Search Results for author: A. K. Qin

Found 30 papers, 4 papers with code

FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter Update

no code implementations18 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.

Personalized Federated Learning

FAGH: Accelerating Federated Learning with Approximated Global Hessian

no code implementations16 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.

Federated Learning

SOFIM: Stochastic Optimization Using Regularized Fisher Information Matrix

no code implementations5 Mar 2024 Gayathri C, Mrinmay Sen, A. K. Qin, 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.

Image Classification Stochastic Optimization

Decentralised Traffic Incident Detection via Network Lasso

no code implementations28 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.

Federated Learning

Two-Stage Multi-task Self-Supervised Learning for Medical Image Segmentation

no code implementations11 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.

Auxiliary Learning Image Segmentation +5

Deep Learning for Medical Image Segmentation with Imprecise Annotation

no code implementations11 Feb 2024 Binyan Hu, A. K. Qin

Medical image segmentation (MIS) plays an instrumental role in medical image analysis, where considerable efforts have been devoted to automating the process.

Brain Segmentation Image Segmentation +1

One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration

no code implementations26 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.

Model Optimization Point Cloud Registration

Training Physics-Informed Neural Networks via Multi-Task Optimization for Traffic Density Prediction

no code implementations8 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.

TrafFormer: A Transformer Model for Predicting Long-term Traffic

no code implementations24 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.

Traffic Prediction

Deep Edge Intelligence: Architecture, Key Features, Enabling Technologies and Challenges

no code implementations24 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.

Edge-computing

Multi-task Optimization Based Co-training for Electricity Consumption Prediction

no code implementations31 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.

Transfer Learning

Sample-Efficient, Exploration-Based Policy Optimisation for Routing Problems

no code implementations31 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.

Efficient Exploration reinforcement-learning +1

A General Multiple Data Augmentation Based Framework for Training Deep Neural Networks

no code implementations29 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.

Data Augmentation Image Classification +2

ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning

no code implementations29 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.

Learning Enhanced Optimisation for Routing Problems

no code implementations17 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.

BIG-bench Machine Learning

Evolutionary Ensemble Learning for Multivariate Time Series Prediction

no code implementations22 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).

Ensemble Learning Time Series +1

AdvDrop: Adversarial Attack to DNNs by Dropping Information

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.

Adversarial Attack Adversarial Robustness

Multi-Party Dual Learning

no code implementations14 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.

BIG-bench Machine Learning Self-Learning

Towards Explainable Multi-Party Learning: A Contrastive Knowledge Sharing Framework

no code implementations14 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.

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink

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.

Adversarial Attack

Learning Vehicle Routing Problems using Policy Optimisation

no code implementations24 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.

reinforcement-learning Reinforcement Learning (RL)

Learning to Optimise General TSP Instances

no code implementations23 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.

Meta-Learning

Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations

1 code implementation12 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.

General Classification Graph Classification +1

A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization

no code implementations2 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.

Transfer Learning

DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition

no code implementations13 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.

Action Recognition Image Classification +2

Location-Centered House Price Prediction: A Multi-Task Learning Approach

no code implementations7 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.

Multi-Task Learning

Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results

no code implementations12 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.

Evolutionary Multitasking for Multiobjective Continuous Optimization: Benchmark Problems, Performance Metrics and Baseline Results

no code implementations8 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.

Multiobjective Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.