Cross-Platform Multi-Modal Transfer Learning Framework for Cyberbullying Detection
Electronics · 20.01.2026 · 15 (2) · 442
DOI: 10.3390/electronics15020442 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 20.01.2026. Verfasst von Weiqi Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Cyberbullying and hate speech increasingly appear in multi-modal social media posts, where images and text are combined in diverse and fast changing ways across platforms. These posts differ in style, vocabulary and layout, and labeled data are sparse and noisy, which makes it difficult to train detectors that are both reliable and deployable under tight computational budgets. Many high performing systems rely on large vision language backbones, full parameter fine tuning, online retrieval or model ensembles, which raises training and inference costs. We present a parameter efficient cross-platform multi-modal transfer learning framework for cyberbullying and hateful content detection. Our framework has three components. First, we perform domain adaptive pretraining of a compact ViLT backbone on in domain image-text corpora. Second, we apply parameter efficient fine tuning that updates only bias terms, a small subset of LayerNorm parameters and the classification head, leaving the inference computation graph unchanged. Third, we use noise aware knowledge distillation from a stronger teacher built from pretrained text and CLIP based image-text encoders, where only high confidence, temperature scaled predictions are used as soft labels during training, and teacher models and any retrieval components are used only offline. We evaluate primarily on Hateful Memes and use IMDB as an auxiliary text only benchmark to show that the deployment aware PEFT + offline-KD recipe can still be applied when other modalities are unavailable. On Hateful Memes, our student updates only 0.11% of parameters and retain about 96% of the AUROC of full fine-tuning.
Zitieren
APA
Zhang, W., Dong, C., Yao, A., Nazari, A., & Gaddam, A. (2026). Cross-Platform Multi-Modal Transfer Learning Framework for Cyberbullying Detection. Electronics, 15(2), 442. https://doi.org/10.3390/electronics15020442
Vancouver
Zhang W, Dong C, Yao A, Nazari A, Gaddam A. Cross-Platform Multi-Modal Transfer Learning Framework for Cyberbullying Detection. Electronics. 2026;15(2):442. doi:10.3390/electronics15020442
BibTeX
@article{Zhang2026,
author = {Zhang, Weiqi and Dong, Chengzu and Yao, Aiting and Nazari, Asef and Gaddam, Anuroop},
title = {Cross-Platform Multi-Modal Transfer Learning Framework for Cyberbullying Detection},
journal = {Electronics},
year = {2026},
volume = {15},
number = {2},
pages = {442},
doi = {10.3390/electronics15020442}
}
EUVIMED