AutoML Meets Time Series Regression Design and Analysis of the AutoSeries Challenge

Analyzing better time series with limited human effort is of interest to academia and industry. Driven by business scenarios, we organized the first Automated Time Series Regression challenge (AutoSeries) for the WSDM Cup 2020. We present its design, analysis, and post-hoc experiments. The code submission requirement precluded participants from any manual intervention, testing automated machine learning capabilities of solutions, across many datasets, under hardware and time limitations. We prepared 10 datasets from diverse application domains (sales, power consumption, air quality, traffic, and parking), featuring missing data, mixed continuous and categorical variables, and various sampling rates. Each dataset was split into a training and a test sequence (which was streamed, allowing models to continuously adapt). The setting of time series regression, differs from classical forecasting in that covariates at the present time are known. Great strides were made by participants to tackle this AutoSeries problem, as demonstrated by the jump in performance from the sample submission, and post-hoc comparisons with AutoGluon. Simple yet effective methods were used, based on feature engineering, LightGBM, and random search hyper-parameter tuning, addressing all aspects of the challenge. Our post-hoc analyses revealed that providing additional time did not yield significant improvements. The winners' code was open-sourced https://www.4paradigm.com/competition/autoseries2020.

Spatio-Temporal U-Net for Cerebral Artery and Vein Segmentation in Digital Subtraction Angiography

X-ray digital subtraction angiography (DSA) is widely used for vessel and/or flow visualization and interventional guidance during endovascular treatment of patients with a stroke or aneurysm. To assist in peri-operative decision making as well as post-operative prognosis, automatic DSA analysis algorithms are being developed to obtain relevant image-based information. Such analyses include detection of vascular disease, evaluation of perfusion based on time intensity curves (TIC), and quantitative biomarker extraction for automated treatment evaluation in endovascular thrombectomy. Methodologically, such vessel-based analysis tasks may be facilitated by automatic and accurate artery-vein segmentation algorithms. The present work describes to the best of our knowledge the first study that addresses automatic artery-vein segmentation in DSA using deep learning. We propose a novel spatio-temporal U-Net (ST U-Net) architecture which integrates convolutional gated recurrent units (ConvGRU) in the contracting branch of U-Net. The network encodes a 2D+t DSA series of variable length and decodes it into a 2D segmentation image. On a multi-center routinely acquired dataset, the proposed method significantly outperformed U-Net (P<0.001) and traditional Frangi-based K-means clustering (P$<$0.001). Particularly in artery-vein segmentation, ST U-Net achieved a Dice coefficient of 0.794, surpassing the existing state-of-the-art methods by a margin of 12\%-20\%. Code will be made publicly available upon acceptance.

SNGuess: A method for the selection of young extragalactic transients

With a rapidly rising number of transients detected in astronomy, classification methods based on machine learning are increasingly being employed. Their goals are typically to obtain a definitive classification of transients, and for good performance they usually require the presence of a large set of observations. However, well-designed, targeted models can reach their classification goals with fewer computing resources. This paper presents SNGuess, a model designed to find young extragalactic nearby transients with high purity. SNGuess works with a set of features that can be efficiently calculated from astronomical alert data. Some of these features are static and associated with the alert metadata, while others must be calculated from the photometric observations contained in the alert. Most of the features are simple enough to be obtained or to be calculated already at the early stages in the lifetime of a transient after its detection. We calculate these features for a set of labeled public alert data obtained over a time span of 15 months from the Zwicky Transient Facility (ZTF). The core model of SNGuess consists of an ensemble of decision trees, which are trained via gradient boosting. Approximately 88% of the candidates suggested by SNGuess from a set of alerts from ZTF spanning from April 2020 to August 2021 were found to be true relevant supernovae (SNe). For alerts with bright detections, this number ranges between 92% and 98%. Since April 2020, transients identified by SNGuess as potential young SNe in the ZTF alert stream are being published to the Transient Name Server (TNS) under the AMPEL_ZTF_NEW group identifier. SNGuess scores for any transient observed by ZTF can be accessed via a web service. The source code of SNGuess is publicly available.

Automated, real-time hospital ICU emergency signaling: A field-level implementation

Contemporary patient surveillance systems have streamlined central surveillance into the electronic health record interface. They are able to process the sheer volume of patient data by adopting machine learning approaches. However, these systems are not suitable for implementation in many hospitals, mostly in developing countries, with limited human, financial, and technological resources. Through conducting thorough research on intensive care facilities, we designed a novel central patient monitoring system and in this paper, we describe the working prototype of our system. The proposed prototype comprises of inexpensive peripherals and simplistic user interface. Our central patient monitoring system implements Kernel-based On-line Anomaly Detection (KOAD) algorithm for emergency event signaling. By evaluating continuous patient data, we show that the system is able to detect critical events in real-time reliably and has low false alarm rate.

Deeptime: a Python library for machine learning dynamical models from time series data

Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software.

Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms

Climate change is increasing the frequency and severity of harmful algal blooms (HABs), which cause significant fish deaths in aquaculture farms. This contributes to ocean pollution and greenhouse gas (GHG) emissions since dead fish are either dumped into the ocean or taken to landfills, which in turn negatively impacts the climate. Currently, the standard method to enumerate harmful algae and other phytoplankton is to manually observe and count them under a microscope. This is a time-consuming, tedious and error-prone process, resulting in compromised management decisions by farmers. Hence, automating this process for quick and accurate HAB monitoring is extremely helpful. However, this requires large and diverse datasets of phytoplankton images, and such datasets are hard to produce quickly. In this work, we explore the feasibility of generating novel high-resolution photorealistic synthetic phytoplankton images, containing multiple species in the same image, given a small dataset of real images. To this end, we employ Generative Adversarial Networks (GANs) to generate synthetic images. We evaluate three different GAN architectures: ProjectedGAN, FastGAN, and StyleGANv2 using standard image quality metrics. We empirically show the generation of high-fidelity synthetic phytoplankton images using a training dataset of only 961 real images. Thus, this work demonstrates the ability of GANs to create large synthetic datasets of phytoplankton from small training datasets, accomplishing a key step towards sustainable systematic monitoring of harmful algal blooms.

Reactive Navigation of an Unmanned Aerial Vehicle with Perception-based Obstacle Avoidance Constraints

In this article we propose a reactive constrained navigation scheme, with embedded obstacles avoidance for an Unmanned Aerial Vehicle (UAV), for enabling navigation in obstacle-dense environments. The proposed navigation architecture is based on Nonlinear Model Predictive Control (NMPC), and utilizes an on-board 2D LiDAR to detect obstacles and translate online the key geometric information of the environment into parametric constraints for the NMPC that constrain the available position-space for the UAV. This article focuses also on the real-world implementation and experimental validation of the proposed reactive navigation scheme, and it is applied in multiple challenging laboratory experiments, where we also conduct comparisons with relevant methods of reactive obstacle avoidance. The solver utilized in the proposed approach is the Optimization Engine (OpEn) and the Proximal Averaged Newton for Optimal Control (PANOC) algorithm, where a penalty method is applied to properly consider obstacles and input constraints during the navigation task. The proposed novel scheme allows for fast solutions, while using limited on-board computational power, that is a required feature for the overall closed loop performance of an UAV and is applied in multiple real-time scenarios. The combination of built-in obstacle avoidance and real-time applicability makes the proposed reactive constrained navigation scheme an elegant framework for UAVs that is able to perform fast nonlinear control, local path-planning and obstacle avoidance, all embedded in the control layer.

Lottery Ticket Hypothesis for Spiking Neural Networks

Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks where binary spikes convey information across multiple timesteps. Pruning for SNNs is highly important as they become deployed on a resource-constraint mobile/edge device. The previous SNN pruning works focus on shallow SNNs (2~6 layers), however, deeper SNNs (>16 layers) are proposed by state-of-the-art SNN works, which is difficult to be compatible with the current pruning work. To scale up a pruning technique toward deep SNNs, we investigate Lottery Ticket Hypothesis (LTH) which states that dense networks contain smaller subnetworks (i.e., winning tickets) that achieve comparable performance to the dense networks. Our studies on LTH reveal that the winning tickets consistently exist in deep SNNs across various datasets and architectures, providing up to 97% sparsity without huge performance degradation. However, the iterative searching process of LTH brings a huge training computational cost when combined with the multiple timesteps of SNNs. To alleviate such heavy searching cost, we propose Early-Time (ET) ticket where we find the important weight connectivity from a smaller number of timesteps. The proposed ET ticket can be seamlessly combined with common pruning techniques for finding winning tickets, such as Iterative Magnitude Pruning (IMP) and Early-Bird (EB) tickets. Our experiment results show that the proposed ET ticket reduces search time by up to 38% compared to IMP or EB methods.

Layer-Wise Partitioning and Merging for Efficient and Scalable Deep Learning

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel strategies to mitigate these problems provide suboptimal runtime performance. In this work, we have proposed a novel layer-wise partitioning and merging, forward and backward pass parallel framework to provide better training performance. The novelty of the proposed work consists of 1) a layer-wise partition and merging model which can minimise communication overhead between devices without the memory cost of existing strategies during the training process; 2) a forward pass and backward pass parallelisation and optimisation to address the update locking problem and minimise the total training cost. The experimental evaluation on real use cases shows that the proposed method outperforms the state-of-the-art approaches in terms of training speed; and achieves almost linear speedup without compromising the accuracy performance of the non-parallel approach.

Hierarchical Agglomerative Graph Clustering in Nearly-Linear Time

We study the widely used hierarchical agglomerative clustering (HAC) algorithm on edge-weighted graphs. We define an algorithmic framework for hierarchical agglomerative graph clustering that provides the first efficient $\tilde{O}(m)$ time exact algorithms for classic linkage measures, such as complete- and WPGMA-linkage, as well as other measures. Furthermore, for average-linkage, arguably the most popular variant of HAC, we provide an algorithm that runs in $\tilde{O}(n\sqrt{m})$ time. For this variant, this is the first exact algorithm that runs in subquadratic time, as long as $m=n^{2-\epsilon}$ for some constant $\epsilon > 0$. We complement this result with a simple $\epsilon$-close approximation algorithm for average-linkage in our framework that runs in $\tilde{O}(m)$ time. As an application of our algorithms, we consider clustering points in a metric space by first using $k$-NN to generate a graph from the point set, and then running our algorithms on the resulting weighted graph. We validate the performance of our algorithms on publicly available datasets, and show that our approach can speed up clustering of point datasets by a factor of 20.7--76.5x.