, Yiqiao et al.
KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ed. / Aidong Zhang; Huzefa Rangwala. Association for Computing Machinery (ACM), 2022. p. 2253-2262 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Reinforcement Subgraph Reasoning for Fake News Detection

AU - Yang, Ruichao

AU - Wang, Xiting

AU - Jin, Yiqiao

AU - Li, Chaozhuo

AU - Lian, Jianxun

AU - Xie, Xing

PY - 2022/8/14

Y1 - 2022/8/14

N2 - The wide spread of fake news has caused serious societal issues. We propose a subgraph reasoning paradigm for fake news detection, which provides a crystal type of explainability by revealing which subgraphs of the news propagation network are the most important for news verification, and concurrently improves the generalization and discrimination power of graph-based detection models by removing task-irrelevant information. In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. We also design a curriculum-based optimization method to ensure better convergence and train the two parts in an end-to-end manner.

AB - The wide spread of fake news has caused serious societal issues. We propose a subgraph reasoning paradigm for fake news detection, which provides a crystal type of explainability by revealing which subgraphs of the news propagation network are the most important for news verification, and concurrently improves the generalization and discrimination power of graph-based detection models by removing task-irrelevant information. In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. We also design a curriculum-based optimization method to ensure better convergence and train the two parts in an end-to-end manner.

KW - explainability

KW - fake news

KW - social network

KW - subgraph reasoning

UR - http://www.scopus.com/inward/record.url?scp=85137144452&partnerID=8YFLogxK

U2 - 10.1145/3534678.3539277

DO - 10.1145/3534678.3539277

M3 - Conference proceeding

AN - SCOPUS:85137144452

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 2253

EP - 2262

BT - KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

A2 - Zhang, Aidong

A2 - Rangwala, Huzefa

PB - Association for Computing Machinery (ACM)

T2 - 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2022

Y2 - 14 August 2022 through 18 August 2022

ER -

Yang R, Wang X, Jin Y, Li C, Lian J, Xie X. Reinforcement Subgraph Reasoning for Fake News Detection. In Zhang A, Rangwala H, editors, KDD 2022 - Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM). 2022. p. 2253-2262. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3534678.3539277

Reinforcement Subgraph Reasoning for Fake News Detection

Abstract

Publication series

Conference

User-Defined Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this