Learning Domain-Invariant Features for Out-of-Context News Detection
This addresses misinformation detection for online media platforms by enabling adaptation to new, unlabeled news topics or agencies, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackles the problem of detecting out-of-context news on unlabeled domains by proposing ConDA-TTA, a method that uses contrastive learning and maximum mean discrepancy to learn domain-invariant features, achieving improvements of up to 2.93% in F1 and 2.08% in accuracy over baselines.
Out-of-context news is a common type of misinformation on online media platforms. This involves posting a caption, alongside a mismatched news image. Existing out-of-context news detection models only consider the scenario where pre-labeled data is available for each domain, failing to address the out-of-context news detection on unlabeled domains (e.g. news topics or agencies). In this work, we therefore focus on domain adaptive out-of-context news detection. In order to effectively adapt the detection model to unlabeled news topics or agencies, we propose ConDA-TTA (Contrastive Domain Adaptation with Test-Time Adaptation) which applies contrastive learning and maximum mean discrepancy (MMD) to learn domain-invariant features. In addition, we leverage test-time target domain statistics to further assist domain adaptation. Experimental results show that our approach outperforms baselines in most domain adaptation settings on two public datasets, by as much as 2.93% in F1 and 2.08% in accuracy.