Many e-commerce websites use recommender systems or personalized rankers to personalize search results based on their previous interactions. However, a large fraction of users has no prior inter-actions, making it impossible to use collaborative filtering or rely on user history for personalization. Even the most active users mayvisit only a few times a year and may have volatile needs or different personas, making their personal history a sparse and noisy signal at best. This paper investigates how, when we cannot rely on the user history, the large scale availability of other user interactions still allows us to build meaningful profiles from the contextual data and whether such contextual profiles are useful to customize the ranking, exemplified by data from a major online travel agentBooking.com.Our main findings are threefold: First, we characterize the Continuous Cold Start Problem(CoCoS) from the viewpoint of typical e-commerce applications. Second, as explicit situational con-text is not available in typical real world applications, implicit cues from transaction logs used at scale can capture essential features of situational context. Third, contextual user profiles can be created offline, resulting in a set of smaller models compared to a single huge non-contextual model, making contextual ranking available with negligible CPU and memory footprint. Finally we conclude that, in an online A/B test on live users, our contextual ranker in-creased user engagement substantially over a non-contextual base-line, with click-through-rate (CTR) increased by 20%. This clearly demonstrates the value of contextual user profiles in a real world application.
The realized stochastic volatility (RSV) model that utilizes the realized volatility as additional information has been proposed to infer volatility of financial time series. We consider the Bayesian inference of the RSV model by the Hybrid Monte Carlo (HMC) algorithm. The HMC algorithm can be parallelized and thus performed on the GPU for speedup. The GPU code is developed with CUDA Fortran. We compare the computational time in performing the HMC algorithm on GPU (GTX 760) and CPU (Intel i7-4770 3.4GHz) and find that the GPU can be up to 17 times faster than the CPU. We also code the program with OpenACC and find that appropriate coding can achieve the similar speedup with CUDA Fortran.
The tripartite graph is one of the commonest topological structures in social tagging systems such as Delicious, which has three types of nodes (i.e., users, URLs and tags). Traditional recommender systems developed based on collaborative filtering for the social tagging systems bring very high demands on CPU time cost. In this paper, to overcome this drawback, we propose a novel approach that extracts non-overlapping user clusters and corresponding overlapping item clusters simultaneously through coarse clustering to accelerate the user-based collaborative filtering and develop a fast recommendation algorithm for the social tagging systems. The experimental results show that the proposed approach is able to dramatically reduce the processing time cost greater than $90\%$ and relatively enhance the accuracy in comparison with the ordinary user-based collaborative filtering algorithm.
BarraCUDA is a C program which uses the BWA algorithm in parallel with nVidia CUDA to align short next generation DNA sequences against a reference genome. The genetically improved (GI) code is up to three times faster on short paired end reads from The 1000 Genomes Project and 60percent more accurate on a short BioPlanet.com GCAT alignment benchmark. GPGPU Barracuda running on a single K80 Tesla GPU can align short paired end nextgen sequences up to ten times faster than bwa on a 12 core CPU.
The internet is considered as the most extensive market in the world. To keep its gradual reputation, it must confront real problems that result from its distribution and from the diversity of the protocols used to insure communications. The Web service technology has diminished significantly the effects of distribution and heterogeneity, but there are several problems that weaken their performance (unavailability, load increase of use, high cost of CPU time...). Faced with this situation, we are forced to move in the direction of the substitution of web services. In this context, we propose an effective technique of substitution based on a new method of matching that allows detecting and expressing the matching between the web services pairwise by considering that each of them is ontology. Also, our method performs a discovery of the most similar web service to that to be replaced by using an efficient method of similarity measurement.
To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmitted over the network. In this context, we discuss and evaluate the benefits and disadvantages of several deep adversarial approaches. In particular, we explore quality and bandwidth trade-offs for approaches based on static landmarks, dynamic landmarks or segmentation maps. We design a mobile-compatible architecture based on the first order animation model of Siarohin et al. In addition, we leverage SPADE blocks to refine results in important areas such as the eyes and lips. We compress the networks down to about 3MB, allowing models to run in real time on iPhone 8 (CPU). This approach enables video calling at a few kbits per second, an order of magnitude lower than currently available alternatives.
The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. We show that we can enhance a full resolution, 2848 x 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 - 7x fewer model parameters, 2 - 3x lower memory utilization, 5 - 20x speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms.
