no code implementations • COLING 2022 • Yuanzhou Yao, Zhao Zhang, Yongjun Xu, Chao Li
To this end, we propose to solve the FKGC problem with the data augmentation technique.
no code implementations • 2 Apr 2024 • Zhuo Chen, Zhao Zhang, Zixuan Li, Fei Wang, Yutao Zeng, Xiaolong Jin, Yongjun Xu
Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs).
no code implementations • 24 Mar 2024 • Libo Huang, Zhulin An, Yan Zeng, Chuanguang Yang, Xinqiang Yu, Yongjun Xu
Exemplar-Free Class Incremental Learning (efCIL) aims to continuously incorporate the knowledge from new classes while retaining previously learned information, without storing any old-class exemplars (i. e., samples).
no code implementations • 22 Dec 2023 • Tangwen Qian, Yile Chen, Gao Cong, Yongjun Xu, Fei Wang
However, the development of multi-source domain generalization in this task presents two notable issues: (1) negative transfer; (2) inadequate modeling for external factors.
no code implementations • 19 Dec 2023 • Yujie Li, Zezhi Shao, Yongjun Xu, Qiang Qiu, Zhaogang Cao, Fei Wang
Complex spatial dependencies in transportation networks make traffic prediction extremely challenging.
3 code implementations • 9 Oct 2023 • Zezhi Shao, Fei Wang, Yongjun Xu, Wei Wei, Chengqing Yu, Zhao Zhang, Di Yao, Guangyin Jin, Xin Cao, Gao Cong, Christian S. Jensen, Xueqi Cheng
Moreover, based on the proposed BasicTS and rich heterogeneous MTS datasets, we conduct an exhaustive and reproducible performance and efficiency comparison of popular models, providing insights for researchers in selecting and designing MTS forecasting models.
1 code implementation • 28 Sep 2023 • Ruiqi Liu, Boyu Diao, Libo Huang, Zhulin An, Yongjun Xu
In E2Net, we propose Representative Network Distillation to identify the representative core subnet by assessing parameter quantity and output similarity with the working network, distilling analogous subnets within the working network to mitigate reliance on rehearsal buffers and facilitating knowledge transfer across previous tasks.
no code implementations • 7 Aug 2023 • Chengqing Yu, Fei Wang, Zezhi Shao, Tao Sun, Lin Wu, Yongjun Xu
Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making.
no code implementations • 27 Jul 2023 • Zezhi Shao, Fei Wang, Zhao Zhang, Yuchen Fang, Guangyin Jin, Yongjun Xu
Then, we propose a novel Hierarchical U-net TransFormer (HUTFormer) to address the issues of long-term traffic forecasting.
1 code implementation • 24 Jul 2023 • Chuanguang Yang, Zhulin An, Libo Huang, Junyu Bi, Xinqiang Yu, Han Yang, Yongjun Xu
CLIP has become a promising language-supervised visual pre-training framework and achieves excellent performance over a wide range of tasks.
no code implementations • 19 Jun 2023 • Chuanguang Yang, Xinqiang Yu, Zhulin An, Yongjun Xu
Knowledge Distillation (KD) aims to optimize a lightweight network from the perspective of over-parameterized training.
1 code implementation • 7 Jun 2023 • Yuting Zhang, Yiqing Wu, Ran Le, Yongchun Zhu, Fuzhen Zhuang, Ruidong Han, Xiang Li, Wei Lin, Zhulin An, Yongjun Xu
Different from traditional recommendation, takeaway recommendation faces two main challenges: (1) Dual Interaction-Aware Preference Modeling.
1 code implementation • 6 May 2023 • Yiqing Wu, Ruobing Xie, Zhao Zhang, Yongchun Zhu, Fuzhen Zhuang, Jie zhou, Yongjun Xu, Qing He
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.
no code implementations • 20 Apr 2023 • Libo Huang, Yan Zeng, Chuanguang Yang, Zhulin An, Boyu Diao, Yongjun Xu
Most successful CIL methods incrementally train a feature extractor with the aid of stored exemplars, or estimate the feature distribution with the stored prototypes.
1 code implementation • The 31st ACM International Conference on Information and Knowledge Management (CIKM) 2022 • Fuwei Zhang, Zhao Zhang, Xiang Ao, Fuzhen Zhuang, Yongjun Xu, Qing He.
