Graph-based Learning Methods Research Articles

Graph-based learning for automated code checking – Exploring the application of graph neural networks for design review

Although automated code checking (ACC) has been a subject of interest for many years, we have not yet seen significant breakthroughs in the field that may lead to the development of generic, comprehensive tools for ACC. Hard-coded rules are the backbone of all emerging platforms for ACC. These rules require a significant amount of engineering, which often requires manual labor; and the resulting rule sets are strict and difficult to scale to other building models. On the other hand, approaches relying purely on classic machine learning (e.g. SVM) are too coarse and unable to accurately express building information. In our hope to come up with a more scalable solution, we investigate here a novel workflow that relies on graph-based learning algorithms instead of processing rule sets. We illustrate the suggested workflow by checking accessibility requirements in residential houses, which we believe is one of the more promising rule sets that can be checked using graph-based learning methods. The high accuracy of the obtained results is encouraging to continue exploring Graph Neural Networks (GNN) for this type of ACC, yet rule-based and classic ML-based approaches show other advantages as well (rigor and speed, respectively). The main contribution of this work is therefore its identification of meaningful limitations and directions for future research, including alternative graph structures and GNN architectures.

Irregularly Sampled Multivariate Time Series Classification: A Graph Learning Approach

To date, graph-based learning methods are proven to be effective for modeling spatial and structural dependencies. However, when applied to IS-MTS, they encounter three major challenges due to the complex data characteristics of IS-MTS: 1)variable time intervals between observations; 2)asynchronous time points across dimensions; 3)a lack of prior knowledge of connectivity structure for message propagation. To fill these gaps, we propose a multivariate temporal graph network to coherently capture structural interactions, learn temporal dependencies, and handle challenging characteristics of IS-MTS data. Specifically, we first build a multivariate interaction module to handle frequent missing values and extract the graph structure relation automatically. Second, we design a novel adjacent graph propagation mechanism to aggregate the neighbor information from multi-step snapshots. Third, we construct a masked temporal-aware attention module to explicitly consider the timestamp context and interval irregularity. Based on an extensive experimental evaluation, we demonstrate the superior performance of the proposed method.

Malware detection with dynamic evolving graph convolutional networks

Malware detection is a vital task for cybersecurity. For malware dynamic behavior, threats come from a small number of Application Programming Interfaces (APIs) embedded in the API sequences, which are easily ignored or obfuscated in the detection process. Prior works proposed graph-based learning methods to solve this problem using API-level behavior relations. However, the malware detection is still challenging, due to the ignore of the temporal correlation between malicious behaviors. In this study, we model the software behaviors with multiscaled API graph sequences to represent API-level behaviors as well as graph-level temporal behavior correlations. We then propose a novel Dynamic Evolving Graph Convolutional Network (DEGCN) model to capture dynamic evolving pattern of both local API-level and global graph-level software behaviors. In particular, we first extract the API-level (node) representations to capture the directed graph representations for each time slot. We then propose a Graph-encoding-based Gate Recurrent Unit (GGRU) network to capture the graph-level evolving features and their evolving status. The graph features of different time slots and different graph scales are concatenated to detect whether the software is benign or malicious. Our evaluation with two public benchmarks reports that DEGCN achieves the best performance compared with state-of-the-art algorithms.

Deep High-Order Tensor Convolutional Sparse Coding for Hyperspectral Image Classification

Most hyperspectral image (HSI) data exist in the form of tensor; the tensor representation preserves the potential spatial–spectral structure information compared with the vector representation, which can help improve the classification performance of HSI. In this article, a deep high-order tensor convolutional sparse coding (CSC) model is proposed, which can be used to train deep high-order filters. Based on the deep high-order tensor CSC model, a deep feature extraction network (DHTCSCNet) is constructed, which is used for feature extraction of HSIs. By combining the spectral–spatial feature and the features extracted by the proposed DHTCSCNet at each layer, a combined feature that incorporates shallow, deep, spectral, and spatial features can be obtained. Then, the graph-based learning (GSL) methods are used to classify the combined feature. Experimental results show that the DHTCSCNet can obtain better classification performance compared with other HSI classification methods.

Hyperspectral Image Classification Via Spectral-Spatial Random Patches Network

Hyperspectral imageclassification is one of the most important steps in HSI analysis and challenging task for hyperspectral data processing, hyperspectral image contains rich spatial and spectral information. The abundance of spectral and spatial information is helpful to improve the classification accuracy. In this article, we propose a spectral-spatial random patches network (SSRPNet), which directly regards the random patches taken from the image as the convolution kernels without any training. The spectral-spatial feature extracted by SSRPNet stacked into a high dimensional vector, which combined with shallow, deep, spectral, spatial feature. Then, the high dimensional vector is fed into graph-based learning methods for classification, which can achieve excellent classification performance by randomly selecting a subset of features from a small sample point to create a graph. Experimental results on three datasets show that the proposed method can achieve satisfactory classification results compared with closely related methods.

