About Me

Welcome! I am currently a fourth-year Ph.D. student at the Department of Computer Science, Emory University, where I am fortunate to be advised by Dr. Liang Zhao. Previously, I received my master’s degree in Statistics from George Washington University in 2020. I received my bachelor’s degree in Mathematics from the School of Mathematical Science, Fudan University in Shanghai, China in 2018. I previously worked as a research intern at NEC Lab America.

Research Interests

I am interested in designing efficient, generalizable, and explainable learning algorithms with theoretical guarantees. Specifically, my current research topics include but are not limited to 1. Learning strategies for domain transfer problems, such as multi-task learning (MTL), domain adaptation (DA), and domain generalization (DG). 2. Large-scale machine learning algorithms with better scalability and performance, such as distributed training for Graph Neural Networks (GNNs) and model compression & acceleration of LLMs, etc. 3. Online learning such as continual/lifelong learning with memory replay and neuro-inspiration.

Selected Projects

1. Domain and Knowledge Transfer

This project focuses on enhancing machine learning models’ adaptability and effectiveness across various domains/tasks.

a) Multi-task Learning

• Sign-Regularized Multi-Task Learning
  SDM 2023
• Saliency-Regularized Deep Multi-Task Learning
  KDD 2022

b) Domain Adaptation

• Prompt-based Domain Discrimination for Multi-source Time Series Domain Adaptation
  Preprint

c) Domain Generalization

• Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks
  ICLR 2023
• Deep Spatial Domain Generalization
  ICDM 2022

2. Efficient Large-Scale Machine Learning

Exploring scalable solutions in machine learning, particularly in GNNs and LLMs.

a) Distributed Training for Graph Neural Networks (GNNs)

• Distributed Graph Neural Network Training with Periodic Stale Representation Synchronization
  Preprint
• Staleness-Alleviated Distributed GNN Training via Online Dynamic-Embedding Prediction
  Preprint

b) Model Compression & Acceleration of LLMs

• Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models
  Preprint
• Gradient-Free Adaptive Global Pruning for Pre-trained Language Models
  Preprint

3. Neuro-Inspired Continual Learning

Focusing on memory-replay and neuro-inspiration approaches for continual learning.

• Saliency-Guided Hidden Associative Replay for Continual Learning
  AMHN Workshop @NeurIPS 2023
• Saliency-Augmented Memory Completion for Continual Learning
  SDM 2023

Services and Awards

• PC member for AISTATS (23’24’), NeurIPS (22’23’), ICLR (24’), AAAI (24’)
• Reviewer for KDD, ICML, ICLR, ICDM
• 2023 SDM student travel award
• 2022 CIKM student travel award
• 2022 KDD student travel award