Left ventricular non-compaction (LVNC) is a rare cardiomyopathy characterized by abnormal trabeculations in the left ventricle cavity. Although traditional computer vision approaches exist for LVNC diagnosis, deep learning-based tools could not be found in the literature. In this paper, a first approach using convolutional neural networks (CNNs) is presented. Four CNNs are trained to automatically segment the compacted and trabecular areas of the left ventricle for a population of patients diagnosed with Hypertrophic cardiomyopathy. Inference results confirm that deep learning-based approaches can achieve excellent results in the diagnosis and measurement of LVNC. The two best CNNs (U-Net and Efficient U-Net B1) perform image segmentation in less than 0.2 s on a CPU and in less than 0.01 s on a GPU. Additionally, a subjective evaluation of the output images with the identified zones is performed by expert cardiologists, with a perfect visual agreement for all the slices, outperforming already existing automatic tools.
Although deep learning models have taken on commercial and political relevance, key aspects of their training and operation remain poorly understood. This has sparked interest in science of deep learning projects, many of which require large amounts of time, money, and electricity. But how much of this research really needs to occur at scale? In this paper, we introduce MNIST-1D: a minimalist, procedurally generated, low-memory, and low-compute alternative to classic deep learning benchmarks. Although the dimensionality of MNIST-1D is only 40 and its default training set size only 4000, MNIST-1D can be used to study inductive biases of different deep architectures, find lottery tickets, observe deep double descent, metalearn an activation function, and demonstrate guillotine regularization in self-supervised learning. All these experiments can be conducted on a GPU or often even on a CPU within minutes, allowing for fast prototyping, educational use cases, and cutting-edge research on a low budget.
Ground segmentation is an important preprocessing task for autonomous vehicles (AVs) with 3D LiDARs. To solve the problem of existing ground segmentation methods being very difficult to balance accuracy and computational complexity, a fast point cloud ground segmentation approach based on a coarse-to-fine Markov random field (MRF) method is proposed. The method uses an improved elevation map for ground coarse segmentation, and then uses spatiotemporal adjacent points to optimize the segmentation results. The processed point cloud is classified into high-confidence obstacle points, ground points, and unknown classification points to initialize an MRF model. The graph cut method is then used to solve the model to achieve fine segmentation. Experiments on datasets showed that our method improves on other algorithms in terms of ground segmentation accuracy and is faster than other graph-based algorithms, which require only a single core of an I7-3770 CPU to process a frame of Velodyne HDL-64E data (in 39.77 ms, on average). Field tests were also conducted to demonstrate the effectiveness of the proposed method.
Federated Learning is a new learning scheme for collaborative training a shared prediction model while keeping data locally on participating devices. In this paper, we study a new model of multiple federated learning services at the multi-access edge computing server. Accordingly, the sharing of CPU resources among learning services at each mobile device for the local training process and allocating communication resources among mobile devices for exchanging learning information must be considered. Furthermore, the convergence performance of different learning services depends on the hyper-learning rate parameter that needs to be precisely decided. Towards this end, we propose a joint resource optimization and hyper-learning rate control problem, namely MS-FEDL, regarding the energy consumption of mobile devices and overall learning time. We design a centralized algorithm based on the block coordinate descent method and a decentralized JP-miADMM algorithm for solving the MS-FEDL problem. Different from the centralized approach, the decentralized approach requires many iterations to obtain but it allows each learning service to independently manage the local resource and learning process without revealing the learning service information. Our simulation results demonstrate the convergence performance of our proposed algorithms and the superior performance of our proposed algorithms compared to the heuristic strategy.
We present "Cross-Camera Convolutional Color Constancy" (C5), a learning-based method, trained on images from multiple cameras, that accurately estimates a scene's illuminant color from raw images captured by a new camera previously unseen during training. C5 is a hypernetwork-like extension of the convolutional color constancy (CCC) approach: C5 learns to generate the weights of a CCC model that is then evaluated on the input image, with the CCC weights dynamically adapted to different input content. Unlike prior cross-camera color constancy models, which are usually designed to be agnostic to the spectral properties of test-set images from unobserved cameras, C5 approaches this problem through the lens of transductive inference: additional unlabeled images are provided as input to the model at test time, which allows the model to calibrate itself to the spectral properties of the test-set camera during inference. C5 achieves state-of-the-art accuracy for cross-camera color constancy on several datasets, is fast to evaluate (~7 and ~90 ms per image on a GPU or CPU, respectively), and requires little memory (~2 MB), and thus is a practical solution to the problem of calibration-free automatic white balance for mobile photography.
