Multi-task Multi-view Learning Research Articles

Incremental Data Stream Classification with Adaptive Multi-Task Multi-View Learning

Incremental Data Stream Classification with Adaptive Multi-Task Multi-View Learning

A fair and interpretable network for clinical risk prediction: a regularized multi-view multi-task learning approach.

In healthcare domain, complication risk profiling which can be seen as multiple clinical risk prediction tasks is challenging due to the complex interaction between heterogeneous clinical entities. With the availability of real-world data, many deep learning methods are proposed for complication risk profiling. However, the existing methods face three open challenges. First, they leverage clinical data from a single view and then lead to suboptimal models. Second, most existing methods lack an effective mechanism to interpret predictions. Third, models learned from clinical data may have inherent pre-existing biases and exhibit discrimination against certain social groups. We then propose a multi-view multi-task network (MuViTaNet) to tackle these issues. MuViTaNet complements patient representation by using a multi-view encoder to exploit more information. Moreover, it uses a multi-task learning to generate more generalized representations using both labeled and unlabeled datasets. Last, a fairness variant (F-MuViTaNet) is proposed to mitigate the unfairness issues and promote healthcare equity. The experiments show that MuViTaNet outperforms existing methods for cardiac complication profiling. Its architecture also provides an effective mechanism for interpreting the predictions, which helps clinicians discover the underlying mechanism triggering the complication onsets. F-MuViTaNet can also effectively mitigate the unfairness with only negligible impact on accuracy.

ASM2TV: An Adaptive Semi-supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition

Many real-world scenarios, such as human activity recognition (HAR) in IoT, can be formalized as a multi-task multi-view learning problem. Each specific task consists of multiple shared feature views collected from multiple sources, either homogeneous or heterogeneous. Common among recent approaches is to employ a typical hard/soft sharing strategy at the initial phase separately for each view across tasks to uncover common knowledge, underlying the assumption that all views are conditionally independent. On the one hand, multiple views across tasks possibly relate to each other under practical situations. On the other hand, supervised methods might be insufficient when labeled data is scarce. To tackle these challenges, we introduce a novel framework ASM2TV for semi-supervised multi-task multi-view learning. We present a new perspective named gating control policy, a learnable task-view-interacted sharing policy that adaptively selects the most desirable candidate shared block for any view across any task, which uncovers more fine-grained task-view-interacted relatedness and improves inference efficiency. Significantly, our proposed gathering consistency adaption procedure takes full advantage of large amounts of unlabeled fragmented time-series, making it a general framework that accommodates a wide range of applications. Experiments on two diverse real-world HAR benchmark datasets collected from various subjects and sources demonstrate our framework's superiority over other state-of-the-arts. Anonymous codes are available at https://github.com/zachstarkk/ASM2TV.

A Multi-View Multi-Task Learning Framework for Multi-Variate Time Series Forecasting

Multi-variate time series (MTS) data is a ubiquitous class of data abstraction in the real world. Any instance of MTS is generated from a hybrid dynamical system and their specific dynamics are usually unknown. The hybrid nature of such a dynamical system is a result of complex external attributes, such as geographic location and time of day, each of which can be categorized into either spatial attributes or temporal attributes. Therefore, there are two fundamental views which can be used to analyze MTS data, namely the spatial view and the temporal view. Moreover, from each of these two views, we can partition the set of data samples of MTS into disjoint forecasting tasks in accordance with their associated attribute values. Then, samples of the same task will manifest similar forthcoming pattern, which is less sophisticated to be predicted in comparison with the original single-view setting. Considering this insight, we propose a novel multi-view multi-task (MVMT) learning framework for MTS forecasting. Instead of being explicitly presented in most scenarios, MVMT information is deeply concealed in the MTS data, which severely hinders the model from capturing it naturally. To this end, we develop two kinds of basic operations, namely task-wise affine transformation and task-wise normalization, respectively. Applying these two operations with prior knowledge on the spatial and temporal view allows the model to adaptively extract MVMT information while predicting. Extensive experiments on three datasets are conducted to illustrate that canonical architectures can be greatly enhanced by the MVMT learning framework in terms of both effectiveness and efficiency. In addition, we design rich case studies to reveal the properties of representations produced at different phases in the entire prediction procedure.

Semisupervised Association Learning Based on Partial Differential Equations for Sparse Representation of Image Class Attributes

Semisupervised learning is an idea that addresses how to use a large number of unlabeled samples and a limited number of labeled samples to learn decision knowledge together. In this paper, we propose a multitask multiview semisupervised learning model based on partial differential equation random field and Hilbert independent standard probability image genus attribute model, i.e., shared semantics. In the framework of the image-like genus attribute model, data from different data sources are generated by their shared hidden space representation. Different from the traditional model, this paper uses the Hilbert independence criterion to inscribe the shared relationship of hidden expressions. Meanwhile, to exploit the correlations between labels in the label space as well, this paper uses the partial differential equation random field to inscribe the correlations between different kinds of labels in the label space and the correlations between hidden features and labels. Using the variational expectation-maximization algorithm, the whole generative process model can be inferred. To verify the effectiveness of the model, two artificial datasets and three real datasets are tested in this paper, and the experimental results verify the effectiveness of the algorithm in the paper. On the one hand, it not only improves the classification accuracy of the multiclassification problem and the multilabel problem; it also outputs the association structure between different kinds of labels and between hidden features and labels.

Continual Multiview Task Learning via Deep Matrix Factorization.

The state-of-the-art multitask multiview (MTMV) learning tackles a scenario where multiple tasks are related to each other via multiple shared feature views. However, in many real-world scenarios where a sequence of the multiview task comes, the higher storage requirement and computational cost of retraining previous tasks with MTMV models have presented a formidable challenge for this lifelong learning scenario. To address this challenge, in this article, we propose a new continual multiview task learning model that integrates deep matrix factorization and sparse subspace learning in a unified framework, which is termed deep continual multiview task learning (DCMvTL). More specifically, as a new multiview task arrives, DCMvTL first adopts a deep matrix factorization technique to capture hidden and hierarchical representations for this new coming multiview task while accumulating the fresh multiview knowledge in a layerwise manner. Then, a sparse subspace learning model is employed for the extracted factors at each layer and further reveals cross-view correlations via a self-expressive constraint. For model optimization, we derive a general multiview learning formulation when a new multiview task comes and apply an alternating minimization strategy to achieve lifelong learning. Extensive experiments on benchmark data sets demonstrate the effectiveness of our proposed DCMvTL model compared with the existing state-of-the-art MTMV and lifelong multiview task learning models.

Multitask Representation Learning With Multiview Graph Convolutional Networks.

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multitask multiview learning in this article. We first explain the feasibility and advantages of multitask multiview learning for these two tasks. Then we propose a novel model named MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multiview graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view the attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network data sets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks.

Predicting microRNA-disease associations from lncRNA-microRNA interactions via Multiview Multitask Learning.

Identifying microRNAs that are associated with different diseases as biomarkers is a problem of great medical significance. Existing computational methods for uncovering such microRNA-diseases associations (MDAs) are mostly developed under the assumption that similar microRNAs tend to associate with similar diseases. Since such an assumption is not always valid, these methods may not always be applicable to all kinds of MDAs. Considering that the relationship between long noncoding RNA (lncRNA) and different diseases and the co-regulation relationships between the biological functions of lncRNA and microRNA have been established, we propose here a multiview multitask method to make use of the known lncRNA-microRNA interaction to predict MDAs on a large scale. The investigation is performed in the absence of complete information of microRNAs and any similarity measurement for it and to the best knowledge, the work represents the first ever attempt to discover MDAs based on lncRNA-microRNA interactions. In this paper, we propose to develop a deep learning model called MVMTMDA that can create a multiview representation of microRNAs. The model is trained based on an end-to-end multitasking approach to machine learning so that, based on it, missing data in the side information can be determined automatically. Experimental results show that the proposed model yields an average area under ROC curve of 0.8410+/-0.018, 0.8512+/-0.012 and 0.8521+/-0.008 when k is set to 2, 5 and 10, respectively. In addition, we also propose here a statistical approach to predicting lncRNA-disease associations based on these associations and the MDA discovered using MVMTMDA. Python code and the datasets used in our studies are made available at https://github.com/yahuang1991polyu/MVMTMDA/.

Predicting Urban Water Quality with Ubiquitous Data - A Data-driven Approach

Urban water quality is of great importance to our daily lives. Prediction of urban water quality help control water pollution and protect human health. However, predicting the urban water quality is a challenging task since the water quality varies in urban spaces non-linearly and depends on multiple factors, such as meteorology, water usage patterns, and land uses. In this article, we forecast the water quality of a station over the next few hours from a data-driven perspective, using the water quality data, and water hydraulic data reported by existing monitor stations and a variety of data sources we observed in the city, such as meteorology, pipe networks, structure of road networks, and point of interests (POIs). First, we identify the influential factors that affect the urban water quality via extensive experiments. Second, we present a multi-task multi-view learning method to fuse those multiple datasets from different domains into an unified learning model. We evaluate our method with real-world datasets, and the extensive experiments verify the advantages of our method over other baselines and demonstrate the effectiveness of our approach.

Retrieving Soil Moisture Over Continental U.S. via Multi-View Multi-Task Learning

Soil moisture (SM) is an essential variable in the hydrological cycle. Quantifying the magnitude of SM is crucial for the climate system. In this letter, we present a new model with multi-view multi-task learning (MVMTL) to estimate SM over continental U.S. Specifically, the multi-view component is used to make full use of spatial and temporal features of each grid cell ( $0.25^{\circ }\times 0.25^{\circ }$ ). Meanwhile, the multi-task component aims to capture the spatial correlations and to perform coestimations between different grid cells in the study area. To evaluate the effectiveness of MVMTL, we compare it with several retrieval methods in terms of the SM product from the European Center for Medium-Range Weather Forecasts Reanalysis Interim (ERA-Interim) and in situ SM measurements. The experimental results show that the MVMTL model can achieve higher performance than the other methods.

Multi-view representation learning in multi-task scene

Over recent decades have witnessed considerable progress in whether multi-task learning or multi-view learning, but the situation that consider both learning scenes simultaneously has received not too much attention. How to utilize multiple views latent representation of each single task to improve each learning task performance is a challenge problem. Based on this, we proposed a novel semi-supervised algorithm, termed as Multi-Task Multi-View learning based on Common and Special Features (MTMVCSF). In general, multi-views are the different aspects of an object and every view includes the underlying common or special information of this object. As a consequence, we will mine multiple views jointly latent factor of each learning task which consists of each view special feature and the common feature of all views. By this way, the original multi-task multi-view data has degenerated into multi-task data, and exploring the correlations among multiple tasks enables to make an improvement on the performance of learning algorithm. Another obvious advantage of this approach is that we get latent representation of the set of unlabeled instances by the constraint of regression task with labeled instances. The performance of classification and semi-supervised clustering task in these latent representations perform obviously better than it in raw data. Furthermore, an anti-noise multi-task multi-view algorithm called AN-MTMVCSF is proposed, which has a strong adaptability to noise labels. The effectiveness of these algorithms is proved by a series of well-designed experiments on both real world and synthetic data.

Multi-view multitask learning for knowledge base relation detection

Relation detection is a key component of knowledge base question answering (KBQA). Existing methods mainly focus on learning semantic relevance between the question and the candidate relation, which is challenging due to the lexical variation (i.e. lexical gaps) especially for relations with few annotated samples. In this paper, we propose to estimate the semantic relevance from both the traditional question–relation view and a novel question–question view, which leverages the similarities among questions corresponding to the same relation. The question–question view can facilitate the learning of few-shot relations, and it supports accessing the annotated samples during inference, thus allowing new annotations to take effect on–the–fly. Moreover, a multi-task learning framework is devised to jointly optimize the models of different views. Experimental results on WebQSP and a Chinese KB relation detection dataset demonstrate the effectiveness and generalization ability of the proposal.

Multi-task and multi-view learning based on particle swarm optimization for short-term traffic forecasting

Spatiotemporal prediction modeling of traffic is an important issue in the field of spatiotemporal data mining. However, it is encountering multiple challenges such as the global spatiotemporal correlation between predictive tasks, balanced between spatiotemporal heterogeneity and the global predictive power of the model, and parameter optimization of prediction models. Most existing short-term traffic prediction methods only emphasize spatiotemporal dependence and heterogeneity, so it is difficult to get satisfactory prediction accuracy. In this paper, spatiotemporal multi-task and multi-view feature learning models based on particle swarm optimization are combined to concurrently address these challenges. First, cross-correlation is used to construct the spatiotemporal proximity view, periodic view and trend view of each road segment to characterize spatiotemporal dependence and heterogeneity. Second, the prediction results of three spatiotemporal views are obtained using a set of kernels, which is further regarded as a high-level heterogeneous semantic feature as the input of the multi-task multi-view feature learning model. Third, additional regularization terms (e.g., group Lasso penalty, graph Laplacian regularization) are utilized to constrain all tasks to select a set of shared features and ensure the relatedness between tasks and consistency between views, so that the predictive model has a good global predictive ability and can capture global spatiotemporal correlation in the road network. Finally, particle swarm optimization is introduced to obtain the optimal parameter set and enhance the training speed of the proposed model. Experimental studies on real vehicular-speed datasets collected on city roads demonstrate that the proposed model significantly outperform the existing nine baseline methods in terms of prediction accuracy. The results suggest that the proposed model merits further attention for other spatiotemporal prediction tasks, such as water quality, crowd flow, owing to the versatility of the modeling process for spatiotemporal data.

A multitask multiview clustering algorithm in heterogeneous situations based on LLE and LE

Multi-view clustering and multi-task clustering attract much attention in recent years. With the development of data mining, a new learning scenario containing the properties of multi-task and multi-view together appears, which called multi-task multi-view learning. Existing multi-task multi-view learning usually applies for classification and considers that all tasks share the same class label sets. Nevertheless, there is not much information about label sets in real world applications and it is difficult for all learning tasks to contain the same label sets. Hence, in order to overcome the two limitations, we propose a multi-task multi-view clustering algorithm in heterogeneous situations based on Locally Linear Embedding (LLE) and Laplacian Eigenmaps (LE) methods (L3E-M2VC). It maps the samples of multiple views from each task to a common view space firstly, then transforms the samples to a discriminative task space secondly, and finally exploits K-Means for clustering. Experiments on several multi-task multi-view data sets are evaluated by RI and CA and the results show that our L3E-M2VC outperforms the other 11 methods, including single-task single-view, multi-view, multi-task, multi-view multi-task algorithms and the varieties of our method.

Infant Brain Development Prediction With Latent Partial Multi-View Representation Learning.

The early postnatal period witnesses rapid and dynamic brain development. However, the relationship between brain anatomical structure and cognitive ability is still unknown. Currently, there is no explicit model to characterize this relationship in the literature. In this paper, we explore this relationship by investigating the mapping between morphological features of the cerebral cortex and cognitive scores. To this end, we introduce a multi-view multi-task learning approach to intuitively explore complementary information from different time-points and handle the missing data issue in longitudinal studies simultaneously. Accordingly, we establish a novel model, latent partial multi-view representation learning. Our approach regards data from different time-points as different views and constructs a latent representation to capture the complementary information from incomplete time-points. The latent representation explores the complementarity across different time-points and improves the accuracy of prediction. The minimization problem is solved by the alternating direction method of multipliers. Experimental results on both synthetic and real data validate the effectiveness of our proposed algorithm.

Multiple-relations-constrained image classification with limited training samples via Pareto optimization

It is a significant challenge to classify images using limited training samples. To this end, we formulate image classification as a multi-task multi-view (MTMV) learning problem and propose a novel Pareto optimization-based method to find the solution. Specifically, we first build a multi-objective multiple-relations-constrained MTMV model called M4 to formulate the procedure of image classification. This model integrates comprehensive relations so that more knowledge can be used when classifying the images. We formulate the model as a multi-objective optimization problem, which addresses conflicts between the inconsistencies of each item in the model and the limitation on the number of relations. To generate the final classifier for each image classification task, an effective Pareto optimization-based algorithm Pareto-M4 is proposed. Pareto-M4 first generates the Pareto-optimal solutions using a novel multi-objective solver MOQPSO and then obtains the final classifiers from all the Pareto-optimal solutions using a recombination procedure. Experiments on various real-world image data sets demonstrate the effectiveness of the proposed image classification method when limited training samples are given.

INFANT BRAIN DEVELOPMENT PREDICTION WITH LATENT PARTIAL MULTI-VIEW REPRESENTATION LEARNING.

The early postnatal period witnesses rapid and dynamic brain development. Understanding the cognitive development patterns can help identify various disorders at early ages of life and is essential for the health and well-being of children. This inspires us to investigate the relation between cognitive ability and the cerebral cortex by exploiting brain images in a longitudinal study. Specifically, we aim to predict the infant brain development status based on the morphological features of the cerebral cortex. For this goal, we introduce a multi-view multi-task learning approach to dexterously explore complementary information from different time points and handle the missing data simultaneously. Specifically, we establish a novel model termed as Latent Partial Multi-view Representation Learning. The approach regards data of different time points as different views, and constructs a latent representation to capture the complementary underlying information from different and even incomplete time points. It uncovers the latent representation that can be jointly used to learn the prediction model. This formulation elegantly explores the complementarity, effectively reduces the redundancy of different views, and improves the accuracy of prediction. The minimization problem is solved by the Alternating Direction Method of Multipliers (ADMM). Experimental results on real data validate the proposed method.

Multi-Task Multi-View Learning Based on Cooperative Multi-Objective Optimization

Traditional multi-task multi-view (MTMV) models work under the single-objective learning framework and cannot incorporate too many regularization terms, which are primarily attributed to the utilization of the conventional numerical optimization methods. To this end, a cooperative multi-objective MTMV (CMO-MTMV) learning method is proposed in this paper. In CMO-MTMV, the MTMV problem is formulated as a multi-objective optimization problem. Compared with the existing single-objective MTMV learning methods, the proposed CMO-MTMV method integrates more relations, including task–task, view–view, instance–instance, and feature–feature relations as multiple objectives. An effective cooperative multi-objective quantum-behaved particle swarm optimization (CMOQPSO) algorithm is further developed to solve the multi-objective optimization problem. The integration of a multi-swarm scheme and a local communication strategy in CMOQPSO renders this algorithm efficient. The experimental results verify the superiority of the proposed CMO-MTMV method compared with the several state-of-the-art machine-learning methods.

An overview of multi-task learning

AbstractAs a promising area in machine learning, multi-task learning (MTL) aims to improve the performance of multiple related learning tasks by leveraging useful information among them. In this paper, we give an overview of MTL by first giving a definition of MTL. Then several different settings of MTL are introduced, including multi-task supervised learning, multi-task unsupervised learning, multi-task semi-supervised learning, multi-task active learning, multi-task reinforcement learning, multi-task online learning and multi-task multi-view learning. For each setting, representative MTL models are presented. In order to speed up the learning process, parallel and distributed MTL models are introduced. Many areas, including computer vision, bioinformatics, health informatics, speech, natural language processing, web applications and ubiquitous computing, use MTL to improve the performance of the applications involved and some representative works are reviewed. Finally, recent theoretical analyses for MTL are presented.

Semantic Feature Learning for Heterogeneous Multitask Classification via Non-Negative Matrix Factorization.

Multitask learning (MTL) aims to learn multiple related tasks simultaneously instead of separately to improve the generalization performance of each task. Most existing MTL methods assumed that the multiple tasks to be learned have the same feature representation. However, this assumption may not hold for many real-world applications. In this paper, we study the problem of MTL with heterogeneous features for each task. To address this problem, we first construct an integrated graph of a set of bipartite graphs to build a connection among different tasks. We then propose a non-negative matrix factorization-based multitask method (MTNMF) to learn a common semantic feature space underlying different heterogeneous feature spaces of each task. Moreover, an improved version of MTNMF (IMTNMF) is proposed, in which we do not need to construct the correlation matrix between input features and class labels, avoiding the information loss. Finally, based on the common semantic features and original heterogeneous features, we model the heterogenous MTL problem as a multitask multiview learning (MTMVL) problem. In this way, a number of existing MTMVL methods can be applied to solve the problem effectively. Extensive experiments on three real-world problems demonstrate the effectiveness of our proposed methods, and the improved version IMTNMF can gain about 2% average accuracy improvement compared with MTNMF.