Jiayi
Chen
(陈
嘉怡)
85 Engineer's Way
Charlottesville
VA 22904, USA
I am a Ph.D. candidate at University of Virginia majoring in Computer Science. I am advised by Prof. Aidong Zhang. My research interests are broadly in Machine Learning and Data Mining, with the focuses on Multimodal Machine Learning (Audio-video and Vision-language related tasks), Federated Learning, and Model-efficient Transfer Learning.
Prior to PhD, I received my Bachelor’s degree in Automation Engineering in 2015 and Master’s degree in Control Science and Engineering in 2018 from Xi’an Jiaotong University. I was affiliated with the Institute of Artificial Intelligence and Robotics during 2015-2018, under the supervision of Prof. Nanning Zheng and Prof. Xuguang Lan, working on projects related to Computer Vision, 3D Neural Stylistic Rendering, and Robotics.
I also did summer internships at Google in 2022 and 2023, working on Multimodal Few-shot Learning, LLMs, and Efficient Personalization.
news
| Dec 9, 2023 | Our paper “On Disentanglement of Asymmetrical Knowledge Transfer for Modality-Task Agnostic Federated Learning” is accepted by AAAI 2024 main track as an Oral paper! |
|---|---|
| Oct 9, 2023 | We got 2 papers accepted by EMNLP 2023! |
| Jun 6, 2023 | I joined the YouTube WatchNext and DeepMind Brain STAR teams for a summer internship at Google! |
| Jun 1, 2023 | Our paper entitled “On Hierarchical Disentanglement of Interactive Behaviors for Multimodal Spatiotemporal Data with Incompleteness” is accepted by KDD 2023 Research Track! |
| Apr 22, 2023 | I successfully presented my Thesis Proposal on “Spatiotemporally Collaborative Multimodal Machine Learning”. |
| Aug 8, 2022 | Our paper entitled “FedMSplit: Correlation-adaptive Federated Multitask Learning across Multimodal Split Networks” was accepted by KDD’22 Research Track. |
| Jun 6, 2022 | I started my first day of summer internship at Google! |
| Apr 22, 2022 | Our paper “Topological Transduction for Hybrid Few-shot Learning” accepted by WWW’22. |
| Sep 18, 2021 | Our paper “HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities” is accepted by CIKM’21. |
| Aug 12, 2020 | Our paper “HGMF: Heterogeneous Graph-Based Fusion for Multimodal Data with Incompleteness” is accepted by KDD 2020 Research Track. |