Yun-Wei Chu
Computer Science · Purdue University West Lafayette
Publications
28
Citations
194
Est. group size
~1
Recurring co-author estimate
Active years
9
Publishing since 2017
Yun-Wei Chu's work focuses on federated learning, a machine learning approach where multiple devices or institutions train models collaboratively without sharing raw data, applied to areas such as machine translation, student performance prediction, and communication-efficient training over networks. Earlier work also covered multimodal tasks like visual storytelling and video dialogue systems. The overall theme is building privacy-conscious, efficient, and personalized machine learning systems that work across distributed data sources.
Publication output has fluctuated over the last decade, with a notable peak in 2021 and 2024, but has averaged about 3 papers per year over the last five years without a clear sustained upward or downward trend.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
IEEE Transactions on Audio Speech and Language Processing · 2025
- Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks
Proceedings of the AAAI Conference on Artificial Intelligence · 2025
- Multi-Layer Personalized Federated Learning for Mitigating Biases in Student Predictive Analytics
IEEE Transactions on Emerging Topics in Computing · 2024
- Energy-Efficient Connectivity-Aware Learning Over Time-Varying D2D Networks
IEEE Journal of Selected Topics in Signal Processing · 2024
- Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
2024
- Unlocking the Potential of Model Calibration in Federated Learning
arXiv (Cornell University) · 2024
- Only Send What You Need: Learning to Communicate Efficiently in Federated Multilingual Machine Translation
arXiv (Cornell University) · 2024
- Rethinking the Starting Point: Collaborative Pre-Training for Federated Downstream Tasks
arXiv (Cornell University) · 2024
- Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
2023
- Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
arXiv (Cornell University) · 2023
- Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning
Proceedings of the 31st ACM International Conference on Information & Knowledge Management · 2022
- Learning to Rank Visual Stories From Human Ranking Data
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
- Multi-Layer Personalized Federated Learning for Mitigating Biases in Student Predictive Analytics
arXiv (Cornell University) · 2022
- Mitigating Biases in Student Performance Prediction via Attention-Based Personalized Federated Learning
arXiv (Cornell University) · 2022
- Let's Talk! Striking Up Conversations via Conversational Visual Question Generation
arXiv (Cornell University) · 2022
- arXiv (Cornell University)×12
- Open MIND×2
- IEEE Access×1
- IEEE Transactions on Emerging Topics in Computing×1
- IEEE Journal of Selected Topics in Signal Processing×1
- Christopher G. Brinton
Computer Science · Purdue University West Lafayette
- Feijie Wu
Computer Science · Purdue University West Lafayette
- Dong-Jun Han
Computer Science · Purdue University West Lafayette
- Chenghong Wang
Computer Science · Indiana University
- Atul Sharma
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