Domain Adaptation with Adversarial Training and Graph Embeddings

TL;DR

This paper introduces a novel deep learning model combining adversarial domain adaptation and graph-based semi-supervised learning to improve classification of social media posts during crises, effectively handling data distribution shifts.

Contribution

The paper presents a unified framework integrating adversarial training and graph embeddings for domain adaptation in crisis-related social media classification.

Findings

Significant accuracy improvements over baselines.

Effective handling of distribution shifts between related crisis events.

Utilization of unlabeled data enhances model performance.

Abstract

The success of deep neural networks (DNNs) is heavily dependent on the availability of labeled data. However, obtaining labeled data is a big challenge in many real-world problems. In such scenarios, a DNN model can leverage labeled and unlabeled data from a related domain, but it has to deal with the shift in data distributions between the source and the target domains. In this paper, we study the problem of classifying social media posts during a crisis event (e.g., Earthquake). For that, we use labeled and unlabeled data from past similar events (e.g., Flood) and unlabeled data for the current event. We propose a novel model that performs adversarial learning based domain adaptation to deal with distribution drifts and graph based semi-supervised learning to leverage unlabeled data within a single unified deep learning framework. Our experiments with two real-world crisis datasets collected from Twitter demonstrate significant improvements over several baselines.