About

Hi! My name is Danni Peng (彭丹昵).
I'm currently a research scientist at the Institute of High Performance Computing (IHPC), A*STAR, Singapore. Before joining IHPC, I obtained my Ph.D. degree in Computer Science and Engineering from Nanyang Technological University (NTU), advised by Prof. Sinno Jialin Pan and sponsored by the Alibaba-NTU Talent Programme. Previously, I received my B.Eng. (Hons.) degree from the National University of Singapore (NUS).
My research interests lie in multi-task and multi-distribution learning scenarios, including meta-learning, continual learning, federated learning, and domain generalization.

Research

Publications

6. Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning
[paper]
Danni Peng, Yuan Wang, Huazhu Fu, Jinpeng Jiang, Yong Liu, Rick Siow Mong Goh, Qingsong Wei
To appear in Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI), 2025 (oral presentation)

5. Learning Task-Specific Initialization for Effective Federated Continual Fine-Tuning of Foundation Model Adapters
[paper]
Danni Peng, Yuan Wang, Huazhu Fu, Qingsong Wei, Yong Liu, Rick Siow Mong Goh
In Proceedings of IEEE Conference on Artificial Intelligence (IEEE CAI), 2024

4. Clustered Task-Aware Meta-Learning by Learning from Learning Paths
[paper][code][bibtex]
Danni Peng, Sinno Jialin Pan
In IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2023

3. Learning Gradient-based Mixup towards Flatter Minima for Domain Generalization
[paper]
Danni Peng, Sinno Jialin Pan
arXiv preprint, 2022

2. Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
[paper][code][bibtex]
Danni Peng, Sinno Jialin Pan, Jie Zhang, Anxiang Zeng
In Proceedings of the 15th ACM Conference on Recommender Systems (RecSys), 2021

1. Preventing Overfitting via Sample Reweighting for Recommender System Incremental Update (Student Abstract)
[paper][code][bibtex]
Danni Peng, Xiaobo Hu, Anxiang Zeng, Jie Zhang
In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), 2021

Doctoral Thesis

Learning to Generalize to New Tasks/Domains with Limited Data [link]

Services

Journal Reviewer

IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI)
IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
Artificial Intelligence (AIJ)

Conference Reviewer

The International Conference on Machine Learning (ICML)
The International Conference on Learning Representations (ICLR)
The Annual Conference on Neural Information Processing Systems (NeurIPS)

Teaching

CZ4041/​CE4041: Machine Learning, NTU (AY 2020-21 Sem 2, AY 2021-22 Sem 2)
CZ3005: Artificial Intelligence, NTU (AY 2020-21 Sem 1)
CZ1015/​CE1015: Introduction to Data Science and Artificial Intelligence, NTU (AY 2019-20 Sem 2)