Binyan Hu, A. K. Qin
Medical image segmentation has been significantly advanced by deep learning (DL) techniques, though the data scarcity inherent in medical applications poses a great challenge to DL-based segmentation methods. 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. Different auxiliary tasks may have different properties and thus can help the target task to different extents. It is desired to leverage their complementary advantages to enhance the overall assistance to the target task. To achieve this, existing methods often adopt a joint training paradigm, which co-solves segmentation and auxiliary tasks by integrating their losses or intermediate gradients. However, direct coupling of losses or intermediate gradients risks undesirable interference because the knowledge acquired from solving each auxiliary task at every training step may not always benefit the target task. To address this issue, we propose a two-stage training approach. In the first stage, the target segmentation task will be independently co-solved with each auxiliary task in both joint training and pre-training modes, with the better model selected via validation performance. In the second stage, the models obtained with respect to each auxiliary task are converted into a single model using an ensemble knowledge distillation method. Our approach allows for making best use of each auxiliary task to create multiple elite segmentation models and then combine them into an even more powerful model. We employed five auxiliary tasks of different proprieties in our approach and applied it to train the U-Net model on an X-ray pneumothorax segmentation dataset. Experimental results demonstrate the superiority of our approach over several existing methods.
Hui Song, A. K. Qin, Chenggang Yan
Real-world electricity consumption prediction may involve different tasks, e.g., prediction for different time steps ahead or different geo-locations. These tasks are often solved independently without utilizing some common problem-solving knowledge that could be extracted and shared among these tasks to augment the performance of solving each task. In this work, we propose a multi-task optimization (MTO) based co-training (MTO-CT) framework, where the models for solving different tasks are co-trained via an MTO paradigm in which solving each task may benefit from the knowledge gained from when solving some other tasks to help its solving process. MTO-CT leverages long short-term memory (LSTM) based model as the predictor where the knowledge is represented via connection weights and biases. In MTO-CT, an inter-task knowledge transfer module is designed to transfer knowledge between different tasks, where the most helpful source tasks are selected by using the probability matching and stochastic universal selection, and evolutionary operations like mutation and crossover are performed for reusing the knowledge from selected source tasks in a target task. We use electricity consumption data from five states in Australia to design two sets of tasks at different scales: a) one-step ahead prediction for each state (five tasks) and b) 6-step, 12-step, 18-step, and 24-step ahead prediction for each state (20 tasks). 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.
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. In the past, traditional machine learning (ML) based detection methods achieved good performance under a centralised computing paradigm, where all data are transmitted to a central server for building ML models therein. Nowadays, deep neural networks based federated learning (FL) has become a mainstream detection approach to enable the model training in a decentralised manner while warranting local data governance. Such neural networks-centred techniques, however, have overshadowed the utility of well-established ML-based detection methods. In this work, we aim to explore the potential of potent conventional ML-based detection models in modern traffic scenarios featured by distributed data. We leverage an elegant but less explored distributed optimisation framework named Network Lasso, with guaranteed global convergence for convex problem formulations, integrate the potent convex ML model with it, and compare it with centralised learning, local learning, and federated learning methods atop a well-known traffic incident detection dataset. Experimental results show that the proposed network lasso-based approach provides a promising alternative to the FL-based approach in data-decentralised traffic scenarios, with a strong convergence guarantee while rekindling the significance of conventional ML-based detection methods.
Boyu Zhang, A. K. Qin, Hong Pan, Timos Sellis
Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. 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. There exist two major issues in this paradigm. Firstly, the validation set may hardly guarantee an unbiased estimate of generalization performance due to potential mismatching with test data. Secondly, training a DNN corresponds to solve a complex optimization problem, which is prone to getting trapped into inferior local optima and thus leads to undesired training results. To address these issues, we propose a novel DNN training framework. It generates multiple pairs of training and validation sets from the gross training set via random splitting, trains a DNN model of a pre-specified structure on each pair while making the useful knowledge (e.g., promising network parameters) obtained from one model training process to be transferred to other model training processes via multi-task optimization, and outputs the best, among all trained models, which has the overall best performance across the validation sets from all pairs. The knowledge transfer mechanism featured in this new framework can not only enhance training effectiveness by helping the model training process to escape from local optima but also improve on generalization performance via implicit regularization imposed on one model training process from other model training processes. We implement the proposed framework, parallelize the implementation on a GPU cluster, and apply it to train several widely used DNN models. Experimental results demonstrate the superiority of the proposed framework over the conventional training paradigm.