Combining Graph-Based Learning With Automated Data Collection for Code Vulnerability Detection

This paper presents FUNDED (Flow-sensitive vUl-Nerability coDE Detection), a novel learning framework for building vulnerability detection models. Funded leverages the advances in graph neural networks (GNNs) to develop a novel graph-based learning method to capture and reason about the program's control, data, and call dependencies. Unlike prior work that treats the program as a sequential sequence or an untyped graph, Funded learns and operates on a graph representation of the program source code, in which individual statements are connected to other statements through relational edges. By capturing the program syntax, semantics and flows, Funded finds better code representation for the downstream software vulnerability detection task. To provide sufficient training data to build an effective deep learning model, we combine probabilistic learning and statistical assessments to automatically gather high-quality training samples from open-source projects. This provides many real-life vulnerable code training samples to complement the limited vulnerable code samples available in standard vulnerability databases. We apply Funded to identify software vulnerabilities at the function level from program source code. We evaluate Funded on large real-world datasets with programs written in C, Java, Swift and Php, and compare it against six state-of-the-art code vulnerability detection models. Experimental results show that Funded significantly outperforms alternative approaches across evaluation settings.

Robust kernelized graph-based learning

The studies of hidden complex structures in data have popularized the use of graph-based learning methods in semi-supervised and unsupervised learning tasks. Kernelized graph-based methods are proven to perform better, but these methods suffer from the issue of appropriate kernel selection. Instead of using multiple views, these methods generally use a single view. But multi-view methods need a proper weight assignment technique to each view in proportion to their contribution to the learning task. To solve this, a novel Self-weighted Multi-view Multiple Kernel Learning (SMVMKL) framework is proposed using multiple kernels on multiple views that automatically assigns appropriate weight to each kernel of each view without introducing an additional parameter. But the real-world data that is either noisy or corrupt with outliers which may effect the performance of the proposed SMVMKL method. To deal with this, a Robust Self-weighted Multi-view Multiple Kernel Learning (RSMVMKL) framework using the l2,1-norm has also been proposed that reduces the effect of outliers present in the data set. Both the proposed methods have been evaluated on multiple benchmark data sets and result in a performance comparable with the other state-of-the-art multi-view methods considered in this paper.

Exploring the Representativity of Art Paintings

Art painting evaluation is sophisticated for a novice with no or limited knowledge on art criticism, and history. In this study, we propose the concept of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">representativity</i> to evaluate paintings instead of using professional concepts, such as genre, media, and style, which may be confusing to non-professionals. We define the concept of representativity to evaluate quantitatively the extent to which a painting can represent the characteristics of an artists creations. We begin by proposing a novel deep representation of art paintings, which is enhanced by style information through a weighted pooling feature fusion module. In contrast to existing feature extraction approaches, the proposed framework embeds painting styles, and authorship information, and learns specific artwork characteristics in a single framework. Subsequently, we propose a graph-based learning method for representativity learning, which considers intra-category, and extra-category information. In view of the significance of historical factors in the art domain, we introduce the creation time of a painting into the learning process. User studies demonstrate our approach helps the public effectively access the creation characteristics of artists through sorting paintings by representativity from highest to lowest.

Affinity matrix with large eigenvalue gap for graph-based subspace clustering and semi-supervised classification

In the graph-based learning method, the data graph or similarity matrix reveals the relationship between data, and reflects similar attributes within a class and differences between classes. Inspired by Davis–Kahan Theorem that the stability of matrix eigenvector space depends on its spectral distance (i.e. its eigenvalue gap), in this paper, we propose a global local affinity matrix model with low rank subspace sparse representation (GLAM-LRSR) based on global information of eigenvalue gap and local distance between samples. This method approximate the similarity matrix with ideally diagonal block structure from the perspective of maximizing the eigenvalue gap, and the local distance between data is utilized as a regular term to prevent the eigenvalue gap from being too large to ensure the efficacy of similarity matrix. We have shown that the combination of subspace (LRSR) partitioning method such as Sparse Subspace Clustering(SSC) and the similarity matrix constructed by GLAM can improve the accuracy of subspace clustering, and that the similarity matrix constructed by GLAM-LRSR can be successfully applied to graph-based semi-supervised classification task. Our experiments on synthetic data as well as the real-world datasets for face clustering, face recovery and motion segmentation have clearly demonstrate the significant advantages of GLAM-LRSR and its effectiveness.

Tensor Graph Convolutional Networks for Multi-Relational and Robust Learning

The era of "data deluge" has sparked renewed interest in graph-based learning methods and their widespread applications ranging from sociology and biology to transportation and communications. In this context of graph-aware methods, the present paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. Key aspects of the novel TGCN architecture are the dynamic adaptation to different relations in the tensor graph via learnable weights, and the consideration of graph-based regularizers to promote smoothness and alleviate over-parameterization. The ultimate goal is to design a powerful learning architecture able to: discover complex and highly nonlinear data associations, combine (and select) multiple types of relations, scale gracefully with the graph size, and remain robust to perturbations on the graph edges. The proposed architecture is relevant not only in applications where the nodes are naturally involved in different relations (e.g., a multi-relational graph capturing family, friendship and work relations in a social network), but also in robust learning setups where the graph entails a certain level of uncertainty, and the different tensor slabs correspond to different versions (realizations) of the nominal graph. Numerical tests showcase that the proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.

Sparse graphs using global and local smoothness constraints

Graph-based learning methods are very useful for many machine learning approaches and classification tasks. Constructing an informative graph is one of the most important steps since a graph can significantly affect the final performance of the learning algorithms. Sparse representation is a useful tool in machine learning and pattern recognition area. Recently, it was shown that sparse graphs (sparse representation based graphs) provide a powerful approach to graph-based semi-supervised classification. In this paper, we introduce a new graph construction method that simultaneously provides a sparse graph and integrates manifold constraints on the sparse coefficients without any prior knowledge on the graph or on its similarity matrix. Furthermore, we propose an efficient solution to the optimization problem. The proposed method imposes that the sparse coding vectors of similar samples should be also similar. Different from existing graph construction methods that are based on the use of explicit constraints or a predefined graph matrix, the proposed smoothness constraints on the graph weights implicitly adapt data to the global structure of the estimated graph. A series of experiments conducted on several public image databases shows that the proposed method can outperform many state-of-the-art methods when applied to the problem of graph-based label propagation.

Solve fraud detection problem by using graph based learning methods

: The credit cards’ fraud transactions detection is the important problem in machine learning field. To detect the credit cards’ fraud transactions help reduce the significant loss of the credit cards’ holders and the banks. To detect the credit cards’ fraud transactions, data scientists normally employ the un-supervised learning techniques and supervised learning technique. In this paper, we employ the graph p-Laplacian based semi-supervised learning methods combined with the under-sampling technique such as Cluster Centroids to solve the credit cards’ fraud transactions detection problem. Experimental results show that that the graph p-Laplacian semi-supervised learning methods outperform the current state of art graph Laplacian based semi-supervised learning method (p=2).

A Graph-Based Reinforcement Learning Method with Converged State Exploration and Exploitation

A Graph-Based Reinforcement Learning Method with Converged State Exploration and Exploitation

On using supervised clustering analysis to improve classification performance

During the past decade, graph-based learning methods have proved to be an effective tool to make full use of both labeled and unlabeled data samples to improve learning performance. These methods try to discover the intrinsic structures and discriminative information embedded in the data, by building one or more graphs to model the relationship among the data samples. Consequently, how to build an effective graph is the core problem. In this paper we introduce a novel graph-based classification method, called Supervised clustering-based Regularized Least Squares Classification (SuperRLSC), in which local and global graphs of the data are built by supervised clustering. The motivation is that supervised clustering may discover more actual data structures compared to unsupervised clustering. In our algorithm, we firstly employ supervised k-means to partition the whole training dataset into several meaningful clusters in order to discover the intrinsic and discriminative structures. We then use the discovered structures to build local and global graphs of the data. The local graph reveals local geometric and discriminative structures, while the global graph reveals global discriminative information. Finally a hybrid local/global graph-based regularization term is embedded into supervised classification (i.e., RLSC in this paper). To validate the effectiveness of our algorithm, a series of experiments are performed on several UCI benchmark datasets. The results show that our algorithm can achieve better or at least comparable performance to the other graph-based algorithms and the traditional state-of-the-art supervised classification methods.

The conjunctive disjunctive graph node kernel for disease gene prioritization

Abstract Disease gene prioritization plays an important role in disclosing the relation between genes and diseases and it has attracted much research. As a consequence, a high number of disease gene prioritization methods have been proposed. Among them, graph-based methods are the most promising paradigms due to their ability to naturally represent many types of relations using a graph representation. One key factor of success of graph-based learning methods is the definition of a proper graph node similarity measure normally measured by graph node kernels. However, most approaches share two common limitations: first, they are based on the diffusion phenomenon which does not effectively exploit the nodes’ context; second, they are not able to process the auxiliary information associated to graph nodes. In this paper, we propose an efficient graph node kernel, based on graph decompositions, that not only is able to effectively take into account nodes’ context, but also to exploit additional information available on graph nodes. The key idea is to learn and generalize from small network fragments present in the neighborhood of genes of interest. An empirical evaluation on several biological databases shows that our proposal achieves state-of-the-art results.

A Three-Layered Graph-Based Learning Approach for Remote Sensing Image Retrieval

With the emergence of huge volumes of high-resolution remote sensing images produced by all sorts of satellites and airborne sensors, processing and analysis of these images require effective retrieval techniques. To alleviate the dramatic variation of the retrieval accuracy among queries caused by the single image feature algorithms, we developed a novel graph-based learning method for effectively retrieving remote sensing images. The method utilizes a three-layer framework that integrates the strengths of query expansion and fusion of holistic and local features. In the first layer, two retrieval image sets are obtained by, respectively, using the retrieval methods based on holistic and local features, and the top-ranked and common images from both of the top candidate lists subsequently form graph anchors. In the second layer, the graph anchors as an expansion query retrieve six image sets from the image database using each individual feature. In the third layer, the images in the six image sets are evaluated for generating positive and negative data, and SimpleMKL is applied to learn suitable query-dependent fusion weights for achieving the final image retrieval result. Extensive experiments were performed on the UC Merced Land Use-Land Cover data set. The source code has been available at our website. Compared with other related methods, the retrieval precision is significantly enhanced without sacrificing the scalability of our approach.

Learning a Nonnegative Sparse Graph for Linear Regression.

Previous graph-based semisupervised learning (G-SSL) methods have the following drawbacks: 1) they usually predefine the graph structure and then use it to perform label prediction, which cannot guarantee an overall optimum and 2) they only focus on the label prediction or the graph structure construction but are not competent in handling new samples. To this end, a novel nonnegative sparse graph (NNSG) learning method was first proposed. Then, both the label prediction and projection learning were integrated into linear regression. Finally, the linear regression and graph structure learning were unified within the same framework to overcome these two drawbacks. Therefore, a novel method, named learning a NNSG for linear regression was presented, in which the linear regression and graph learning were simultaneously performed to guarantee an overall optimum. In the learning process, the label information can be accurately propagated via the graph structure so that the linear regression can learn a discriminative projection to better fit sample labels and accurately classify new samples. An effective algorithm was designed to solve the corresponding optimization problem with fast convergence. Furthermore, NNSG provides a unified perceptiveness for a number of graph-based learning methods and linear regression methods. The experimental results showed that NNSG can obtain very high classification accuracy and greatly outperforms conventional G-SSL methods, especially some conventional graph construction methods.

Laplacian minimax probability machine

In this paper, we propose a Laplacian minimax probability machine, which is a semi-supervised version of minimax probability machine based on the manifold regularization framework. We also show that the proposed method can be kernelized on the basis of a theorem similar to the representer theorem for non-linear cases. Experiments confirm that the proposed methods achieve competitive results, as compared to existing graph-based learning methods such as the Laplacian support vector machine and the Laplacian regularized least square, for publicly available datasets from the UCI machine learning repository.

Fast Semantic Diffusion for Large-Scale Context-Based Image and Video Annotation

Exploring context information for visual recognition has recently received significant research attention. This paper proposes a novel and highly efficient approach, which is named semantic diffusion, to utilize semantic context for large-scale image and video annotation. Starting from the initial annotation of a large number of semantic concepts (categories), obtained by either machine learning or manual tagging, the proposed approach refines the results using a graph diffusion technique, which recovers the consistency and smoothness of the annotations over a semantic graph. Different from the existing graph-based learning methods that model relations among data samples, the semantic graph captures context by treating the concepts as nodes and the concept affinities as the weights of edges. In particular, our approach is capable of simultaneously improving annotation accuracy and adapting the concept affinities to new test data. The adaptation provides a means to handle domain change between training and test data, which often occurs in practice. Extensive experiments are conducted to improve concept annotation results using Flickr images and TV program videos. Results show consistent and significant performance gain (10 +% on both image and video data sets). Source codes of the proposed algorithms are available online.

Interactive image segmentation using probabilistic hypergraphs

This paper introduces a novel interactive framework for segmenting images using probabilistic hypergraphs which model the spatial and appearance relations among image pixels. The probabilistic hypergraph provides us a means to pose image segmentation as a machine learning problem. In particular, we assume that a small set of pixels, which are referred to as seed pixels, are labeled as the object and background. The seed pixels are used to estimate the labels of the unlabeled pixels by learning on a hypergraph via minimizing a quadratic smoothness term formed by a hypergraph Laplacian matrix subject to the known label constraints. We derive a natural probabilistic interpretation of this smoothness term, and provide a detailed discussion on the relation of our method to other hypergraph and graph based learning methods. We also present a front-to-end image segmentation system based on the proposed method, which is shown to achieve promising quantitative and qualitative results on the commonly used GrabCut dataset.