In order to represent the facts happening in a specific time, temporal knowledge graph (TKG) embedding approaches are put forward.
Ranked #2 on Link Prediction on GDELT
no code implementations • 4 Oct 2022 • Renlong Wei, Qing Xue, Shaodan Ma, Yongjun Xu, Li Yan, Xuming Fang
To explore the impact of IRS on the performance of mmWave communication, we investigate a multi-IRS assisted mmWave communication network and formulate a sum rate maximization problem by jointly optimizing the active and passive beamforming and the set of IRSs for assistance.
1 code implementation • 11 Aug 2022 • Chuanguang Yang, Zhulin An, Helong Zhou, Linhang Cai, Xiang Zhi, Jiwen Wu, Yongjun Xu, Qian Zhang
MixSKD mutually distills feature maps and probability distributions between the random pair of original images and their mixup images in a meaningful way.
1 code implementation • 10 Aug 2022 • Zezhi Shao, Zhao Zhang, Fei Wang, Wei Wei, Yongjun Xu
These results suggest that we can design efficient and effective models as long as they solve the indistinguishability of samples, without being limited to STGNNs.
2 code implementations • 23 Jul 2022 • Chuanguang Yang, Zhulin An, Helong Zhou, Fuzhen Zhuang, Yongjun Xu, Qian Zhan
This enables each network to learn extra contrastive knowledge from others, leading to better feature representations, thus improving the performance of visual recognition tasks.
2 code implementations • 18 Jun 2022 • Zezhi Shao, Zhao Zhang, Fei Wang, Yongjun Xu
However, the patterns of time series and the dependencies between them (i. e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data.
Ranked #2 on Traffic Prediction on PEMS-BAY (using extra training data)
1 code implementation • 18 Jun 2022 • Zezhi Shao, Zhao Zhang, Wei Wei, Fei Wang, Yongjun Xu, Xin Cao, Christian S. Jensen
However, intuitively, traffic data encompasses two different kinds of hidden time series signals, namely the diffusion signals and inherent signals.
Ranked #3 on Traffic Prediction on PEMS-BAY
1 code implementation • 7 Jun 2022 • Chuanguang Yang, Zhulin An, Yongjun Xu
This ensures the exact mapping from a high-level spatial location to the specific input image patch.
1 code implementation • CVPR 2022 • Chuanguang Yang, Helong Zhou, Zhulin An, Xue Jiang, Yongjun Xu, Qian Zhang
Current Knowledge Distillation (KD) methods for semantic segmentation often guide the student to mimic the teacher's structured information generated from individual data samples.
1 code implementation • AAAI 2022 • Linhang Cai, Zhulin An, Chuanguang Yang, Yangchun Yan, Yongjun Xu
In detail, the proposed PGMPF selectively suppresses the gradient of those ”unimportant” parameters via a prior gradient mask generated by the pruning criterion during fine-tuning.
no code implementations • 17 Jan 2022 • Libo Huang, Zhulin An, Xiang Zhi, Yongjun Xu
Generative models often incur the catastrophic forgetting problem when they are used to sequentially learning multiple tasks, i. e., lifelong generative learning.
no code implementations • 11 Nov 2021 • Zhao Zhang, Fuzhen Zhuang, HengShu Zhu, Chao Li, Hui Xiong, Qing He, Yongjun Xu
This will lead to low-quality and unreliable representations of KGs.
no code implementations • 9 Nov 2021 • Wangyang Xu, Jiancheng An, Yongjun Xu, Chongwen Huang, Lu Gan, Chau Yuen
To mitigate the effects of shadow fading and obstacle blocking, reconfigurable intelligent surface (RIS) has become a promising technology to improve the signal transmission quality of wireless communications by controlling the reconfigurable passive elements with less hardware cost and lower power consumption.
1 code implementation • 24 Oct 2021 • Xianhua Yu, Dong Li, Yongjun Xu, Ying-Chang Liang
To this end, it is crucial to adjust the phases of reflecting elements of the IRS, and most of the research works focus on how to optimize/quantize the phase for different optimization objectives.
1 code implementation • 7 Sep 2021 • Chuanguang Yang, Zhulin An, Linhang Cai, Yongjun Xu
Each auxiliary branch is guided to learn self-supervision augmented task and distill this distribution from teacher to student.
no code implementations • 31 Aug 2021 • Zezhi Shao, Yongjun Xu, Wei Wei, Fei Wang, Zhao Zhang, Feida Zhu
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph.
