no code implementations • Findings (NAACL) 2022 • Qiqi Wang, Kaiqi Zhao, Robert Amor, Benjamin Liu, Ruofan Wang
We propose a Document-to-Graph Classifier (D2GCLF), which extracts facts as relations between key participants in the law case and represents a legal document with four relation graphs.
no code implementations • 22 Aug 2024 • Yile Chen, Weiming Huang, Kaiqi Zhao, Yue Jiang, Gao Cong
The proliferation of geospatial data in urban and territorial environments has significantly facilitated the development of geospatial artificial intelligence (GeoAI) across various urban applications.
1 code implementation • 17 Mar 2024 • Kaiqi Zhao, Ming Zhao
Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models.
no code implementations • 17 Oct 2023 • Zeyu Zhang, Jiamou Liu, Kaiqi Zhao, Yifei Wang, Pengqian Han, Xianda Zheng, Qiqi Wang, Zijian Zhang
Signed graphs are valuable for modeling complex relationships with positive and negative connections, and Signed Graph Neural Networks (SGNNs) have become crucial tools for their analysis.
no code implementations • 15 Oct 2023 • Zeyu Zhang, Shuyan Wan, Sijie Wang, Xianda Zheng, Xinrui Zhang, Kaiqi Zhao, Jiamou Liu, Dong Hao
Signed Graph Neural Networks (SGNNs) are vital for analyzing complex patterns in real-world signed graphs containing positive and negative links.
no code implementations • 22 Sep 2023 • Kaiqi Zhao, Ming Zhao
Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining.
1 code implementation • 14 Mar 2023 • Kaiqi Zhao, Animesh Jain, Ming Zhao
Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks.
1 code implementation • 14 Mar 2023 • Kaiqi Zhao, Yitao Chen, Ming Zhao
Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning.
1 code implementation • 3 Mar 2023 • Song Yang, Jiamou Liu, Kaiqi Zhao
Instead, we propose a user-agnostic global trajectory flow map and a novel Graph Enhanced Transformer model (GETNext) to better exploit the extensive collaborative signals for a more accurate next POI prediction, and alleviate the cold start problem in the meantime.
no code implementations • 28 Feb 2023 • Yufan Sheng, Xin Cao, Yixiang Fang, Kaiqi Zhao, Jianzhong Qi, Gao Cong, Wenjie Zhang
In this paper, we propose WISK, a learned index for spatial keyword queries, which self-adapts for optimizing querying costs given a query workload.
1 code implementation • 12 Feb 2023 • Yifei Wang, Yupan Wang, Zeyu Zhang, Song Yang, Kaiqi Zhao, Jiamou Liu
To this end, we propose USER, an unsupervised robust version of graph neural networks that is based on structural entropy.
no code implementations • 22 Jan 2022 • Kaiqi Zhao, Yitao Chen, Ming Zhao
The results show that 1) our model compression method can remove up to 99. 36% parameters of WRN-28-10, while preserving a Top-1 accuracy of over 90% on CIFAR-10; 2) our knowledge transfer method enables the compressed models to achieve more than 90% accuracy on CIFAR-10 and retain good accuracy on old categories; 3) it allows the compressed models to converge within real time (three to six minutes) on the edge for incremental learning tasks; 4) it enables the model to classify unseen categories of data (78. 92% Top-1 accuracy) that it is never trained with.
no code implementations • 22 Jan 2022 • Kaiqi Zhao, Animesh Jain, Ming Zhao
To solve this problem, we propose two activation-based pruning methods, Iterative Activation-based Pruning (IAP) and Adaptive Iterative Activation-based Pruning (AIAP).
1 code implementation • 21 Jan 2022 • Kaiqi Zhao, Animesh Jain, Ming Zhao
Pruning is a promising approach to compress complex deep learning models in order to deploy them on resource-constrained edge devices.
1 code implementation • International Conference on Data Mining (ICDM) 2021 • Song Yang, Jiamou Liu, Kaiqi Zhao
We argue that such correlations are universal and play a pivotal role in traffic flow.
no code implementations • 11 Sep 2021 • Song Yang, Jiamou Liu, Kaiqi Zhao
We argue that such correlations are universal and play a pivotal role in traffic flow.
1 code implementation • 2 May 2021 • Xinglong Chang, Katharina Dost, Kaiqi Zhao, Ambra Demontis, Fabio Roli, Gill Dobbie, Jörg Wicker
Applicability Domain defines a domain based on the known compounds and rejects any unknown compound that falls outside the domain.
no code implementations • 18 May 2020 • Yu Gong, Ziwen Jiang, Yufei Feng, Binbin Hu, Kaiqi Zhao, Qingwen Liu, Wenwu Ou
Recommender system (RS) has become a crucial module in most web-scale applications.
no code implementations • 2 Mar 2018 • Yu Gong, Kaiqi Zhao, Kenny Q. Zhu
Verbs play an important role in the understanding of natural language text.