1.2k citations
- Chinese Academy of SciencesCN254 papers
- University of Chinese Academy of SciencesCN111 papers
- University of Science and Technology of ChinaCN17 papers
- Peking UniversityCN13 papers
- Tencent (China)CN13 papers
- Tsinghua UniversityCN10 papers
- Beihang UniversityCN9 papers
- Microsoft Research Asia (China)CN8 papers
- National University of SingaporeSG8 papers
- Peng Cheng LaboratoryCN8 papers
- Institute of Information EngineeringCN6 papers
- Lenovo (China)CN6 papers
40 papers · 1 filter
BLAST: Balanced Sampling Time Series Corpus for Universal Forecasting Models
Zezhi Shao, Yujie Li, Fei Wang +7
The advent of universal time series forecasting models has revolutionized zero-shot forecasting across diverse domains, yet the critical role of data diversity in training these mo…
Tackling Noisy Clients in Federated Learning with End-to-end Label Correction
Xuefeng Jiang, Sheng Sun, Jia Li +6
Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However,…
Downstream-Pretext Domain Knowledge Traceback for Active Learning
Beichen Zhang, Liang Li, Zheng-Jun Zha +2
Active learning (AL) is designed to construct a high-quality labeled dataset by iteratively selecting the most informative samples. Such sampling heavily relies on data representat…
Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer
Wendong Bi, Xueqi Cheng, Bingbing Xu +3
The data-hungry problem, characterized by insufficiency and low-quality of data, poses obstacles for deep learning models. Transfer learning has been a feasible way to transfer kno…
AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks
Cheng Gong, Ye Lu, Surong Dai +3
Exploring the expected quantizing scheme with suitable mixed-precision policy is the key point to compress deep neural networks (DNNs) in high efficiency and accuracy. This explora…
Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
Lanning Wei, Zhiqiang He, Huan Zhao +1
In recent years, Graph Neural Networks (GNNs) have been popular in the graph classification task. Currently, shallow GNNs are more common due to the well-known over-smoothing probl…