no code implementations • EMNLP (ACL) 2021 • Jin Zhao, Nianwen Xue, Jens Van Gysel, Jinho D. Choi
We present UMR-Writer, a web-based application for annotating Uniform Meaning Representations (UMR), a graph-based, cross-linguistically applicable semantic representation developed recently to support the development of interpretable natural language applications that require deep semantic analysis of texts.
no code implementations • 4 Apr 2024 • Abhishek Duttagupta, Jin Zhao, Shanker Shreejith
Federated Learning (FL) is a distributed learning scheme that enables deep learning to be applied to sensitive data streams and applications in a privacy-preserving manner.
no code implementations • 27 Mar 2024 • Chen Wang, Jin Zhao, Jiaqi Gong
Recent advancements in Large Language Models (LLMs), particularly those built on Transformer architectures, have significantly broadened the scope of natural language processing (NLP) applications, transcending their initial use in chatbot technology.
no code implementations • 25 Mar 2024 • Yuxin Zhang, Haoyu Chen, Zheng Lin, Zhe Chen, Jin Zhao
Clustered federated learning (CFL) is proposed to mitigate the performance deterioration stemming from data heterogeneity in federated learning (FL) by grouping similar clients for cluster-wise model training.
no code implementations • 2 May 2023 • Jin Zhao, Huang Zhao Zhang, Ming-Zhe Chong, Yue-Yi Zhang, Zi-Wen Zhang, Zong-Kun Zhang, Chao-Hai Du, Pu-Kun Liu
In this study, a multifunctional deep neural network is demonstrated to reconstruct target information in a metasurface targets interactive system.
no code implementations • 4 Oct 2022 • Zixiao Wang, Yuluo Guo, Jin Zhao, Yu Zhang, Hui Yu, Xiaofei Liao, Biao Wang, Ting Yu
In this paper, we propose a Graph Inception Diffusion Networks(GIDN) model.
Ranked #1 on Link Property Prediction on ogbl-ddi
no code implementations • 6 Mar 2022 • Jin Zhao, Member, Fangxing Li, Fellow, Srijib Mukherjee, Senior Member, Christopher Sticht
The proposed deep RL method provides real-time computing to support on-line dynamic MMGF scheme, and the scheme handles a long-term resilience enhancement problem using adaptive on-line MMGF to defend changeable conditions.
no code implementations • 16 Sep 2021 • Jin Zhao, Fangxing Li, Xi Chen, Qiuwei Wu
This paper proposes a new deep learning (DL) based model-free robust method for bulk system on-line load restoration with high penetration of wind power.
1 code implementation • ACL 2021 • Jiarui Yao, Haoling Qiu, Jin Zhao, Bonan Min, Nianwen Xue
In this paper, we frame factuality assessment as a modal dependency parsing task that identifies the events and their sources, formally known as conceivers, and then determine the level of certainty that the sources are asserting with respect to the events.
no code implementations • 8 Jul 2019 • Fangqiao Hu, Jin Zhao, Yong Huang, Hui Li
Considering the prior human knowledge that these structures are in conformity to regular spatial layouts in terms of components, a learning-based topology-aware 3D reconstruction method which can obtain high-level structural graph layouts and low-level 3D shapes from images is proposed in this paper.
no code implementations • 9 May 2019 • Xinyu You, Xuanjie Li, Yuedong Xu, Hui Feng, Jin Zhao, Huaicheng Yan
Packet routing is one of the fundamental problems in computer networks in which a router determines the next-hop of each packet in the queue to get it as quickly as possible to its destination.