1 code implementation • 29 Jul 2021 • Chuanguang Yang, Zhulin An, Linhang Cai, Yongjun Xu
We therefore adopt an alternative self-supervised augmented task to guide the network to learn the joint distribution of the original recognition task and self-supervised auxiliary task.
Ranked #20 on Knowledge Distillation on ImageNet
1 code implementation • 26 Apr 2021 • Chuanguang Yang, Zhulin An, Linhang Cai, Yongjun Xu
We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning.
no code implementations • 6 Nov 2020 • Yangchun Yan, Rongzuo Guo, Chao Li, Kang Yang, Yongjun Xu
However, these methods ignore a small part of weights in the next layer which disappears as the feature map is removed.
no code implementations • 6 Nov 2020 • Linhang Cai, Zhulin An, Yongjun Xu
Filter pruning is widely used to reduce the computation of deep learning, enabling the deployment of Deep Neural Networks (DNNs) in resource-limited devices.
no code implementations • 19 Oct 2020 • Linhang Cai, Zhulin An, Chuanguang Yang, Yongjun Xu
Network pruning is widely used to compress Deep Neural Networks (DNNs).
no code implementations • 23 Jun 2020 • Jianrong Xu, Boyu Diao, Bifeng Cui, Kang Yang, Chao Li, Yongjun Xu
Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow.
1 code implementation • 7 Jun 2020 • Chuanguang Yang, Zhulin An, Yongjun Xu
Previous Online Knowledge Distillation (OKD) often carries out mutually exchanging probability distributions, but neglects the useful representational knowledge.
no code implementations • 31 Jan 2020 • Chuanguang Yang, Zhulin An, Xiaolong Hu, Hui Zhu, Yongjun Xu
Deep convolutional neural networks (CNN) always depend on wider receptive field (RF) and more complex non-linearity to achieve state-of-the-art performance, while suffering the increased difficult to interpret how relevant patches contribute the final prediction.
no code implementations • 19 Jan 2020 • Hui Zhu, Zhulin An, Kaiqiang Xu, Xiaolong Hu, Yongjun Xu
Existing approaches to improve the performances of convolutional neural networks by optimizing the local architectures or deepening the networks tend to increase the size of models significantly.
1 code implementation • Computer Communications 2019 • Jianmin Liu, Qi Wang, ChenTao He, Katia Jaffrès-Runser, Yida Xu, Zhenyu Li, Yongjun Xu
It is difficult for existing routing protocols for Mobile Ad Hoc Networks (MANETs) and Vehicular Ad Hoc Networks (VANETs) to adapt the high dynamics of FANETs.
no code implementations • 20 Nov 2019 • Xiaolong Hu, Zhulin An, Chuanguang Yang, Hui Zhu, Kaiqaing Xu, Yongjun Xu
For VGG16 pre-trained on ImageNet, our method averagely gains 14. 29\% accuracy promotion for two-classes sub-tasks.
no code implementations • 4 Sep 2019 • Hui Zhu, Zhulin An, Chuanguang Yang, Xiaolong Hu, Kaiqiang Xu, Yongjun Xu
In this paper, we propose a method for efficient automatic architecture search which is special to the widths of networks instead of the connections of neural architecture.
1 code implementation • 26 Aug 2019 • Chuanguang Yang, Zhulin An, Hui Zhu, Xiaolong Hu, Kun Zhang, Kaiqiang Xu, Chao Li, Yongjun Xu
We propose a simple yet effective method to reduce the redundancy of DenseNet by substantially decreasing the number of stacked modules by replacing the original bottleneck by our SMG module, which is augmented by local residual.
Ranked #60 on Image Classification on CIFAR-10
no code implementations • 2 Jun 2019 • Chuanguang Yang, Zhulin An, Chao Li, Boyu Diao, Yongjun Xu
In this work, we propose a heuristic genetic algorithm (GA) for pruning convolutional neural networks (CNNs) according to the multi-objective trade-off among error, computation and sparsity.
1 code implementation • 10 May 2019 • Hui Zhu, Zhulin An, Chuanguang Yang, Kaiqiang Xu, Erhu Zhao, Yongjun Xu
Latest algorithms for automatic neural architecture search perform remarkable but are basically directionless in search space and computational expensive in training of every intermediate architecture.