Scholar
Guangji Bai
Google Scholar ID: gBMbU28AAAAJ
Applied Scientist, Amazon
Citations & Impact
Citations
494
H-index
12
i10-index
12
Publications
20
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- - Published papers:
- - SparseLLM: Towards Global Pruning for Pre-trained Language Models (NeurIPS 2024)
- - FedSpaLLM: Federated Pruning of Large Language Models (NAACL 2025 main)
- - Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models (Under review of CSUR)
- - Staleness-Alleviated Distributed GNN Training via Online Dynamic-Embedding Prediction (SDM 2025)
- - Continuous Temporal Domain Generalization (NeurIPS 2024)
- - Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks (ICLR 2023 Oral)
- - Sign-Regularized Multi-Task Learning (SDM 2023)
- - Saliency-Regularized Deep Multi-Task Learning (KDD 2022)
- - Saliency-Augmented Memory Completion for Continual Learning (SDM 2023)
- - PC member for KDD, ICML, ICLR, AISTATS, NeurIPS, AAAI, ICDM, etc.
- - Primary writer for the NSF NAIRR 240189 grant ($15k) on parallel and distributed training of LLMs on graphs.
- - Student travel award for KDD 22’, ICLR 23’, SDM 23’, CIKM 23’, NeurIPS 24’
Research Experience
- - Applied Scientist at Amazon.com, working on the shopping recommendation system
- - Research intern at Argonne National Laboratory and NEC Lab America
Education
- - Ph.D. in Computer Science from Emory University, advised by Dr. Liang Zhao
- - Master's degree in Statistics from George Washington University, 2020
- - Bachelor's degree in Mathematics from Fudan University, 2018
Background
- Applied Scientist at Amazon.com, focusing on building the next-gen shopping recommendation system, with a focus on customer intent understanding and modeling. Research interests include efficient large-scale machine learning, domain and knowledge transfer, and neuro-inspired continual learning.
Miscellany
- Personal interests not mentioned
