Publications

SA-PEF: Step-Ahead Partial Error Feedback for Efficient Federated Learning

Click the Cite button above to import publication metadata into your reference management software. Abstract Biased gradient compression with error feedback (EF) reduces communication in federated learning (FL), but under non-IID data, the residual error can decay slowly, causing gradient mismatch and stalled progress in the early rounds.

Dawit Kiros Redie, Reza Arablouei, Stefan Werner

Enhancing Efficiency and Privacy in Federated Learning via Partial Model Sharing

Communication overhead and privacy risks remain significant challenges in federated learning (FL). We introduce Partial Model Sharing …

Dawit Kiros Redie, Reza Arablouei, Stefan Werner

Oral cancer detection using transfer learning-based framework from histopathology images

Transfer learning for oral cancer detection using histopathology images, improving diagnostic accuracy with limited data.

Dawit Kiros Redie, Saurabh Bilgaiyan, Santwana Sagnika

Diagnosis of COVID-19 using chest X-ray images based on modified DarkCovidNet model

This study presents a CNN-based model using chest X-ray images for accurate COVID-19 detection. The model achieved 99.53% accuracy for …

Dawit Kiros Redie, Abdulhakim Edao Sirko, Tensaie Melkamu Demissie, Semagn Sisay Teferi, Vimal Kumar Shrivastava, Om Prakash Verma, Tarun Kumar Sharma