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. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MO-MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTMOO research.
Guangliang Gao, Zhifeng Bao, Jie Cao, A. K. Qin, Timos Sellis, Zhiang Wu
Accurate house prediction is of great significance to various real estate stakeholders such as house owners, buyers, investors, and agents. We propose a location-centered prediction framework that differs from existing work in terms of data profiling and prediction model. Regarding data profiling, we define and capture a fine-grained location profile powered by a diverse range of location data sources, such as transportation profile (e.g., distance to nearest train station), education profile (e.g., school zones and ranking), suburb profile based on census data, facility profile (e.g., nearby hospitals, supermarkets). 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. However, such modeling ignores the relatedness between partitions, and for all prediction scenarios, there may not be sufficient training samples per partition for the latter approach. We address this problem by conducting a careful study of exploiting the Multi-Task Learning (MTL) model. Specifically, we map the strategies for splitting the entire house data to the ways the tasks are defined in MTL, and each partition obtained is aligned with a task. Furthermore, we select specific MTL-based methods with different regularization terms to capture and exploit the relatedness between tasks. Based on real-world house transaction data collected in Melbourne, Australia. We design extensive experimental evaluations, and the results indicate a significant superiority of MTL-based methods over state-of-the-art approaches. Meanwhile, we conduct an in-depth analysis on the impact of task definitions and method selections in MTL on the prediction performance, and demonstrate that the impact of task definitions on prediction performance far exceeds that of method selections.
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. It can be viewed as a variant of natural gradient descent, where the challenge of storing and calculating the full FIM is addressed through making use of the regularized FIM and directly finding the gradient update direction via Sherman-Morrison matrix inversion. Additionally, like the popular Adam method, SOFIM uses the first moment of the gradient to address the issue of non-stationary objectives across mini-batches due to heterogeneous data. The utilization of the regularized FIM and Sherman-Morrison matrix inversion leads to the improved convergence rate with the same space and time complexities as stochastic gradient descent (SGD) with momentum. The extensive experiments on training deep learning models using several benchmark image classification datasets demonstrate that the proposed SOFIM outperforms SGD with momentum and several state-of-the-art Newton optimization methods in term of the convergence speed for achieving the pre-specified objectives of training and test losses as well as test accuracy.
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. The relationship between tasks varies between different test problems, which would be helpful to have a comprehensive evaluation of the MFO algorithms. It is expected that the proposed test problems will germinate progress the field of the MTSOO research.
Ziming Liu, Guangyu Gao, A. K. Qin, Jinyang Li
State-of-the-art video action recognition models with complex network architecture have archived significant improvements, but these models heavily depend on large-scale well-labeled datasets. To reduce such dependency, we propose a self-supervised teacher-student architecture, i.e., the Differentiated Teachers Guided self-supervised Network (DTG-Net). In DTG-Net, except for reducing labeled data dependency by self-supervised learning (SSL), pre-trained action related models are used as teacher guidance providing prior knowledge to alleviate the demand for a large number of unlabeled videos in SSL. Specifically, leveraging the years of effort in action-related tasks, e.g., image classification, image-based action recognition, the DTG-Net learns the self-supervised video representation under various teacher guidance, i.e., those well-trained models of action-related tasks. Meanwhile, the DTG-Net is optimized in the way of contrastive self-supervised learning. When two image sequences are randomly sampled from the same video or different videos as the positive or negative pairs, respectively, they are then sent to the teacher and student networks for feature embedding. After that, the contrastive feature consistency is defined between features embedding of each pair, i.e., consistent for positive pair and inconsistent for negative pairs. Meanwhile, to reflect various teacher tasks' different guidance, we also explore different weighted guidance on teacher tasks. 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. Its performance is better than most pre-training methods but also has excellent competitiveness compared to supervised action recognition methods.
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. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial examples created with large and less realistic distortions that are easily identified by human observers. In this paper, we propose a novel approach, called Adversarial Camouflage (\emph{AdvCam}), to craft and camouflage physical-world adversarial examples into natural styles that appear legitimate to human observers. Specifically, \emph{AdvCam} transfers large adversarial perturbations into customized styles, which are then "hidden" on-target object or off-target background. Experimental evaluation shows that, in both digital and physical-world scenarios, adversarial examples crafted by \emph{AdvCam} are well camouflaged and highly stealthy, while remaining effective in fooling state-of-the-art DNN image classifiers. Hence, \emph{AdvCam} is a flexible approach that can help craft stealthy attacks to evaluate the robustness of DNNs. \emph{AdvCam} can also be used to protect private information from being detected by deep learning systems.
