Jianhui Sun

Research Scientist, Meta

js9gu AT virginia DOT edu

Bio

I am a Research Scientist at Meta.

I was a Ph.D. student in Department of Computer Science at University of Virginia, advised by Prof. Aidong Zhang.

I obtained my B.S. degree in Mathematics at Fudan University and I was in the PhD program in Department of Statistics at University of Virginia. I spent summers doing internships in Meta and Amazon.

My research covers a variety of topics in Machine Learning and Data Mining, including federated learning [NeurIPS'23, NeurIPS'23, AAAI'24], AutoML [TKDD'23, KDD'22, KDD'21], and adversarial attacks [KDD'23, KDD'20].

News

Publications [Google Scholar]

indicates equal contribution.

On the Role of Server Momentum in Federated Learning

AAAI'24: AAAI Conference on Artificial Intelligence. 2024.

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

NeurIPS'23: Advances in Neural Information Processing Systems. 2023.

Federated Conditional Stochastic Optimization

NeurIPS'23: Advances in Neural Information Processing Systems. 2023.

Enhance Diffusion to Improve Robust Generalization

KDD'23: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2023.

Scheduling Hyperparameters to Improve Generalization: From Centralized SGD to Asynchronous SGD

TKDD: Transactions on Knowledge Discovery from Data. 2023.

Demystify Hyperparameters for Stochastic Optimization with Transferable Representations

KDD'22: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2022.

A Stagewise Hyperparameter Scheduler to Improve Generalization

KDD'21: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2021.

Malicious Attacks against Deep Reinforcement Learning Interpretations

KDD'20: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2020. Best Paper Runner-up

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

ICLR'24: International Conference on Learning Representations. 2024.

On the Role of Server Momentum in Federated Learning

AAAI'24: AAAI Conference on Artificial Intelligence. 2024.

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

NeurIPS'23: Advances in Neural Information Processing Systems. 2023.

Federated Conditional Stochastic Optimization

NeurIPS'23: Advances in Neural Information Processing Systems. 2023.

Enhance Diffusion to Improve Robust Generalization

KDD'23: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2023.

Scheduling Hyperparameters to Improve Generalization: From Centralized SGD to Asynchronous SGD

TKDD: Transactions on Knowledge Discovery from Data. 2023.

Understanding and Enhancing Robustness of Concept-based Models

AAAI'23: AAAI Conference on Artificial Intelligence. 2023.

Shifting Episodic Prediction With Online Cognitive Bias Modification: A Randomized Controlled Trial

Clinical Psychological Science. 2023.

Dynamic Transfer Learning across Graphs

Demystify Hyperparameters for Stochastic Optimization with Transferable Representations

KDD'22: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2022.

Augmenting Knowledge Transfer across Graphs

ICDM'22: IEEE International Conference on Data Mining. 2022.

A Stagewise Hyperparameter Scheduler to Improve Generalization

KDD'21: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2021.

Malicious Attacks against Deep Reinforcement Learning Interpretations

KDD'20: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2020. Best Paper Runner-up

Correlation Networks for Extreme Multi-label Text Classification

KDD'20: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2020.

GLIMA: Global and Local Time Series Imputation with Multi-directional Attention Learning

BigData'20: IEEE International Conference on Big Data. 2020.

Recurrent Imputation for Multivariate Time Series with Missing Values

ICHI'19: IEEE International Conference on Healthcare Informatics. 2019.

A Low-rank Multivariate General Linear Model for Multi-subject fMRI Data and a Non-convex Optimization Algorithm for Brain Response Comparison

NeuroImage. 2018.

Vitæ