Unsupervised Domain Adaptation With Global and Local Graph Neural Networks Under Limited Supervision and Its Application to Disaster Response

Ghosh, Samujjwal and Maji, Subhadeep and Desarkar, Maunendra Sankar (2022) Unsupervised Domain Adaptation With Global and Local Graph Neural Networks Under Limited Supervision and Its Application to Disaster Response. IEEE Transactions on Computational Social Systems. pp. 1-12. ISSN 2373-7476

Text
IEEE_Transactions_on_Computational_Social_Systems.pdf - Published Version
Restricted to Registered users only
Download (2MB) | Request a copy

Abstract

Identification and categorization of social media posts generated during disasters are crucial to reduce the suffering of the affected people. However, the lack of labeled data is a significant bottleneck in learning an effective categorization system for a disaster. This motivates us to study the problem as unsupervised domain adaptation (UDA) between a previous disaster with labeled data (source) and a current disaster (target). However, if the amount of labeled data available is limited, it restricts the learning capabilities of the model. To handle this challenge, we use limited labeled data along with abundantly available unlabeled data, generated during a source disaster to propose a novel two-part graph neural network (GNN). The first part extracts domain-agnostic global information by constructing a token-level graph across domains and the second part preserves local instance-level semantics. In our experiments, we show that the proposed method outperforms state-of-the-art techniques by 2.74% weighted F₁ score on average on two standard public datasets in the area of disaster management. We also report experimental results for granular actionable multilabel classification datasets in disaster domain for the first time, on which we outperform BERT by 3.00% on average w.r.t. weighted F₁. Additionally, we show that our approach can retain performance when minimal labeled data are available. IEEE

[error in script]

IITH Creators:

IITH Creators	ORCiD
Desarkar, Maunendra Sankar	https://orcid.org/0000-0003-1963-7338

Item Type:

Article

Uncontrolled Keywords:

Computational modeling; Disaster management; Disaster response; graph neural network (GNN); Graph neural networks; Predictive models; Social networking (online); Task analysis; text classification; unsupervised domain adaptation (UDA); Wireless fidelity

Subjects:

Computer science

Divisions:

Department of Computer Science & Engineering

Depositing User:

. LibTrainee 2021

Date Deposited:

22 Jul 2022 06:10

Last Modified:

22 Jul 2022 06:10

URI:

http://raiithold.iith.ac.in/id/eprint/9859