Automated machine learning pipeline (ML) composition and optimisation aim at automating the process of finding the most promising ML pipelines within allocated resources (i.e., time, CPU and memory). Existing methods, such as Bayesian-based and genetic-based optimisation, which are implemented in Auto-Weka, Auto-sklearn and TPOT, evaluate pipelines by executing them. Therefore, the pipeline composition and optimisation of these methods frequently require a tremendous amount of time that prevents them from exploring complex pipelines to find better predictive models. To further explore this research challenge, we have conducted experiments showing that many of the generated pipelines are invalid in the first place, and attempting to execute them is a waste of time and resources. To address this issue, we propose a novel method to evaluate the validity of ML pipelines, without their execution, using a surrogate model (AVATAR). The AVATAR generates a knowledge base by automatically learning the capabilities and effects of ML algorithms on datasets' characteristics. This knowledge base is used for a simplified mapping from an original ML pipeline to a surrogate model which is a Petri net based pipeline. Instead of executing the original ML pipeline to evaluate its validity, the AVATAR evaluates its surrogate model constructed by capabilities and effects of the ML pipeline components and input/output simplified mappings. Evaluating this surrogate model is less resource-intensive than the execution of the original pipeline. As a result, the AVATAR enables the pipeline composition and optimisation methods to evaluate more pipelines by quickly rejecting invalid pipelines. We integrate the AVATAR into the sequential model-based algorithm configuration (SMAC). Our experiments show that when SMAC employs AVATAR, it finds better solutions than on its own.
Federated Learning (FL) is emerging as a promising technology to build machine learning models in a decentralized, privacy-preserving fashion. Indeed, FL enables local training on user devices, avoiding user data to be transferred to centralized servers, and can be enhanced with differential privacy mechanisms. Although FL has been recently deployed in real systems, the possibility of collaborative modeling across different 3rd-party applications has not yet been explored. In this paper, we tackle this problem and present Federated Learning as a Service (FLaaS), a system enabling different scenarios of 3rd-party application collaborative model building and addressing the consequent challenges of permission and privacy management, usability, and hierarchical model training. FLaaS can be deployed in different operational environments. As a proof of concept, we implement it on a mobile phone setting and discuss practical implications of results on simulated and real devices with respect to on-device training CPU cost, memory footprint and power consumed per FL model round. Therefore, we demonstrate FLaaS's feasibility in building unique or joint FL models across applications for image object detection in a few hours, across 100 devices.
Perception is a critical component of high-integrity applications of robotics and autonomous systems, such as self-driving vehicles. In these applications, failure of perception systems may put human life at risk, and a broad adoption of these technologies requires the development of methodologies to guarantee and monitor safe operation. Despite the paramount importance of perception systems, currently there is no formal approach for system-level monitoring. In this work, we propose a mathematical model for runtime monitoring and fault detection and identification in perception systems. Towards this goal, we draw connections with the literature on diagnosability in multiprocessor systems, and generalize it to account for modules with heterogeneous outputs that interact over time. The resulting temporal diagnostic graphs (i) provide a framework to reason over the consistency of perception outputs -- across modules and over time -- thus enabling fault detection, (ii) allow us to establish formal guarantees on the maximum number of faults that can be uniquely identified in a given perception system, and (iii) enable the design of efficient algorithms for fault identification. We demonstrate our monitoring system, dubbed PerSyS, in realistic simulations using the LGSVL self-driving simulator and the Apollo Auto autonomy software stack, and show that PerSyS is able to detect failures in challenging scenarios (including scenarios that have caused self-driving car accidents in recent years), and is able to correctly identify faults while entailing a minimal computation overhead (< 5 ms on a single-core CPU).
