Field Programmable Gate Arrays (FPGAs) are an attractive platform to accelerate CPD due to the vast Recent advances in collecting and analyzing large inherent parallelism and energy efficiency FPGAs can datasets have led to the information being naturally offer. Since sparse MTTKRP is memory bound, improving represented as higher-order tensors. Tensor Decomposition the sustained memory bandwidth and latency transforms input tensors to a reduced latent between the compute units on the FPGA and the external space which can then be leveraged to learn salient features DRAM memory can significantly reduce the of the underlying data distribution. Tensor Decomposition MTTKRP compute time. FPGA facilitates near memory has been successfully employed in many computing with custom adaptive hardware due fields, including machine learning, signal processing, to its reconfigurability and large on-chip BlockRAM and network analysis (Mondelli and Montanari, 2019; memory (Xilinx, 2019). It enables the development Cheng et al., 2020; Wen et al., 2020). Canonical of memory controllers and compute units specialized Polyadic Decomposition (CPD) is the most popular for specific data formats; such customization is not means of decomposing a tensor to a low-rank tensor supported on CPU and GPU.

The propagation of rumours on social media poses an important threat to societies, so that various techniques for rumour detection have been proposed recently. Yet, existing work focuses on \emph{what} entities constitute a rumour, but provides little support to understand \emph{why} the entities have been classified as such. This prevents an effective evaluation of the detected rumours as well as the design of countermeasures. In this work, we argue that explanations for detected rumours may be given in terms of examples of related rumours detected in the past. A diverse set of similar rumours helps users to generalize, i.e., to understand the properties that govern the detection of rumours. Since the spread of rumours in social media is commonly modelled using feature-annotated graphs, we propose a query-by-example approach that, given a rumour graph, extracts the $k$ most similar and diverse subgraphs from past rumours. The challenge is that all of the computations require fast assessment of similarities between graphs. To achieve an efficient and adaptive realization of the approach in a streaming setting, we present a novel graph representation learning technique and report on implementation considerations. Our evaluation experiments show that our approach outperforms baseline techniques in delivering meaningful explanations for various rumour propagation behaviours.

We introduce SPIRAL, a SuPerlinearly convergent Incremental pRoximal ALgorithm, for solving nonconvex regularized finite sum problems under a relative smoothness assumption. In the spirit of SVRG and SARAH, each iteration of SPIRAL consists of an inner and an outer loop. It combines incremental and full (proximal) gradient updates with a linesearch. It is shown that when using quasi-Newton directions, superlinear convergence is attained under mild assumptions at the limit points. More importantly, thanks to said linesearch, global convergence is ensured while it is shown that unit stepsize will be eventually always accepted. Simulation results on different convex, nonconvex, and non-Lipschitz differentiable problems show that our algorithm as well as its adaptive variant are competitive to the state of the art.

Anomaly detection is a well-established research area that seeks to identify samples outside of a predetermined distribution. An anomaly detection pipeline is comprised of two main stages: (1) feature extraction and (2) normality score assignment. Recent papers used pre-trained networks for feature extraction achieving state-of-the-art results. However, the use of pre-trained networks does not fully-utilize the normal samples that are available at train time. This paper suggests taking advantage of this information by using teacher-student training. In our setting, a pretrained teacher network is used to train a student network on the normal training samples. Since the student network is trained only on normal samples, it is expected to deviate from the teacher network in abnormal cases. This difference can serve as a complementary representation to the pre-trained feature vector. Our method -- Transformaly -- exploits a pre-trained Vision Transformer (ViT) to extract both feature vectors: the pre-trained (agnostic) features and the teacher-student (fine-tuned) features. We report state-of-the-art AUROC results in both the common unimodal setting, where one class is considered normal and the rest are considered abnormal, and the multimodal setting, where all classes but one are considered normal, and just one class is considered abnormal. The code is available at https://github.com/MatanCohen1/Transformaly.

There are hundreds of methods for analysis of data obtained in mRNA-sequencing. The most of them are focused on small number of genes. In this study, we propose an approach that reduces the analysis of several thousand genes to analysis of several clusters. The list of genes is enriched with information from open databases. Then, the descriptions are encoded as vectors using the pretrained language model (BERT) and some text processing approaches. The encoded gene function pass through the dimensionality reduction and clusterization. Aiming to find the most efficient pipeline, 180 cases of pipeline with different methods in the major pipeline steps were analyzed. The performance was evaluated with clusterization indexes and expert review of the results.

Heart rate variability (HRV) indices describe properties of interbeat intervals in electrocardiogram (ECG). Usually HRV is measured exclusively in normal sinus rhythm (NSR) excluding any form of paroxysmal rhythm. Atrial fibrillation (AF) is the most widespread cardiac arrhythmia in human population. Usually such abnormal rhythm is not analyzed and assumed to be chaotic and unpredictable. Nonetheless, ranges of HRV indices differ between patients with AF, yet physiological characteristics which influence them are poorly understood. In this study, we propose a statistical model that describes relationship between HRV indices in NSR and AF. The model is based on Mahalanobis distance, the k-Nearest neighbour approach and multivariate normal distribution framework. Verification of the method was performed using 10 min intervals of NSR and AF that were extracted from long-term Holter ECGs. For validation we used Bhattacharyya distance and Kolmogorov-Smirnov 2-sample test in a k-fold procedure. The model is able to predict at least 7 HRV indices with high precision.

This paper proposes a classification model for predicting the main activity of bitcoin addresses based on their balances. Since the balances are functions of time, we apply methods from functional data analysis; more specifically, the features of the proposed classification model are the functional principal components of the data. Classifying bitcoin addresses is a relevant problem for two main reasons: to understand the composition of the bitcoin market, and to identify addresses used for illicit activities. Although other bitcoin classifiers have been proposed, they focus primarily on network analysis rather than curve behavior. Our approach, on the other hand, does not require any network information for prediction. Furthermore, functional features have the advantage of being straightforward to build, unlike expert-built features. Results show improvement when combining functional features with scalar features, and similar accuracy for the models using those features separately, which points to the functional model being a good alternative when domain-specific knowledge is not available.

In contrast to a standard closed-set domain adaptation task, partial domain adaptation setup caters to a realistic scenario by relaxing the identical label set assumption. The fact of source label set subsuming the target label set, however, introduces few additional obstacles as training on private source category samples thwart relevant knowledge transfer and mislead the classification process. To mitigate these issues, we devise a mechanism for strategic selection of highly-confident target samples essential for the estimation of class-importance weights. Furthermore, we capture class-discriminative and domain-invariant features by coupling the process of achieving compact and distinct class distributions with an adversarial objective. Experimental findings over numerous cross-domain classification tasks demonstrate the potential of the proposed technique to deliver superior and comparable accuracy over existing methods.

Time series analysis has achieved great success in diverse applications such as network security, environmental monitoring, and medical informatics. Learning similarities among different time series is a crucial problem since it serves as the foundation for downstream analysis such as clustering and anomaly detection. It often remains unclear what kind of distance metric is suitable for similarity learning due to the complex temporal dynamics of the time series generated from event-triggered sensing, which is common in diverse applications, including automated driving, interactive healthcare, and smart home automation. The overarching goal of this paper is to develop an unsupervised learning framework that is capable of learning task-aware similarities among unlabeled event-triggered time series. From the machine learning vantage point, the proposed framework harnesses the power of both hierarchical multi-scale sequence autoencoders and Gaussian Mixture Model (GMM) to effectively learn the low-dimensional representations from the time series. Finally, the obtained similarity measure can be easily visualized for explaining. The proposed framework aspires to offer a stepping stone that gives rise to a systematic approach to model and learn similarities among a multitude of event-triggered time series. Through extensive qualitative and quantitative experiments, it is revealed that the proposed method outperforms state-of-the-art methods considerably.

The theoretical analysis of spectral clustering mainly focuses on consistency, while there is relatively little research on its generalization performance. In this paper, we study the excess risk bounds of the popular spectral clustering algorithms: \emph{relaxed} RatioCut and \emph{relaxed} NCut. Firstly, we show that their excess risk bounds between the empirical continuous optimal solution and the population-level continuous optimal solution have a $\mathcal{O}(1/\sqrt{n})$ convergence rate, where $n$ is the sample size. Secondly, we show the fundamental quantity in influencing the excess risk between the empirical discrete optimal solution and the population-level discrete optimal solution. At the empirical level, algorithms can be designed to reduce this quantity. Based on our theoretical analysis, we propose two novel algorithms that can not only penalize this quantity, but also cluster the out-of-sample data without re-eigendecomposition on the overall sample. Experiments verify the effectiveness of the proposed algorithms.