Siyang Jiang Homepage
Publications

Publications

Publications

AAAI
Incremental Reinforcement Learning with Dual-Adaptive ϵ-greedy Exploration

Wei Ding*, Siyang Jiang*, Hsi-Wen Chen*,Ming-Syan Chen

Proc. of Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023). Accept rate: 19.60%, 1721 out of 8777
* denotes the equal contribution.

FPT
Dual-Triangular QR Decomposition with Global Acceleration and Partially Q-Rotation Skipping

Rui Fang, Siyang Jiang, Hsi-Wen Chen, Wei Ding and Ming-Syan Chen

Proc. of the IEEE International Conference on Field Programmable Technology (FPT 2022).

NN
Pairwise learning problems with regularization networks and Nyström subsampling approach

Cheng Wang, Ting Hu, Siyang Jiang

Neural Networks (2022, JCR Q1)

JCSC
LiCAM: Long-Tailed Instance Segmentation with Real-Time Classification Accuracy Monitoring

Rongguang Ye, Yantong Guo, Xian Shuai, Rongye Ye, Siyang Jiang†, Hui Jiang†

Journal of Circuits, Systems and Computers, 2022
† Denotes the corresponding authors.

PAKDD
PGADA:Perturbation-Guided Adversarial Alignment for Few-shot Learning Under the Support-QueryShift

Siyang Jiang, Wei Ding, Hsi-Wen Chen, Ming-Syan Chen

Proc. of the 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD, 2022). Accept rate: 19.30%, 121 out of 627.

IPSN
BalanceFL: Addressing Class Imbalance in Long-tail Federated Learning

Xian Shuai, Yulin Shen, Siyang Jiang, Zhihe Zhao, Zhenyu Yan, Guoliang Xing

ACM/IEEE Intermational Conference on Information Processing in Sensor Networks (IPSN 2022). Accept rate: 30.15%, 38 out of 126.

RIIT
Rethinking The Implementation Tricks And Monotonicity Constraint In Cooperative Multi-Agent Reinforcement Learning

Jian Hu*, Siyang Jiang*, Haibin Wu, Seth Austin Harding, Shih-Wei Liao

* Denotes equal contributions

FTP
Dataflow Systolic Array Implementations of Exploring Dual-Triangular Structure in QR Decomposition Using High-Level Synthesis

Siyang Jiang, Hsi-Wen Chen, Ming-Syan Chen

Proc. of the IEEE International Conference on Field Programmable Technology (FPT 2021). Accept rate: 22.22%, 32 out of 144