Ziqiang Li, Hong Pan, Yaping Zhu, A. K. Qin
Precise segmentation of organs and tumors plays a crucial role in clinical applications. It is a challenging task due to the irregular shapes and various sizes of organs and tumors as well as the significant class imbalance between the anatomy of interest (AOI) and the background region. In addition, in most situation tumors and normal organs often overlap in medical images, but current approaches fail to delineate both tumors and organs accurately. To tackle such challenges, we propose a position-guided deformable UNet, namely PGD-UNet, which exploits the spatial deformation capabilities of deformable convolution to deal with the geometric transformation of both organs and tumors. Position information is explicitly encoded into the network to enhance the capabilities of deformation. Meanwhile, we introduce a new pooling module to preserve position information lost in conventional max-pooling operation. Besides, due to unclear boundaries between different structures as well as the subjectivity of annotations, labels are not necessarily accurate for medical image segmentation tasks. It may cause the overfitting of the trained network due to label noise. To address this issue, we formulate a novel loss function to suppress the influence of potential label noise on the training process. Our method was evaluated on two challenging segmentation tasks and achieved very promising segmentation accuracy in both tasks.
Hui Song, A. K. Qin, Flora D. Salim
Multivariate time series (MTS) prediction plays a key role in many fields such as finance, energy and transport, where each individual time series corresponds to the data collected from a certain data source, so-called channel. A typical pipeline of building an MTS prediction model (PM) consists of selecting a subset of channels among all available ones, extracting features from the selected channels, and building a PM based on the extracted features, where each component involves certain optimization tasks, i.e., selection of channels, feature extraction (FE) methods, and PMs as well as configuration of the selected FE method and PM. Accordingly, pursuing the best prediction performance corresponds to optimizing the pipeline by solving all of its involved optimization problems. This is a non-trivial task due to the vastness of the solution space. Different from most of the existing works which target at optimizing certain components of the pipeline, we propose a novel evolutionary ensemble learning framework to optimize the entire pipeline in a holistic manner. 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). Finally, selective ensemble learning is designed to choose the optimal subset of solutions from the POSs and combine them to yield final prediction by using greedy sequential selection and least square methods. We implement the proposed framework and evaluate our implementation on two real-world applications, i.e., electricity consumption prediction and air quality prediction. The performance comparison with state-of-the-art techniques demonstrates the superiority of the proposed approach.
Binyan Hu, Yu Sun, A. K. Qin
Deep neural networks (DNNs) often rely on massive labelled data for training, which is inaccessible in many applications. Data augmentation (DA) tackles data scarcity by creating new labelled data from available ones. Different DA methods have different mechanisms and therefore using their generated labelled data for DNN training may help improving DNN's generalisation to different degrees. Combining multiple DA methods, namely multi-DA, for DNN training, provides a way to boost generalisation. Among existing multi-DA based DNN training methods, those relying on knowledge distillation (KD) have received great attention. They leverage knowledge transfer to utilise the labelled data sets created by multiple DA methods instead of directly combining them for training DNNs. However, existing KD-based methods can only utilise certain types of DA methods, incapable of utilising the advantages of arbitrary DA methods. We propose a general multi-DA based DNN training framework capable to use arbitrary DA methods. To train a DNN, our framework replicates a certain portion in the latter part of the DNN into multiple copies, leading to multiple DNNs with shared blocks in their former parts and independent blocks in their latter parts. Each of these DNNs is associated with a unique DA and a newly devised loss that allows comprehensively learning from the data generated by all DA methods and the outputs from all DNNs in an online and adaptive way. The overall loss, i.e., the sum of each DNN's loss, is used for training the DNN. Eventually, one of the DNNs with the best validation performance is chosen for inference. We implement the proposed framework by using three distinct DA methods and apply it for training representative DNNs. Experiments on the popular benchmarks of image classification demonstrate the superiority of our method to several existing single-DA and multi-DA based training methods.
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. Currently, mainstream MIS approaches are based on deep neural networks (DNNs), which are typically trained on a dataset with annotations produced by certain medical experts. In the medical domain, the annotations generated by different experts can be inherently distinct due to complexity of medical images and variations in expertise and post-segmentation missions. Consequently, the DNN model trained on the data annotated by some experts may hardly adapt to a new expert. In this work, we evaluate a customised expert-adaptive method, characterised by multi-expert annotation, multi-task DNN-based model training, and lightweight model fine-tuning, to investigate model's adaptivity to a new expert in the situation where the amount and mobility of training images are limited. Experiments conducted on brain MRI segmentation tasks with limited training data demonstrate its effectiveness and the impact of its key parameters.
Qiyuan Zhu, A. K. Qin, Hussein Dia, Adriana-Simona Mihaita, Hanna Grzybowska
Traffic flow forecasting is a crucial task in intelligent transport systems. Deep learning offers an effective solution, capturing complex patterns in time-series traffic flow data to enable the accurate prediction. However, deep learning models are prone to overfitting the intricate details of flow data, leading to poor generalisation. Recent studies suggest that decomposition-based deep ensemble learning methods may address this issue by breaking down a time series into multiple simpler signals, upon which deep learning models are built and ensembled to generate the final prediction. However, few studies have compared the performance of decomposition-based ensemble methods with non-decomposition-based ones which directly utilise raw time-series data. This work compares several decomposition-based and non-decomposition-based deep ensemble learning methods. Experimental results on three traffic datasets demonstrate the superiority of decomposition-based ensemble methods, while also revealing their sensitivity to aggregation strategies and forecasting horizons.
Prabath Abeysekara, Hai Dong, A. K. Qin
Predictive analytics in Mobile Edge Computing (MEC) based Internet of Things (IoT) is becoming a high demand in many real-world applications. A prediction problem in an MEC-based IoT environment typically corresponds to a collection of tasks with each task solved in a specific MEC environment based on the data accumulated locally, which can be regarded as a Multi-task Learning (MTL) problem. However, the heterogeneity of the data (non-IIDness) accumulated across different MEC environments challenges the application of general MTL techniques in such a setting. Federated MTL (FMTL) has recently emerged as an attempt to address this issue. Besides FMTL, there exists another powerful but under-exploited distributed machine learning technique, called Network Lasso (NL), which is inherently related to FMTL but has its own unique features. In this paper, we made an in-depth evaluation and comparison of these two techniques on three distinct IoT datasets representing real-world application scenarios. Experimental results revealed that NL outperformed FMTL in MEC-based IoT environments in terms of both accuracy and computational efficiency.
C. Jacobs, T. Collett, K. Glazebrook, C. McCarthy, A. K. Qin, T. M. C. Abbott, F. B. Abdalla, J. Annis, S. Avila, K. Bechtol, E. Bertin, D. Brooks, E. Buckley-Geer, D. L. Burke, A. Carnero Rosell, M. Carrasco Kind, J. Carretero, L. N. da Costa, C. Davis, J. De Vicente, S. Desai, H. T. Diehl, P. Doel, T. F. Eifler, B. Flaugher, J. Frieman, J. García- Bellido, E. Gaztanaga, D. W. Gerdes, D. A. Goldstein, D. Gruen, R. A. Gruendl, J. Gschwend, G. Gutierrez, W. G. Hartley, D. L. Hollowood, K. Honscheid, B. Hoyle, D. J. James, K. Kuehn, N. Kuropatkin, O. Lahav, T. S. Li, M. Lima, H. Lin, M. A. G. Maia, P. Martini, C. J. Miller, R. Miquel, B. Nord, A. A. Plazas, E. Sanchez, V. Scarpine, M. Schubnell, S. Serrano, I. Sevilla-Noarbe, M. Smith, M. Soares-Santos, F. Sobreira, E. Suchyta, M. E. C. Swanson, G. Tarle, V. Vikram, A. R. Walker, Y. Zhang, J. Zuntz
We search Dark Energy Survey (DES) Year 3 imaging data for galaxy-galaxy strong gravitational lenses using convolutional neural networks. We generate 250,000 simulated lenses at redshifts > 0.8 from which we create a data set for training the neural networks with realistic seeing, sky and shot noise. Using the simulations as a guide, we build a catalogue of 1.1 million DES sources with 1.8 < g - i < 5, 0.6 < g -r < 3, r_mag > 19, g_mag > 20 and i_mag > 18.2. We train two ensembles of neural networks on training sets consisting of simulated lenses, simulated non-lenses, and real sources. We use the neural networks to score images of each of the sources in our catalogue with a value from 0 to 1, and select those with scores greater than a chosen threshold for visual inspection, resulting in a candidate set of 7,301 galaxies. During visual inspection we rate 84 as "probably" or "definitely" lenses. Four of these are previously known lenses or lens candidates. We inspect a further 9,428 candidates with a different score threshold, and identify four new candidates. We present 84 new strong lens candidates, selected after a few hours of visual inspection by astronomers. This catalogue contains a comparable number of high-redshift lenses to that predicted by simulations. Based on simulations we estimate our sample to contain most discoverable lenses in this imaging and at this redshift range.
Mrinmay Sen, A. K. Qin, Krishna Mohan C
In federated learning (FL), the significant communication overhead due to the slow convergence speed of training the global model poses a great challenge. Specifically, a large number of communication rounds are required to achieve the convergence in FL. One potential solution is to employ the Newton-based optimization method for training, known for its quadratic convergence rate. However, the existing Newton-based FL training methods suffer from either memory inefficiency or high computational costs for local clients or the server. To address this issue, we propose an FL with approximated global Hessian (FAGH) method to accelerate FL training. FAGH leverages the first moment of the approximated global Hessian and the first moment of the global gradient to train the global model. By harnessing the approximated global Hessian curvature, FAGH accelerates the convergence of global model training, leading to the reduced number of communication rounds and thus the shortened training time. Experimental results verify FAGH's effectiveness in decreasing the number of communication rounds and the time required to achieve the pre-specified objectives of the global model performance in terms of training and test losses as well as test accuracy. Notably, FAGH outperforms several state-of-the-art FL training methods.
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. In PINNs, the NN acts as the solution approximator for the PDE while the PDE acts as the prior knowledge to guide the NN training, leading to the desired generalization performance of the NN when facing the limited availability of training data. However, training PINNs is a non-trivial task largely due to the complexity of the loss composed of both NN and physical law parts. In this work, we propose a new PINN training framework based on the multi-task optimization (MTO) paradigm. Under this framework, multiple auxiliary tasks are created and solved together with the given (main) task, where the useful knowledge from solving one task is transferred in an adaptive mode to assist in solving some other tasks, aiming to uplift the performance of solving the main task. We implement the proposed framework and apply it to train the PINN for addressing the traffic density prediction problem. Experimental results demonstrate that our proposed training framework leads to significant performance improvement in comparison to the traditional way of training the PINN.
C. Jacobs, T. Collett, K. Glazebrook, E. Buckley-Geer, H. T. Diehl, H. Lin, C. McCarthy, A. K. Qin, C. Odden, M. Caso Escudero, P. Dial, V. J. Yung, S. Gaitsch, A. Pellico, K. A. Lindgren, T. M. C. Abbott, J. Annis, S. Avila, D. Brooks, D. L. Burke, A. Carnero Rosell, M. Carrasco Kind, J. Carretero, L. N. da Costa, J. De Vicente, P. Fosalba, J. Frieman, J. Garcia-Bellido, E. Gaztanaga, D. A. Goldstein, D. Gruen, R. A. Gruendl, J. Gschwend, D. L. Hollowood, K. Honscheid, B. Hoyle, D. J. James, E. Krause, N. Kuropatkin, O. Lahav, M. Lima, M. A. G. Maia, J. L. Marshall, R. Miquel, A. A. Plazas, A. Roodman, E. Sanchez, V. Scarpine, S. Serrano, I. Sevilla-Noarbe, M. Smith, F. Sobreira, E. Suchyta, M. E. C. Swanson, G. Tarle, V. Vikram, A. R. Walker, Y. Zhang
May 25, 2019·astro-ph.GA·PDF We search Dark Energy Survey (DES) Year 3 imaging for galaxy-galaxy strong gravitational lenses using convolutional neural networks, extending previous work with new training sets and covering a wider range of redshifts and colors. We train two neural networks using images of simulated lenses, then use them to score postage stamp images of 7.9 million sources from the Dark Energy Survey chosen to have plausible lens colors based on simulations. We examine 1175 of the highest-scored candidates and identify 152 probable or definite lenses. Examining an additional 20,000 images with lower scores, we identify a further 247 probable or definite candidates. After including 86 candidates discovered in earlier searches using neural networks and 26 candidates discovered through visual inspection of blue-near-red objects in the DES catalog, we present a catalog of 511 lens candidates.