We propose a novel approach to compute the MAXCUT in attributed graphs, i.e., graphs with features associated with nodes and edges. Our approach works well on any kind of graph topology and can find solutions that jointly optimize the MAXCUT along with other objectives. Based on the obtained MAXCUT partition, we implement a hierarchical graph pooling layer for Graph Neural Networks, which is sparse, trainable end-to-end, and particularly suitable for downstream tasks on heterophilic graphs.

We address the problem of uncertainty quantification in time series forecasting by exploiting observations at correlated sequences. Relational deep learning methods leveraging graph representations are among the most effective tools for obtaining point estimates from spatiotemporal data and correlated time series. However, the problem of exploiting relational structures to estimate the uncertainty of such predictions has been largely overlooked in the same context. To this end, we propose a novel distribution-free approach based on the conformal prediction framework and quantile regression. Despite the recent applications of conformal prediction to sequential data, existing methods operate independently on each target time series and do not account for relationships among them when constructing the prediction interval. We fill this void by introducing a novel conformal prediction method based on graph deep learning operators. Our approach, named Conformal Relational Prediction (CoRel), does not require the relational structure (graph) to be known a priori and can be applied on top of any pre-trained predictor. Additionally, CoRel includes an adaptive component to handle non-exchangeable data and changes in the input time series. Our approach provides accurate coverage and achieves state-of-the-art uncertainty quantification in relevant benchmarks.

Given a set of synchronous time series, each associated with a sensor-point in space and characterized by inter-series relationships, the problem of spatiotemporal forecasting consists of predicting future observations for each point. Spatiotemporal graph neural networks achieve striking results by representing the relationships across time series as a graph. Nonetheless, most existing methods rely on the often unrealistic assumption that inputs are always available and fail to capture hidden spatiotemporal dynamics when part of the data is missing. In this work, we tackle this problem through hierarchical spatiotemporal downsampling. The input time series are progressively coarsened over time and space, obtaining a pool of representations that capture heterogeneous temporal and spatial dynamics. Conditioned on observations and missing data patterns, such representations are combined by an interpretable attention mechanism to generate the forecasts. Our approach outperforms state-of-the-art methods on synthetic and real-world benchmarks under different missing data distributions, particularly in the presence of contiguous blocks of missing values.

Many recent works in the field of graph machine learning have introduced pooling operators to reduce the size of graphs. In this article, we present an operational framework to unify this vast and diverse literature by describing pooling operators as the combination of three functions: selection, reduction, and connection (SRC). We then introduce a taxonomy of pooling operators, based on some of their key characteristics and implementation differences under the SRC framework. Finally, we propose three criteria to evaluate the performance of pooling operators and use them to investigate the behavior of different operators on a variety of tasks.

This article presents a novel probabilistic forecasting method called ensemble conformalized quantile regression (EnCQR). EnCQR constructs distribution-free and approximately marginally valid prediction intervals (PIs), which are suitable for nonstationary and heteroscedastic time series data. EnCQR can be applied on top of a generic forecasting model, including deep learning architectures. EnCQR exploits a bootstrap ensemble estimator, which enables the use of conformal predictors for time series by removing the requirement of data exchangeability. The ensemble learners are implemented as generic machine learning algorithms performing quantile regression (QR), which allow the length of the PIs to adapt to local variability in the data. In the experiments, we predict time series characterized by a different amount of heteroscedasticity. The results demonstrate that EnCQR outperforms models based only on QR or conformal prediction (CP), and it provides sharper, more informative, and valid PIs.

Image translation with convolutional autoencoders has recently been used as an approach to multimodal change detection (CD) in bitemporal satellite images. A main challenge is the alignment of the code spaces by reducing the contribution of change pixels to the learning of the translation function. Many existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. We propose to extract relational pixel information captured by domain-specific affinity matrices at the input and use this to enforce alignment of the code spaces and reduce the impact of change pixels on the learning objective. A change prior is derived in an unsupervised fashion from pixel pair affinities that are comparable across domains. To achieve code space alignment, we enforce pixels with similar affinity relations in the input domains to be correlated also in code space. We demonstrate the utility of this procedure in combination with cycle consistency. The proposed approach is compared with the state-of-the-art machine learning and deep learning algorithms. Experiments conducted on four real and representative datasets show the effectiveness of our methodology.

Neural forecasting of spatiotemporal time series drives both research and industrial innovation in several relevant application domains. Graph neural networks (GNNs) are often the core component of the forecasting architecture. However, in most spatiotemporal GNNs, the computational complexity scales up to a quadratic factor with the length of the sequence times the number of links in the graph, hence hindering the application of these models to large graphs and long temporal sequences. While methods to improve scalability have been proposed in the context of static graphs, few research efforts have been devoted to the spatiotemporal case. To fill this gap, we propose a scalable architecture that exploits an efficient encoding of both temporal and spatial dynamics. In particular, we use a randomized recurrent neural network to embed the history of the input time series into high-dimensional state representations encompassing multi-scale temporal dynamics. Such representations are then propagated along the spatial dimension using different powers of the graph adjacency matrix to generate node embeddings characterized by a rich pool of spatiotemporal features. The resulting node embeddings can be efficiently pre-computed in an unsupervised manner, before being fed to a feed-forward decoder that learns to map the multi-scale spatiotemporal representations to predictions. The training procedure can then be parallelized node-wise by sampling the node embeddings without breaking any dependency, thus enabling scalability to large networks. Empirical results on relevant datasets show that our approach achieves results competitive with the state of the art, while dramatically reducing the computational burden.

Subgraph-enhanced graph neural networks (SGNN) can increase the expressive power of the standard message-passing framework.This model family represents each graph as a collection of subgraphs, generally extracted by random sampling or with hand-crafted heuristics.Our key observation is that by selecting "meaningful" subgraphs, besides improving the expressivity of a GNN, it is also possible to obtain interpretable results.For this purpose, we introduce a novel framework that jointly predicts the class of the graph and a set of explanatory sparse subgraphs, which can be analyzed to understand the decision process of the classifier.The subgraphs produced by our framework allow to achieve comparable performance in terms of accuracy, with the additional benefit of providing explanations.

Recently proposed Graph Neural Networks (GNNs) for vertex clustering are trained with an unsupervised minimum cut objective, approximated by a Spectral Clustering (SC) relaxation. However, the SC relaxation is loose and, while it offers a closed-form solution, it also yields overly smooth cluster assignments that poorly separate the vertices. In this paper, we propose a GNN model that computes cluster assignments by optimizing a tighter relaxation of the minimum cut based on graph total variation (GTV). The cluster assignments can be used directly to perform vertex clustering or to implement graph pooling in a graph classification framework. Our model consists of two core components: i) a message-passing layer that minimizes the $\ell_1$ distance in the features of adjacent vertices, which is key to achieving sharp transitions between clusters; ii) an unsupervised loss function that minimizes the GTV of the cluster assignments while ensuring balanced partitions. Experimental results show that our model outperforms other GNNs for vertex clustering and graph classification.

In Graph Neural Networks (GNNs), hierarchical pooling operators generate local summaries of the data by coarsening the graph structure and the vertex features. Considerable attention has been devoted to analyzing the expressive power of message-passing (MP) layers in GNNs, while a study on how graph pooling affects the expressiveness of a GNN is still lacking. Additionally, despite the recent advances in the design of pooling operators, there is not a principled criterion to compare them. In this work, we derive sufficient conditions for a pooling operator to fully preserve the expressive power of the MP layers before it. These conditions serve as a universal and theoretically-grounded criterion for choosing among existing pooling operators or designing new ones. Based on our theoretical findings, we analyze several existing pooling operators and identify those that fail to satisfy the expressiveness conditions. Finally, we introduce an experimental setup to verify empirically the expressive power of a GNN equipped with pooling layers, in terms of its capability to perform a graph isomorphism test.

Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired by the auto-regressive moving average (ARMA) filter that, compared to polynomial ones, provides a more flexible frequency response, is more robust to noise, and better captures the global graph structure. We propose a graph neural network implementation of the ARMA filter with a recursive and distributed formulation, obtaining a convolutional layer that is efficient to train, localized in the node space, and can be transferred to new graphs at test time. We perform a spectral analysis to study the filtering effect of the proposed ARMA layer and report experiments on four downstream tasks: semi-supervised node classification, graph signal classification, graph classification, and graph regression. Results show that the proposed ARMA layer brings significant improvements over graph neural networks based on polynomial filters.

In this article, we explore the possibility of detecting polar lows in C-band synthetic aperture radar (SAR) images by means of deep learning. Specifically, we introduce a novel dataset consisting of Sentinel-1 images divided into two classes, representing the presence and absence of a maritime mesocyclone, respectively. The dataset is constructed using the ECMWF reanalysis version 5 (ERA5) dataset as baseline and it consists of 2004 annotated images. To our knowledge, this is the first dataset of its kind to be publicly released. The dataset is used to train a deep learning model to classify the labeled images. Evaluated on an independent test set, the model yields an$F1$score of 0.95, indicating that polar lows can be consistently detected from SAR images. Interpretability techniques applied to the deep learning model reveal that atmospheric fronts and cyclonic eyes are key features in the classification. Moreover, experimental results show that the model is accurate even if: 1) such features are significantly cropped due to the limited swath width of the SAR; 2) the features are partly covered by sea ice; and 3) land is covering significant parts of the images. By evaluating the model performance on multiple input image resolutions (pixel sizes of 500 m, 1 km, and 2 km), it is found that higher resolution yield the best performance. This emphasizes the potential of using high-resolution sensors like SAR for detecting polar lows, as compared to conventionally used sensors such as scatterometers.

Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supervised information of the change areas, which, however, is not always available. A main challenge in the unsupervised problem setting is to avoid that change pixels affect the learning of the translation function. We propose two new network architectures trained with loss functions weighted by priors that reduce the impact of change pixels on the learning objective. The change prior is derived in an unsupervised fashion from relational pixel information captured by domain-specific affinity matrices. Specifically, we use the vertex degrees associated with an absolute affinity difference matrix and demonstrate their utility in combination with cycle consistency and adversarial training. The proposed neural networks are compared with the state-of-the-art algorithms. Experiments conducted on three real data sets show the effectiveness of our methodology.

In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed offline in a preprocessing stage. NDP consists of three steps. First, a node decimation procedure selects the nodes belonging to one side of the partition identified by a spectral algorithm that approximates the MAXCUT solution. Afterward, the selected nodes are connected with Kron reduction to form the coarsened graph. Finally, since the resulting graph is very dense, we apply a sparsification procedure that prunes the adjacency matrix of the coarsened graph to reduce the computational cost in the GNN. Notably, we show that it is possible to remove many edges without significantly altering the graph structure. Experimental results show that NDP is more efficient compared to state-of-the-art graph pooling operators while reaching, at the same time, competitive performance on a significant variety of graph classification tasks.

Deep learning for graphs encompasses all those neural models endowed with multiple layers of computation operating on data represented as graphs.The most common building blocks of these models are graph encoding layers, which compute a vector embedding for each node in a graph using message-passing operators.In this paper, we provide an overview of the key concepts in the field, point towards open questions, and frame the contributions of the ESANN 2021 special session into the broader context of deep learning for graphs.

The time series cluster kernel (TCK) provides a powerful tool for analysing multivariate time series subject to missing data. TCK is designed using an ensemble learning approach in which Bayesian mixture models form the base models. Because of the Bayesian approach, TCK can naturally deal with missing values without resorting to imputation and the ensemble strategy ensures robustness to hyperparameters, making it particularly well suited for unsupervised learning. However, TCK assumes missing at random and that the underlying missingness mechanism is ignorable, i.e. uninformative, an assumption that does not hold in many real-world applications, such as e.g. medicine. To overcome this limitation, we present a kernel capable of exploiting the potentially rich information in the missing values and patterns, as well as the information from the observed data. In our approach, we create a representation of the missing pattern, which is incorporated into mixed mode mixture models in such a way that the information provided by the missing patterns is effectively exploited. Moreover, we also propose a semi-supervised kernel, capable of taking advantage of incomplete label information to learn more accurate similarities. Experiments on benchmark data, as well as a real-world case study of patients described by longitudinal electronic health record data who potentially suffer from hospital-acquired infections, demonstrate the effectiveness of the proposed methods.

Classification of multivariate time series (MTS) has been tackled with a large variety of methodologies and applied to a wide range of scenarios. Reservoir computing (RC) provides efficient tools to generate a vectorial, fixed-size representation of the MTS that can be further processed by standard classifiers. Despite their unrivaled training speed, MTS classifiers based on a standard RC architecture fail to achieve the same accuracy of fully trainable neural networks. In this article, we introduce the reservoir model space, an unsupervised approach based on RC to learn vectorial representations of MTS. Each MTS is encoded within the parameters of a linear model trained to predict a low-dimensional embedding of the reservoir dynamics. Compared with other RC methods, our model space yields better representations and attains comparable computational performance due to an intermediate dimensionality reduction procedure. As a second contribution, we propose a modular RC framework for MTS classification, with an associated open-source Python library. The framework provides different modules to seamlessly implement advanced RC architectures. The architectures are compared with other MTS classifiers, including deep learning models and time series kernels. Results obtained on the benchmark and real-world MTS data sets show that RC classifiers are dramatically faster and, when implemented using our proposed representation, also achieve superior classification accuracy.

Spectral clustering (SC) is a popular clustering technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging to the same cluster. However, the eigendecomposition of the Laplacian is expensive and, since clustering results are graph-specific, pooling methods based on SC must perform a new optimization for each new sample. In this paper, we propose a graph clustering approach that addresses these limitations of SC. We formulate a continuous relaxation of the normalized minCUT problem and train a GNN to compute cluster assignments that minimize this objective. Our GNN-based implementation is differentiable, does not require to compute the spectral decomposition, and learns a clustering function that can be quickly evaluated on out-of-sample graphs. From the proposed clustering method, we design a graph pooling operator that overcomes some important limitations of state-of-the-art graph pooling techniques and achieves the best performance in several supervised and unsupervised tasks.

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning, this line of research is in its infancy, and how to design and optimize suitable loss functions to train deep neural networks for clustering is still an open question. Our contribution to this emerging field is a new deep clustering network that leverages the discriminative power of information-theoretic divergence measures, which have been shown to be effective in traditional clustering. We propose a novel loss function that incorporates geometric regularization constraints, thus avoiding degenerate structures of the resulting clustering partition. Experiments on synthetic benchmarks and real datasets show that the proposed network achieves competitive performance with respect to other state-of-the-art methods, scales well to large datasets, and does not require pre-training steps.

Noisy labeled data represent a rich source of information that often are easily accessible and cheap to obtain, but label noise might also have many negative consequences if not accounted for. How to fully utilize noisy labels has been studied extensively within the framework of standard supervised machine learning over a period of several decades. However, very little research has been conducted on solving the challenge posed by noisy labels in non-standard settings. This includes situations where only a fraction of the samples are labeled (semi-supervised) and each high-dimensional sample is associated with multiple labels. In this work, we present a novel semi-supervised and multi-label dimensionality reduction method that effectively utilizes information from both noisy multi-labels and unlabeled data. With the proposed Noisy multi-label semi-supervised dimensionality reduction (NMLSDR) method, the noisy multi-labels are denoised and unlabeled data are labeled simultaneously via a specially designed label propagation algorithm. NMLSDR then learns a projection matrix for reducing the dimensionality by maximizing the dependence between the enlarged and denoised multi-label space and the features in the projected space. Extensive experiments on synthetic data, benchmark datasets, as well as a real-world case study, demonstrate the effectiveness of the proposed algorithm and show that it outperforms state-of-the-art multi-label feature extraction algorithms.

Change detection (CD) in heterogeneous multitemporal satellite images is an emerging and challenging topic in remote sensing. In particular, one of the main challenges is to tackle the problem in an unsupervised manner. In this paper, we propose an unsupervised framework for bitemporal heterogeneous CD based on the comparison of affinity matrices and image regression. First, our method quantifies the similarity of affinity matrices computed from colocated image patches in the two images. This is done to automatically identify pixels that are likely to be unchanged. With the identified pixels as pseudotraining data, we learn a transformation to map the first image to the domain of the other image and vice versa. Four regression methods are selected to carry out the transformation: Gaussian process regression, support vector regression, random forest regression (RFR), and a recently proposed kernel regression method called homogeneous pixel transformation. To evaluate the potentials and limitations of our framework and also the benefits and disadvantages of each regression method, we perform experiments on two real data sets. The results indicate that the comparison of the affinity matrices can already be considered a CD method by itself. However, image regression is shown to improve the results obtained by the previous step alone and produces accurate CD maps despite of the heterogeneity of the multitemporal input data. Notably, the RFR approach excels by achieving similar accuracy as the other methods, but with a significantly lower computational cost and with fast and robust tuning of hyperparameters.

We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF). Atrial fibrillation is the most common type of arrhythmia, but in many cases PAF episodes are asymptomatic. Therefore, in order to help diagnosing PAF, it is important to design procedures for detecting and, more importantly, predicting PAF episodes. We propose a method for predicting PAF events whose first step consists of a feature extraction procedure that represents each ECG as a multi-variate time series. Successively, we design a classification framework based on kernel similarities for multi-variate time series, capable of handling missing data. We consider different approaches to perform classification in the original space of the multi-variate time series and in an embedding space, defined by the kernel similarity measure. We achieve a classification accuracy comparable with state of the art methods, with the additional advantage of detecting the PAF onset up to 15 minutes in advance.

In this paper, we elaborate over the well-known interpretability issue in echo-state networks (ESNs). The idea is to investigate the dynamics of reservoir neurons with time-series analysis techniques developed in complex systems research. Notably, we analyze time series of neuron activations with recurrence plots (RPs) and recurrence quantification analysis (RQA), which permit to visualize and characterize high-dimensional dynamical systems. We show that this approach is useful in a number of ways. First, the 2-D representation offered by RPs provides a visualization of the high-dimensional reservoir dynamics. Our results suggest that, if the network is stable, reservoir and input generate similar line patterns in the respective RPs. Conversely, as the ESN becomes unstable, the patterns in the RP of the reservoir change. As a second result, we show that an RQA measure, called , is highly correlated with the well-established maximal local Lyapunov exponent. This suggests that complexity measures based on RP diagonal lines distribution can quantify network stability. Finally, our analysis shows that all RQA measures fluctuate on the proximity of the so-called edge of stability, where an ESN typically achieves maximum computational capability. We leverage on this property to determine the edge of stability and show that our criterion is more accurate than two well-known counterparts, both based on the Jacobian matrix of the reservoir. Therefore, we claim that RPs and RQA-based analyses are valuable tools to design an ESN, given a specific problem.

It is a widely accepted fact that the computational capability of recurrent neural networks (RNNs) is maximized on the so-called "edge of criticality." Once the network operates in this configuration, it performs efficiently on a specific application both in terms of: 1) low prediction error and 2) high short-term memory capacity. Since the behavior of recurrent networks is strongly influenced by the particular input signal driving the dynamics, a universal, application-independent method for determining the edge of criticality is still missing. In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in RNNs. It is proved that Fisher information is maximized for (finite-size) systems operating in such critical regions. However, Fisher information is notoriously difficult to compute and requires the analytic form of the probability density function ruling the system behavior. This paper takes advantage of a recently developed nonparametric estimator of the Fisher information matrix and provides a method to determine the critical region of echo state networks (ESNs), a particular class of recurrent networks. The considered control parameters, which indirectly affect the ESN performance, are explored to identify those configurations lying on the edge of criticality and, as such, maximizing Fisher information and computational performance. Experimental results on benchmarks and real-world data demonstrate the effectiveness of the proposed method.

In this work we present a novel recurrent neural network architecture designed to model systems characterized by multiple characteristic timescales in their dynamics. The proposed network is composed by several recurrent groups of neurons that are trained to separately adapt to each timescale, in order to improve the system identification process. We test our framework on time series prediction tasks and we show some promising, preliminary results achieved on synthetic data. To evaluate the capabilities of our network, we compare the performance with several state-of-the-art recurrent architectures.

The computational capability of an Echo State Network (ESN), expressed in terms of low prediction error and high short-term memory capacity, is maximized on the so-called “edge of criticality”. In this paper we present a novel, unsupervised approach to identify this edge and, accordingly, we determine hyperparameters configuration that maximize network performance. The proposed method is application-independent and stems from recent theoretical results consolidating the link between Fisher information and critical phase transitions. We show how to identify optimal ESN hyperparameters by relying only on the Fisher information matrix (FIM) estimated from the activations of hidden neurons. In order to take into account the particular input signal driving the network dynamics, we adopt a recently proposed non-parametric FIM estimator. Experimental results on a set of standard benchmarks are provided and discussed, demonstrating the validity of the proposed method.

Short-Term Load Forecasting (STLF) is a fundamental component in the efficient management of power systems, which has been studied intensively over the past 50 years. The emerging development of smart grid technologies is posing new challenges as well as opportunities to STLF. Load data, collected at higher geographical granularity and frequency through thousands of smart meters, allows us to build a more accurate local load forecasting model, which is essential for local optimization of power load through demand side management. With this paper, we show how several existing approaches for STLF are not applicable on local load forecasting, either because of long training time, unstable optimization process, or sensitivity to hyper-parameters. Accordingly, we select five models suitable for local STFL, which can be trained on different time-series with limited intervention from the user. The experiment, which consists of 40 time-series collected at different locations and aggregation levels, revealed that yearly pattern and temperature information are only useful for high aggregation level STLF. On local STLF task, the modified version of double seasonal Holt-Winter proposed in this paper performs relatively well with only 3 months of training data, compared to more complex methods.

The generalization capability is usually recognized as the most desired feature of data-driven learning systems, such as classifiers. However, in many practical applications obtaining human-understandable information, relevant to the problem at hand, from the classidication model can be equally important. In this paper we propose a classification system able to fulfill these two requirements simultaneously for a generic image classification task. As a first preprocessing step, an input image to the classifier is represented by a labeled graph, relying on a segmentation algorithm. The graph is conceived to represent visual and topological information of the relevant segments of the image. Then, the graph is classified by a suited inductive inference engine. In the learning procedure all the training set images are represented by graphs, feeding a state-of-the-art classification system working on structured domains. The synthesis procedure consists in extracting characterizing subgraphs from the training set, which are used to embed the graphs into a vector space, enabling thus the applicability of well-known classifiers for feature-based patterns. Such characterizing subgraphs, which are derived in an unsupervised fashion, are interpretable by suitable field experts, allowing a semantic analysis of the discovered classification rules for the given problem at hand. The system is optimized with a genetic algorithm, which tunes the system parameters according to a cross-validation scheme. We show the validity of the approach by performing experiments considering some image classification problems derived from an on-line repository.

In this paper we propose an inexact graph matching algorithm which computes the dissimilarity of a time-varying labeled graph with respect to a static one. This approach is specifically designed for processing very large labeled graphs, which are subject to frequent edit operations that modify the topology and the labeling of restricted zones of the graph. In this scenario, repeating each time an extensive computation of the whole dissimilarity value would require too much time; moreover, since only a specific part of the graph changes, it would result also in a waste of computations. We propose a fast approach for computing the graph dissimilarity which exploits the dissimilarity value estimated in the previous time interval and the nature of the observed edit operations. We evaluate the properties of the proposed approach with respect to well-known graph matching algorithms, by simulating the dynamics of the graph. Overall, the experiments confirm the effectiveness of the approach.

We propose two variants of a general-purpose graph classification system which rely on a theoretical result that we prove in this paper. The result allows us to solve analytically the setting of a sequential clustering algorithm that is used for compressing the input labeled graphs represented in the dissimilarity space. As a consequence, we achieve a considerable asymptotic and practical speed-up of the overall classification system, maintaining state-of-the-art results in terms of test set classification accuracy on well-known benchmarking datasets of labeled graphs. The obtained speed-up makes the system one step closer towards the applicability to bigger labeled graphs and larger datasets.