Jiabei Liu — accepted AI-conference papers

2025

FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning

Fan Wu, Xinyu Yan, Jiabei Liu, Wei Yang Bryan Lim

NeurIPS 2025poster

Federated Multi-Task Learning (FL-MTL) enables clients with heterogeneous data to collaboratively train models capable of handling multiple downstream tasks. However, FL-MTL faces key challenges, including statistical heterogeneity, task interference, and the need to balance local learning with glob…

Cited by 0 Source ↗code ↗Scholar ↗

2020

Meta Metric Learning for Highly Imbalanced Aerial Scene Classification

Jian Guan, Jiabei Liu, Jianguo Sun, Pengming Feng, Tong Shuai, Wenwu Wang

ICASSP 2020accepted

Class imbalance is an important factor that affects the performance of deep learning models used for remote sensing scene classification. In this paper, we propose a random finetuning meta metric learning model (RF-MML) to address this problem. Derived from episodic training in meta metric learning,…

Cited by 0 Source ↗Scholar ↗