Dong-Jun Han
Computer Science · Purdue University West Lafayette
Publications
89
Citations
507
Est. group size
~5
Recurring co-author estimate
Active years
14
Publishing since 2013
Dong-Jun Han works on distributed and privacy-preserving machine learning, especially federated learning (where multiple devices train a shared model without sharing raw data) and split learning (where a model is divided across devices and a server). Recent work also touches domain generalization, model calibration, and adapting vision-language models to new or shifted data distributions. The research combines theoretical analysis with practical system designs for settings involving multiple, decentralized data sources.
Publication output has grown substantially over the last decade, rising from just a few papers per year before 2022 to a sustained higher rate of 11-21 papers annually from 2023 onward.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Multi-Tier Split Federated Learning for Multi-Level Personalization
2026
- Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
arXiv (Cornell University) · 2026
- Differentially-Private Multi-Tier Federated Learning: A Formal Analysis and Evaluation
IEEE Transactions on Networking · 2026
- Efficient Split Learning With Overlapping Areas: Handling Distribution Shift in Multi-Cell Networks
IEEE Transactions on Networking · 2026
- Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
Open MIND · 2026
- Sporadic Gradient Tracking over Directed Graphs: A Theoretical Perspective on Decentralized Federated Learning
arXiv (Cornell University) · 2026
- ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization
Proceedings of the AAAI Conference on Artificial Intelligence · 2026
- Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
arXiv (Cornell University) · 2026
- Differentially-Private Multi-Tier Federated Learning: A Formal Analysis and Evaluation
arXiv (Cornell University) · 2025
- PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative Models
arXiv (Cornell University) · 2025
- Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration
Proceedings of the AAAI Conference on Artificial Intelligence · 2024
- FDW-YOLOv8: A Lightweight Unmanned Aerial Vehicle Small Target Detection Algorithm Based on Enhanced YOLOv8
2024
- Consistency-Guided Temperature Scaling Using Style and Content Information for Out-of-Domain Calibration
arXiv (Cornell University) · 2024
- Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization
arXiv (Cornell University) · 2024
- Improving Low-Latency Predictions in Multi-Exit Neural Networks via Block-Dependent Losses
IEEE Transactions on Neural Networks and Learning Systems · 2023
- arXiv (Cornell University)×38
- IEEE Journal on Selected Areas in Communications×4
- IEEE Transactions on Networking×4
- IEEE Transactions on Wireless Communications×3
- IOP Conference Series Materials Science and Engineering×3
- Sai Aparna Aketi
Computer Science · Purdue University West Lafayette
- Feijie Wu
Computer Science · Purdue University West Lafayette
- Rohit Parasnis
Computer Science · Purdue University West Lafayette
- Christopher G. Brinton
Computer Science · Purdue University West Lafayette
- Wenzhi Fang
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile