no code implementations • 18 Mar 2024 • Ziru Niu, Hai Dong, A. K. Qin
This approach ensures that a portion of the local model remains personalized, thereby enhancing the model's robustness against biased parameters from other clients.
no code implementations • 16 Mar 2024 • Mrinmay Sen, A. K. Qin, Krishna Mohan C
Specifically, a large number of communication rounds are required to achieve the convergence in FL.
no code implementations • 5 Mar 2024 • Mrinmay Sen, A. K. Qin, Gayathri C, Raghu Kishore N, Yen-Wei Chen, Balasubramanian Raman
This paper introduces a new stochastic optimization method based on the regularized Fisher information matrix (FIM), named SOFIM, which can efficiently utilize the FIM to approximate the Hessian matrix for finding Newton's gradient update in large-scale stochastic optimization of machine learning models.
no code implementations • 28 Feb 2024 • Qiyuan Zhu, A. K. Qin, Prabath Abeysekara, Hussein Dia, Hanna Grzybowska
Traffic incident detection plays a key role in intelligent transportation systems, which has gained great attention in transport engineering.
no code implementations • 11 Feb 2024 • Binyan Hu, A. K. Qin
Self-supervised learning offers a solution by creating auxiliary learning tasks from the available dataset and then leveraging the knowledge acquired from solving auxiliary tasks to help better solve the target segmentation task.
no code implementations • 11 Feb 2024 • Binyan Hu, A. K. Qin
Medical image segmentation (MIS) plays an instrumental role in medical image analysis, where considerable effort has been devoted to automating the process.
no code implementations • 26 Jul 2023 • Yongzhe Yuan, Yue Wu, Maoguo Gong, Qiguang Miao, A. K. Qin
In this paper, we propose an effective inlier estimation method for unsupervised point cloud registration by capturing geometric structure consistency between the source point cloud and its corresponding reference point cloud copy.
no code implementations • 8 Jul 2023 • Bo wang, A. K. Qin, Sajjad Shafiei, Hussein Dia, Adriana-Simona Mihaita, Hanna Grzybowska
Physics-informed neural networks (PINNs) are a newly emerging research frontier in machine learning, which incorporate certain physical laws that govern a given data set, e. g., those described by partial differential equations (PDEs), into the training of the neural network (NN) based on such a data set.
no code implementations • 24 Feb 2023 • David Alexander Tedjopurnomo, Farhana M. Choudhury, A. K. Qin
Traffic prediction is a flourishing research field due to its importance in human mobility in the urban space.
no code implementations • 24 Oct 2022 • Prabath Abeysekara, Hai Dong, A. K. Qin
DEI employs Deep Learning, Artificial Intelligence, Cloud and Edge Computing, 5G/6G networks, Internet of Things, Microservices, etc.
no code implementations • 31 May 2022 • Hui Song, A. K. Qin, Chenggang Yan
The performance of MTO-CT is evaluated on solving each of these two sets of tasks in comparison to solving each task in the set independently without knowledge sharing under the same settings, which demonstrates the superiority of MTO-CT in terms of prediction accuracy.
no code implementations • 31 May 2022 • Nasrin Sultana, Jeffrey Chan, Tabinda Sarwar, A. K. Qin
In this paper, we show that our model can generalise to various route problems, such as the split-delivery VRP (SDVRP), and compare the performance of our method with that of current state-of-the-art approaches.
no code implementations • 29 May 2022 • Binyan Hu, Yu Sun, A. K. Qin
Combining multiple DA methods, namely multi-DA, for DNN training, provides a way to boost generalisation.
no code implementations • 29 Oct 2021 • Maoguo Gong, Yuan Gao, Yue Wu, A. K. Qin
Inspired by the idea of dropout in neural networks, we introduce a network sampling strategy in the multi-party setting, which distributes different subnets of the central model to clients for updating, and the differentiable sampling rates allow each client to extract optimal local architecture from the supernet according to its private data distribution.
no code implementations • 17 Sep 2021 • Nasrin Sultana, Jeffrey Chan, Tabinda Sarwar, Babak Abbasi, A. K. Qin
However, there is still a substantial gap in solution quality between machine learning and operations research algorithms.
no code implementations • 22 Aug 2021 • Hui Song, A. K. Qin, Flora D. Salim
In this framework, a specific pipeline is encoded as a candidate solution and a multi-objective evolutionary algorithm is applied under different population sizes to produce multiple Pareto optimal sets (POSs).
1 code implementation • ICCV 2021 • Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He
Human can easily recognize visual objects with lost information: even losing most details with only contour reserved, e. g. cartoon.
no code implementations • 14 Apr 2021 • Yuan Gao, Jiawei Li, Maoguo Gong, Yu Xie, A. K. Qin
Since the existing naive model parameter averaging method is contradictory to the learning paradigm of neural networks, we simulate the process of human cognition and communication, and analogy multi-party learning as a many-to-one knowledge sharing problem.
no code implementations • 14 Apr 2021 • Maoguo Gong, Yuan Gao, Yu Xie, A. K. Qin, Ke Pan, Yew-Soon Ong
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data.
1 code implementation • CVPR 2021 • Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yun Yang, Yuefeng Chen, Shaokai Ye, Yuan He
Though it is well known that the performance of deep neural networks (DNNs) degrades under certain light conditions, there exists no study on the threats of light beams emitted from some physical source as adversarial attacker on DNNs in a real-world scenario.
no code implementations • 24 Dec 2020 • Nasrin Sultana, Jeffrey Chan, A. K. Qin, Tabinda Sarwar
In our evaluation, we experimentally illustrate that the model produces state-of-the-art performance on variants of Vehicle Routing problems such as Capacitated Vehicle Routing Problem (CVRP), Multiple Routing with Fixed Fleet Problems (MRPFF) and Travelling Salesman problem.
no code implementations • 23 Oct 2020 • Nasrin Sultana, Jeffrey Chan, A. K. Qin, Tabinda Sarwar
In recent years, learning to optimise approaches have shown success in solving TSP problems.
1 code implementation • 12 Oct 2020 • Wenfeng Liu, Maoguo Gong, Zedong Tang, A. K. Qin
To enhance node representativeness, the output of each convolutional layer is concatenated with the output of the previous layer's readout to form a global context-aware node representation.
no code implementations • 2 Jul 2020 • Boyu Zhang, A. K. Qin, Hong Pan, Timos Sellis
The training set is used for training the model while the validation set is used to estimate the generalization performance of the trained model as the training proceeds to avoid over-fitting.
no code implementations • 2 Jul 2020 • Ziqiang Li, Hong Pan, Yaping Zhu, A. K. Qin
Position information is explicitly encoded into the network to enhance the capabilities of deformation.
no code implementations • 13 Jun 2020 • Ziming Liu, Guangyu Gao, A. K. Qin, Jinyang Li
Finally, the DTG-Net is evaluated in two ways: (i) the self-supervised DTG-Net to pre-train the supervised action recognition models with only unlabeled videos; (ii) the supervised DTG-Net to be jointly trained with the supervised action networks in an end-to-end way.
1 code implementation • CVPR 2020 • Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, A. K. Qin, Yun Yang
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples.
no code implementations • 7 Jan 2019 • Guangliang Gao, Zhifeng Bao, Jie Cao, A. K. Qin, Timos Sellis, Fellow, IEEE, Zhiang Wu
Regarding the choice of prediction model, we observe that a variety of approaches either consider the entire house data for modeling, or split the entire data and model each partition independently.
no code implementations • 12 Jun 2017 • Bingshui Da, Yew-Soon Ong, Liang Feng, A. K. Qin, Abhishek Gupta, Zexuan Zhu, Chuan-Kang Ting, Ke Tang, Xin Yao
In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously.
no code implementations • 8 Jun 2017 • Yuan Yuan, Yew-Soon Ong, Liang Feng, A. K. Qin, Abhishek Gupta, Bingshui Da, Qingfu Zhang, Kay Chen Tan, Yaochu Jin, Hisao Ishibuchi
In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously.