Multi-view Learning Framework Research Articles

MEGACare: Knowledge-guided multi-view hypergraph predictive framework for healthcare

Predicting a patient’s future health condition by analyzing their Electronic Health Records (EHRs) is a trending subject in the intelligent medical field, which can help clinicians prescribe safely and effectively, and also make more accurate diagnoses. Benefiting from powerful feature extraction capabilities, graph representation learning can capture complex relationships and achieve promising performance in many clinical prediction tasks. However, existing works either exclusively consider single domain knowledge with an independent task or do not fully capitalize on domain knowledge that can provide more predictive signals in the code encoding stage. Moreover, the heterogeneous and high-dimensional nature of EHR data leads to a deficiency of hardly encoding implicit high-order correlations. To address these limitations, we proposed a knowledge-guided Multi-viEw hyperGrAph predictive framework (MEGACare) for diagnosis prediction and medication recommendation. Our MEGACare leveraged multi-faceted medical knowledge, including ontology structure, code description, and molecular information to enhance medical code presentations. Furthermore, we constructed an EHR hypergraph and a multi-view learning framework to capture the high-order correlation between patient visits and medical codes. Specifically, we propose three perspectives around the pairwise relationship between patient visits and medical codes to comprehensively learn patient representation and enhance the robustness of our framework. We evaluated our MEGACare framework against a set of state-of-the-art methods for two clinical outcome prediction tasks in the public MIMIC-III dataset, and the results showed that our proposed framework was superior to the baseline methods.11Our code and data are released at https://github.com/senticnet/MEGACare.

Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers

As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern recognition tasks. In this complex representation learning problem, three main challenges can be characterized as follows: i) How to learn consistent representations of samples across all views? ii) How to exploit and utilize category correlations of multi-label to guide inference? iii) How to avoid the negative impact resulting from the incompleteness of views or labels? To cope with these problems, we propose a general multi-view multi-label learning framework named label-guided masked view- and category-aware transformers in this paper. First, we design two transformer-style based modules for cross-view features aggregation and multi-label classification, respectively. The former aggregates information from different views in the process of extracting view-specific features, and the latter learns subcategory embedding to improve classification performance. Second, considering the imbalance of expressive power among views, an adaptively weighted view fusion module is proposed to obtain view-consistent embedding features. Third, we impose a label manifold constraint in sample-level representation learning to maximize the utilization of supervised information. Last but not least, all the modules are designed under the premise of incomplete views and labels, which makes our method adaptable to arbitrary multi-view and multi-label data. Extensive experiments on five datasets confirm that our method has clear advantages over other state-of-the-art methods.

Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View

Graph anomaly detection (GAD) is a vital task in graph-based machine learning and has been widely applied in many real-world applications. The primary goal of GAD is to capture anomalous nodes from graph datasets, which evidently deviate from the majority of nodes. Recent methods have paid attention to various scales of contrastive strategies for GAD, i.e., node-subgraph and node-node contrasts. However, they neglect the subgraph-subgraph comparison information which the normal and abnormal subgraph pairs behave differently in terms of embeddings and structures in GAD, resulting in sub-optimal task performance. In this paper, we fulfill the above idea in the proposed multi-view multi-scale contrastive learning framework with subgraph-subgraph contrast for the first practice. To be specific, we regard the original input graph as the first view and generate the second view by graph augmentation with edge modifications. With the guidance of maximizing the similarity of the subgraph pairs, the proposed subgraph-subgraph contrast contributes to more robust subgraph embeddings despite of the structure variation. Moreover, the introduced subgraph-subgraph contrast cooperates well with the widely-adopted node-subgraph and node-node contrastive counterparts for mutual GAD performance promotions. Besides, we also conduct sufficient experiments to investigate the impact of different graph augmentation approaches on detection performance. The comprehensive experimental results well demonstrate the superiority of our method compared with the state-of-the-art approaches and the effectiveness of the multi-view subgraph pair contrastive strategy for the GAD task. The source code is released at https://github.com/FelixDJC/GRADATE.

A multi-view contrastive learning for heterogeneous network embedding

Graph contrastive learning has been developed to learn discriminative node representations on homogeneous graphs. However, it is not clear how to augment the heterogeneous graphs without substantially altering the underlying semantics or how to design appropriate pretext tasks to fully capture the rich semantics preserved in heterogeneous information networks (HINs). Moreover, early investigations demonstrate that contrastive learning suffer from sampling bias, whereas conventional debiasing techniques (e.g., hard negative mining) are empirically shown to be inadequate for graph contrastive learning. How to mitigate the sampling bias on heterogeneous graphs is another important yet neglected problem. To address the aforementioned challenges, we propose a novel multi-view heterogeneous graph contrastive learning framework in this paper. We use metapaths, each of which depicts a complementary element of HINs, as the augmentation to generate multiple subgraphs (i.e., multi-views), and propose a novel pretext task to maximize the coherence between each pair of metapath-induced views. Furthermore, we employ a positive sampling strategy to explicitly select hard positives by jointly considering semantics and structures preserved on each metapath view to alleviate the sampling bias. Extensive experiments demonstrate MCL consistently outperforms state-of-the-art baselines on five real-world benchmark datasets and even its supervised counterparts in some settings.

Robust semi-supervised multi-view graph learning with sharable and individual structure

The construction of a high-quality multi-view consensus graph is key to graph-based semi-supervised multi-view learning (GSSMvL) methods. However, most existing GSSMvL methods explore sample relationships in the original multi-view feature space, which obtains a contaminated graph that cannot reveal the underlying manifold structure of the samples. Moreover, traditional GSSMvL methods fail to explore the diverse structures of multi-view features, which may lose their complementary information and lead to a suboptimal graph. In this paper, we propose a novel unified robust semi-supervised multi-view graph learning framework based on the sharable and individual structure (RSSMvSI), which can eliminate the influence of noise and exploit the knowledge of multi-view data in a reasonable manner. Specifically, we first learn clean data by manipulating sparse noise with l2,1 norm. We then simultaneously explore the sharable and individual self-representation subspace on the learned clean multi-view data. The key point is that noisy data does not participate in subspace learning, which improves the robustness of the proposed method. By constructing the optimal consensus graph with the learned sharable and individual subspace, RSSMvSI can better utilize the complementary information of multi-view data and approximate the manifold structure of samples. To the best of our knowledge, this is the first attempt to learn the self-representation subspace on recovered multi-view clean data. Extensive experiments on various real-world multi-view datasets demonstrate the superiority and robustness against state-of-the-art methods.

B-mode ultrasound based CAD for liver cancers via multi-view privileged information learning

B-mode ultrasound-based computer-aided diagnosis model can help sonologists improve the diagnostic performance for liver cancers, but it generally suffers from the bottleneck due to the limited structure and internal echogenicity information in B-mode ultrasound images. Contrast-enhanced ultrasound images provide additional diagnostic information on dynamic blood perfusion of liver lesions for B-mode ultrasound images with improved diagnostic accuracy. Since transfer learning has indicated its effectiveness in promoting the performance of target computer-aided diagnosis model by transferring knowledge from related imaging modalities, a multi-view privileged information learning framework is proposed to improve the diagnostic accuracy of the single-modal B-mode ultrasound-based diagnosis for liver cancers. This framework can make full use of the shared label information between the paired B-mode ultrasound images and contrast-enhanced ultrasound images to guide knowledge transfer It consists of a novel supervised dual-view deep Boltzmann machine and a new deep multi-view SVM algorithm. The former is developed to implement knowledge transfer from the multi-phase contrast-enhanced ultrasound images to the B-mode ultrasound-based diagnosis model via a feature-level learning using privileged information paradigm, which is totally different from the existing learning using privileged information paradigm that performs knowledge transfer in the classifier. The latter further fuses and enhances feature representation learned from three pre-trained supervised dual-view deep Boltzmann machine networks for the classification task. An experiment is conducted on a bimodal ultrasound liver cancer dataset. The experimental results show that the proposed framework outperforms all the compared algorithms with the best classification accuracy of 88.91 ± 1.52%, sensitivity of 88.31 ± 2.02%, and specificity of 89.50 ± 3.12%. It suggests the effectiveness of our proposed MPIL framework for the BUS-based CAD of liver cancers.

Trust-worth multi-representation learning for audio classification with uncertainty estimation

Multi-view learning has been explored for audio classification tasks, exploiting different representations of audio signals, ranging from MFCC, CQT, to raw signals. The quality of each view may vary for different audio signals, and the appropriate uncertainty quantification for each view has not been fully explored. In this work, we explore a trusted multi-view learning framework for classification tasks in order to fully incorporate different views. Our framework consists of three parallel branches of Transformer architectures (Gammatone spectrogram, log-Mel and CQT) and they are combined using the uncertainty estimation of different branch. In addition to computing the classification probabilities, the uncertainty of each representation can also be obtained using the framework. We firstly calculate the evidence based on feature vectors to obtain the probabilities and the uncertainty of classification problems for Gammatone, log-Mel and CQT branch. By integrating the confidence from each of the different representations using the Dempster–Shafer theory, the classification framework can provide higher accuracy and confidence. To demonstrate the effectiveness of the proposed framework, we conduct the experiments on the GTZAN dataset. The obtained results show that our method can reach the accuracy of 83.0%, which significantly outperforms single representation-based methods while providing uncertainty estimation for different views.

Global–local contrastive multiview representation learning for skeleton-based action recognition

Skeleton-based human action recognition has been drawing more interest recently due to its low sensitivity to appearance changes and the accessibility of more skeleton data. However, the skeletons captured in practice are sensitive to the view of an actor, given the occlusion of different human-body joints and the errors in human joint localization. Each view is noisy and incomplete, but important factors, such as motion and semantics, should be shared between all views in action representation learning. We support the classic hypothesis that a powerful representation is one that models view-invariant factors, and so does unsupervised learning. Therefore, we study this hypothesis under the framework of contrastive multiview learning, where we learn a representation for action recognition that aims to maximize the mutual information between different views of the same action sequence. Apart from that, a global–local contrastive loss is proposed to model the multi-scale co-occurrence relationships in both spatial and temporal domains. Extensive experimental results show that the proposed method significantly boosts the performance of unsupervised skeleton-based human action methods on three challenging benchmarks of PKUMMD, NTU RGB+D 60, and NTU RGB+D 120.

Self-paced Multi-view Learning for CT-based severity assessment of COVID-19

Prior studies for the task of severity assessment of COVID-19 (SA-COVID) usually suffer from domain-specific cognitive deficits. They mainly focus on visual cues based on single cognitive functions but fail to reconcile the valuable information from other alternative views. Inspired by the cognitive process of radiologists, this paper shifts naturally from single-symptom measurements to a multi-view analysis, and proposes a novel Self-paced Multi-view Learning (SPML) framework for automated SA-COVID. Specifically, the proposed SPML framework first comprehensively aggregates multi-view contexts in lung infection with different measure paradigms, i.e., Global Feature Branch, Texture Feature Branch, and Volume Feature Branch. In this way, multiple-perspective clues are taken into account to reflect the most essential pathological manifestation on CT images. To alleviate small-sample learning problems, we also introduce an optimization with self-paced learning strategy to cognitively increase the characterization capabilities of training samples by learning from simple to complex. In contrast to traditional batch-wise learning, a pure self-paced way can further guarantee the efficiency and accuracy of SPML when dealing with small and biased samples. Furthermore, we construct a well-established SA-COVID dataset that contains 300 CT images with fine annotations. Extensive experiments on this dataset demonstrate that SPML consistently outperforms the state-of-the-art baselines. The SA-COVID dataset is publicly released at https://github.com/YishuLiu/SA-COVID.

MOL: Towards accurate weakly supervised remote sensing object detection via Multi-view nOisy Learning

Weakly supervised object detection (WSOD) has become a growing trend in remote sensing images (RSIs) analysis, which aims to train an object detector given only image-level annotations (i.e., categories of existing objects in the given image), reducing the dependency on expensive object-level annotations. However, an object detector trained on such weak annotations is susceptible to the issues of background interference and missing detection due to the complex backgrounds and densely arranged objects of RSIs. In this paper, we develop a novel Multi-view nOisy Learning framework, named MOL, to tackle the abovementioned problems, which consists of two sequential stages: reliable object discovery and progressive object mining. (i) In reliable object discovery, we formulate WSOD as a multiple instance learning problem to discover potential objects in the given image, which process inevitably suffers background interference due to a lack of accurate supervision signal. To this end, we take inspiration from noisy learning theory and propose a temporal consistency-based instance selection strategy for discovering reliable foreground objects, reducing the risk of background interference. (ii) In progressive object mining, we serve the observed reliable objects as the initial pseudo-labels for building an object detector and propose a novel multi-view object mining strategy to progressively mine neglected objects from multiple distinct views, alleviating the missing detection issue. In this way, a well-trained object detector is obtained, which can achieve satisfactory performance in RSIs. Experimental results on two public benchmarks demonstrate that our method outperforms previous state-of-the-art methods by a large margin of 13.97% mAP and 1.69% mAP on NWPU VHR-10.v2 and DIOR, respectively. The code is available at: https://github.com/GC-WSL/MOL.

A Unified Framework for Graph-Based Multi-View Partial Multi-Label Learning

A Unified Framework for Graph-Based Multi-View Partial Multi-Label Learning

DrugAI: a multi-view deep learning model for predicting drug-target activating/inhibiting mechanisms.

Understanding the mechanisms of candidatedrugs play an important role in drug discovery. The activating/inhibiting mechanisms between drugs and targets are major types of mechanisms of drugs. Owing to the complexity of drug-target (DT) mechanisms and data scarcity, modelling this problem based on deep learning methods to accurately predict DT activating/inhibiting mechanisms remains a considerable challenge. Here, by considering network pharmacology, we propose a multi-view deep learning model, DrugAI, which combines four modules, i.e. a graph neural network for drugs, a convolutional neural network for targets, a network embedding module for drugs and targets and a deep neural network for predicting activating/inhibiting mechanisms between drugs and targets. Computational experiments show that DrugAI performs better than state-of-the-art methods and has good robustness and generalization. To demonstrate the reliability of the predictive results of DrugAI, bioassay experiments are conducted to validate two drugs (notopterol and alpha-asarone) predicted to activate TRPV1. Moreover, external validation bears out 61 pairs of mechanism relationships between natural products and their targets predicted by DrugAI based on independent literatures and PubChem bioassays. DrugAI, for the first time, provides a powerful multi-view deep learning framework for robust prediction of DT activating/inhibiting mechanisms.

SMGCL: Semi-supervised Multi-view Graph Contrastive Learning

Graph contrastive learning (GCL), aiming to generate supervision information by transforming the graph data itself, is increasingly becoming a focus of graph research. It has shown promising performance in graph representation learning by extracting global-level abstract features of graphs. Nonetheless, most GCL methods are performed in a completely unsupervised manner and would get unappealing results in balancing the multi-view information of graphs. To alleviate this, we propose a Semi-supervised Multi-view Graph Contrastive Learning (SMGCL) framework for graph classification. The framework can capture the comparative relations between label-independent and label-dependent node (or graph) pairs across different views. In particular, we devise a graph neural network (GNN)-based label augmentation module to exploit the label information and guarantee the discrimination of the learned representations. In addition, a shared decoder module is complemented to extract the underlying determinative relationship between learned representations and graph topology. Experimental results on graph classification tasks demonstrate the superiority of the proposed framework.

ScAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data.

Technological advances have enabled us to profile single-cell multi-omics data from the same cells, providing us with an unprecedented opportunity to understand the cellular phenotype and links to its genotype. The available protocols and multi-omics datasets [including parallel single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) data profiled from the same cell] are growing increasingly. However, such data are highly sparse and tend to have high level of noise, making data analysis challenging. The methods that integrate the multi-omics data can potentially improve the capacity of revealing the cellular heterogeneity. We propose an adaptively weighted multi-view learning (scAWMV) method for the integrative analysis of parallel scRNA-seq and scATAC-seq data profiled from the same cell. scAWMV considers both the difference in importance across different modalities in multi-omics data and the biological connection of the features in the scRNA-seq and scATAC-seq data. It generates biologically meaningful low-dimensional representations for the transcriptomic and epigenomic profiles via unsupervised learning. Application to four real datasets demonstrates that our framework scAWMV is an efficient method to dissect cellular heterogeneity for single-cell multi-omics data. The software and datasets are available at https://github.com/pengchengzeng/scAWMV. Supplementary data are available at Bioinformatics online.

Deep multiview learning to identify imaging-driven subtypes in mild cognitive impairment

BackgroundIn Alzheimer’s Diseases (AD) research, multimodal imaging analysis can unveil complementary information from multiple imaging modalities and further our understanding of the disease. One application is to discover disease subtypes using unsupervised clustering. However, existing clustering methods are often applied to input features directly, and could suffer from the curse of dimensionality with high-dimensional multimodal data. The purpose of our study is to identify multimodal imaging-driven subtypes in Mild Cognitive Impairment (MCI) participants using a multiview learning framework based on Deep Generalized Canonical Correlation Analysis (DGCCA), to learn shared latent representation with low dimensions from 3 neuroimaging modalities.ResultsDGCCA applies non-linear transformation to input views using neural networks and is able to learn correlated embeddings with low dimensions that capture more variance than its linear counterpart, generalized CCA (GCCA). We designed experiments to compare DGCCA embeddings with single modality features and GCCA embeddings by generating 2 subtypes from each feature set using unsupervised clustering. In our validation studies, we found that amyloid PET imaging has the most discriminative features compared with structural MRI and FDG PET which DGCCA learns from but not GCCA. DGCCA subtypes show differential measures in 5 cognitive assessments, 6 brain volume measures, and conversion to AD patterns. In addition, DGCCA MCI subtypes confirmed AD genetic markers with strong signals that existing late MCI group did not identify.ConclusionOverall, DGCCA is able to learn effective low dimensional embeddings from multimodal data by learning non-linear projections. MCI subtypes generated from DGCCA embeddings are different from existing early and late MCI groups and show most similarity with those identified by amyloid PET features. In our validation studies, DGCCA subtypes show distinct patterns in cognitive measures, brain volumes, and are able to identify AD genetic markers. These findings indicate the promise of the imaging-driven subtypes and their power in revealing disease structures beyond early and late stage MCI.

A Multi-View attention-based deep learning framework for malware detection in smart healthcare systems

Recent security attack reports show that the number of malware attacks is gradually growing over the years due to the rapid adoption of smart healthcare systems. The development of a safe and secure smart healthcare system is considered to be important from a security point of view. Malware detection is an essential subsystem in healthcare ecosystems to secure the system from malware attacks. The literature survey shows that malware detection is done using deep learning with either portable executable (PE)-Header or PE-Imports or PE-Image or application programming interface (API) calls. However, each of these feature sets is important in PE files to boost the malware detection rate. This work proposes a Multi-View attention-based deep learning framework for malware detection by considering features of PE-Header, PE-Imports, PE-Image, and API calls. Detailed evaluation and experimental analysis of the proposed method is shown on the malware detection benchmark datasets. The proposed approach performed better than the machine learning-based and non-attention-based approaches with an accuracy of 95% for malware detection using features from PE-Header, PE-Imports, PE-Image, and API calls. In addition, detailed evaluation results are included for image-based malware detection on datasets from Windows and Android operating systems. In the Windows-based dataset, the proposed approach showed an accuracy of 98% and an accuracy of 97% in the Android-based dataset. Also, the proposed approach performed better than the existing malware detection approaches. Experimental results on three malware datasets indicate that the proposed method is robust and generalizable for both Windows and Android-based malware detection in smart healthcare systems.

Robust multi-view learning via adaptive regression

As data collected from different sources have multiple representations, multi-view learning has become an important paradigm of machine learning. To exploit multi-view data, previous works either tackle each view separately or concatenate all views directly, such that the distinctions as well as correlations of different views are often ignored. Furthermore, existing models usually involve intractable parameters that need to be manually determined to balance the contributions of different views, degrading the efficiency and applicability of models. In this paper, a novel multi-view learning framework, namely Robust Multi-view learning via Adaptive Regression (RMAR), is derived to discriminate diverse views in a self-supervised weighting manner without extra parameters. Meanwhile, RMAR coalesces multiple feature projections with adaptive view-wise weights and adopts L2,1-norm regression loss to learn a joint projection subspace compatible across all views, not only increasing the robustness of model but also preserving the consistency and diversity among views. Furthermore, RMAR can be naturally extended for feature selection by imposing L2,1-norm constraint on feature projections. Additionally, an efficient convergent algorithm is developed to solve RMAR. Extensive experiments have been performed to validate the effectiveness of RMAR for classification and feature selection and show its superiority over state-of-the-arts.

Abnormal User Detection via Multiview Graph Clustering in the Mobile e-Commerce Network

In recent years, Internet of Things has not only promoted the continuous development of e-commerce transaction but also brought loop-hole to the fraud gangs who always utilize mobile devices to commit fraud crimes. For example, fraud gangs are usually organized to purchase commodities at low prices in e-commerce promotions. They benefit from the price spread by reselling commodities at high prices. In the past few years, the transaction fraud caused serious financial losses to merchants in e-commerce platform. To detect the fraudulent user and behavior effectively, a multiview graph clustering-based abnormal detection model is developed in this paper. In the proposed model, two fraudulent behavior patterns are proposed by abstracting the e-commerce network as a heterogeneous information graph. On this basis, two user-similarity graphs are reorganized from the heterogeneous graph with the help of different metapaths. Subsequently, in order to capture the corresponding fraudulent behavior patterns, the above two graphs are encoded into user embeddings and assigned to specific clusters in respective views. Finally, the consensus detection result is produced by fusing the complementary information of different views in a joint multiview learning framework. As we know, our work is the first one that uses multiview graph clustering in e-commerce fraud detection, which will provide a new research perspective for fraud detection in e-commerce platform. Extensive experiments are conducted on real and semisynthetic datasets, and the results demonstrate the effectiveness and superiority of the proposed model.

Reciprocal perspective as a super learner improves drug-target interaction prediction (MUSDTI)

The identification of novel drug-target interactions (DTI) is critical to drug discovery and drug repurposing to address contemporary medical and public health challenges presented by emergent diseases. Historically, computational methods have framed DTI prediction as a binary classification problem (indicating whether or not a drug physically interacts with a given protein target); however, framing the problem instead as a regression-based prediction of the physiochemical binding affinity is more meaningful. With growing databases of experimentally derived drug-target interactions (e.g. Davis, Binding-DB, and Kiba), deep learning-based DTI predictors can be effectively leveraged to achieve state-of-the-art (SOTA) performance. In this work, we formulated a DTI competition as part of the coursework for a senior undergraduate machine learning course and challenged students to generate component DTI models that might surpass SOTA models and effectively combine these component models as part of a meta-model using the Reciprocal Perspective (RP) multi-view learning framework. Following 6 weeks of concerted effort, 28 student-produced component deep-learning DTI models were leveraged in this work to produce a new SOTA RP-DTI model, denoted the Meta Undergraduate Student DTI (MUSDTI) model. Through a series of experiments we demonstrate that (1) RP can considerably improve SOTA DTI prediction, (2) our new double-cold experimental design is more appropriate for emergent DTI challenges, (3) that our novel MUSDTI meta-model outperforms SOTA models, (4) that RP can improve upon individual models as an ensembling method, and finally, (5) RP can be utilized for low computation transfer learning. This work introduces a number of important revelations for the field of DTI prediction and sequence-based, pairwise prediction in general.

MDLF: A Multi-View-Based Deep Learning Framework for Individual Trip Destination Prediction in Public Transportation Systems

Understanding and predicting each individual’s real-time travel destination given the origin information in urban public transportation systems is crucial for personalized traveler recommendation, targeted demand management, dynamic traffic operations and so on. Existing methods are often based on modeling the regular travel patterns through analyzing the long-term personal travel information. They are suitable for destination prediction of individual regular trips with regular travel patterns, but may not work well for occasional trips with strong randomness and uncertainty, especially for the individuals with a few historical travel data. In this paper, we focus on more challenging issue about destination prediction of occasional trips. We design a general Multi-View Deep Learning Framework (MDLF) based on the data-driven insight that a location where a user will destine to is not only related to the user’s own travel preference to the location, but also influenced by crowd’s travel preference and the region’s characteristics of the location under certain spatiotemporal contexts. The destination of an individual’s occasional trip can be predicted by combining all these complementary influencing factors. The novelty of MDLF is mainly reflected in two aspects. The first is the effective feature extraction from multiple and complementary views. The second is that a CNN (Recurrent Neural Network) based deep learning component for predicting each occasional trip’s destination by calculating a moving trend score for each possible destination. We evaluate the MDLF based on two real-world smart card datasets collected by AFC (Automatic Fare Collection) Systems. The experimental results demonstrate the superiority of MDLF against other competitors.