Jing Zhang

Dr. Jing Zhang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
JZJie Zhou
Jie Zhou
QYQian Yu
Qian Yu
CLChuan Luo
Chuan Luo
JZJing Zhang
Jing Zhang
We propose a novel multi-task learning method termed Feature Decomposition Network (FDN). The key idea of the proposed FDN is to reduce the phenomenon of feature redundancy by explicitly decomposing features into task-specific features and task-shared features with carefully designed constraints. Experimental results show that our proposed FDN can outperform the state-of-the-art (SOTA) methods by a noticeable margin on Ali-CCP.

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
CXChao Xue
Chao Xue
DLDi Liang
Di Liang
PWPengfei Wang
Pengfei Wang
JZJing Zhang
Jing Zhang
Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They adopt pre-trained language models (PLMs) to obtain question representations, while PLMs tend to focus on entity information and ignore entity transfer caused by temporal constraints, and finally fail to learn specific temporal representations of entities. (II) They neither emphasize the graph structure between entities nor explicitly model the multi-hop relationship in the graph, which will make it difficult to solve complex multi-hop question answering. To alleviate this problem, we propose a novel Question Calibration and Multi-Hop Modeling (QC-MHM) network. Specifically, We first calibrate the question representation by fusing the question and the time-constrained concepts in KG. Then, we construct the GNN layer to complete multi-hop message passing. Finally, the question representation is combined with the embedding output by the GNN to generate the final prediction. Empirical results verify that the proposed model achieves better performance than the state-of-the-art models in the benchmark dataset. Notably, the Hits@1 and Hits@10 results of QC-MHM on the CronQuestions dataset's complex questions are absolutely improved by 5.1% and 1.2% compared to the best-performing baseline. Moreover, QC-MHM can generate interpretable and trustworthy predictions.

7 September 2022 in Micromachines
Verified
Journal Article
Open access
PDF file
JZJing Zhang
Jing Zhang
DLDong Liu
Dong Liu
WCWeihai Chen
Weihai Chen
ZPZhongcai Pei
Zhongcai Pei
JWJianhua Wang
Jianhua Wang
Brain–machine interfaces (BMIs) have been applied as a pattern recognition system for neuromodulation and neurorehabilitation. Decoding brain signals (e.g., EEG) with high accuracy is a prerequisite to building a reliable and practical BMI. This study presents a deep convolutional neural network (CNN) for EEG-based motor decoding. Both upper-limb and lower-limb motor imagery were detected from this end-to-end learning with four datasets. An average classification accuracy of 93.36 ± 1.68% was yielded on the four datasets. We compared the proposed approach with two other models, i.e., multilayer perceptron and the state-of-the-art framework with common spatial patterns and support vector machine. We observed that the performance of the CNN-based framework was significantly better than the other two models. Feature visualization was further conducted to evaluate the discriminative channels employed for the decoding. We showed the feasibility of the proposed architecture to decode motor imagery from raw EEG data without manually designed features. With the advances in the fields of computer vision and speech recognition, deep learning can not only boost the EEG decoding performance but also help us gain more insight from the data, which may further broaden the knowledge of neuroscience for brain mapping.

29 December 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
JZJing Zhang
Jing Zhang
DLDong Liu
Dong Liu
WCWeihai Chen
Weihai Chen
ZPZhongcai Pei
Zhongcai Pei
JWJianhua Wang
Jianhua Wang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
BTBowen Tang
Bowen Tang
JZJing Zhang
Jing Zhang
LYLong Yan
Long Yan
QYQian Yu
Qian Yu
LSLu Sheng
Lu Sheng
DXDong Xu
Dong Xu
Deep learning models have the ability to extract rich knowledge from large-scale datasets. However, the sharing of data has become increasingly challenging due to concerns regarding data copyright and privacy. Consequently, this hampers the effective transfer of knowledge from existing data to novel downstream tasks and concepts. Zero-shot learning (ZSL) approaches aim to recognize new classes by transferring semantic knowledge learned from base classes. However, traditional generative ZSL methods often require access to real images from base classes and rely on manually annotated attributes, which presents challenges in terms of data restrictions and model scalability. To this end, this paper tackles a challenging and practical problem dubbed as data-free zero-shot learning (DFZSL), where only the CLIP-based base classes data pre-trained classifier is available for zero-shot classification. Specifically, we propose a generic framework for DFZSL, which consists of three main components. Firstly, to recover the virtual features of the base data, we model the CLIP features of base class images as samples from a von Mises-Fisher (vMF) distribution based on the pre-trained classifier. Secondly, we leverage the text features of CLIP as low-cost semantic information and propose a feature-language prompt tuning (FLPT) method to further align the virtual image features and textual features. Thirdly, we train a conditional generative model using the well-aligned virtual image features and corresponding semantic text features, enabling the generation of new classes features and achieve better zero-shot generalization. Our framework has been evaluated on five commonly used benchmarks for generalized ZSL, as well as 11 benchmarks for the base-to-new ZSL. The results demonstrate the superiority and effectiveness of our approach. Our code is available in https://github.com/ylong4/DFZSL.

1 September 2024 in Cognitive Neurodynamics
Verified
Journal Article
Closed access
PDF file
JZJing Zhang
Jing Zhang
CSCheng Shen
Cheng Shen
WCWeihai Chen
Weihai Chen
XMXinzhi Ma
Xinzhi Ma
ZLZilin Liang
Zilin Liang
YZYue Zhang
Yue Zhang