We present an efficient multi-sensor odometry system for mobile platforms that jointly optimizes visual, lidar, and inertial information within a single integrated factor graph. This runs in real-time at full framerate using fixed lag smoothing. To perform such tight integration, a new method to extract 3D line and planar primitives from lidar point clouds is presented. This approach overcomes the suboptimality of typical frame-to-frame tracking methods by treating the primitives as landmarks and tracking them over multiple scans. True integration of lidar features with standard visual features and IMU is made possible using a subtle passive synchronization of lidar and camera frames. The lightweight formulation of the 3D features allows for real-time execution on a single CPU. Our proposed system has been tested on a variety of platforms and scenarios, including underground exploration with a legged robot and outdoor scanning with a dynamically moving handheld device, for a total duration of 96 min and 2.4 km traveled distance. In these test sequences, using only one exteroceptive sensor leads to failure due to either underconstrained geometry (affecting lidar) or textureless areas caused by aggressive lighting changes (affecting vision). In these conditions, our factor graph naturally uses the best information available from each sensor modality without any hard switches.
In this paper, we use modeling and prediction tool MuMMI (Multiple Metrics Modeling Infrastructure) and ten machine learning methods to model and predict performance and power and compare their prediction error rates. We use a fault-tolerant linear algebra code and a fault-tolerant heat distribution code to conduct our modeling and prediction study on the Cray XC40 Theta and IBM BG/Q Mira at Argonne National Laboratory and the Intel Haswell cluster Shepard at Sandia National Laboratories. Our experiment results show that the prediction error rates in performance and power using MuMMI are less than 10% for most cases. Based on the models for runtime, node power, CPU power, and memory power, we identify the most significant performance counters for potential optimization efforts associated with the application characteristics and the target architectures, and we predict theoretical outcomes of the potential optimizations. When we compare the prediction accuracy using MuMMI with that using 10 machine learning methods, we observe that MuMMI not only results in more accurate prediction in both performance and power but also presents how performance counters impact the performance and power models. This provides some insights about how to fine-tune the applications and/or systems for energy efficiency.
We present a simple, fast, and light-weight RNN based framework for forecasting future locations of humans in first person monocular videos. The primary motivation for this work was to design a network which could accurately predict future trajectories at a very high rate on a CPU. Typical applications of such a system would be a social robot or a visual assistance system for all, as both cannot afford to have high compute power to avoid getting heavier, less power efficient, and costlier. In contrast to many previous methods which rely on multiple type of cues such as camera ego-motion or 2D pose of the human, we show that a carefully designed network model which relies solely on bounding boxes can not only perform better but also predicts trajectories at a very high rate while being quite low in size of approximately 17 MB. Specifically, we demonstrate that having an auto-encoder in the encoding phase of the past information and a regularizing layer in the end boosts the accuracy of predictions with negligible overhead. We experiment with three first person video datasets: CityWalks, FPL and JAAD. Our simple method trained on CityWalks surpasses the prediction accuracy of state-of-the-art method (STED) while being 9.6x faster on a CPU (STED runs on a GPU). We also demonstrate that our model can transfer zero-shot or after just 15% fine-tuning to other similar datasets and perform on par with the state-of-the-art methods on such datasets (FPL and DTP). To the best of our knowledge, we are the first to accurately forecast trajectories at a very high prediction rate of 78 trajectories per second on CPU.
This paper wants to focus on providing a characterization of the runtime performances of state-of-the-art implementations of KGE alghoritms, in terms of memory footprint and execution time. Despite the rapidly growing interest in KGE methods, so far little attention has been devoted to their comparison and evaluation; in particular, previous work mainly focused on performance in terms of accuracy in specific tasks, such as link prediction. To this extent, a framework is proposed for evaluating available KGE implementations against graphs with different properties, with a particular focus on the effectiveness of the adopted optimization strategies. Graphs and models have been trained leveraging different architectures, in order to enlighten features and properties of both models and the architectures they have been trained on. Some results enlightened with experiments in this document are the fact that multithreading is efficient, but benefit deacreases as the number of threads grows in case of CPU. GPU proves to be the best architecture for the given task, even if CPU with some vectorized instructions still behaves well. Finally, RAM utilization for the loading of the graph never changes between different architectures and depends only on the type of graph, not on the model.
Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As our emotional patterns and sensitive attributes like our identity, gender, well-being, are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving, on-device paralinguistic information learning and filtering before transmitting voice data. In this paper we introduce EDGY, a configurable, lightweight, disentangled representation learning framework that transforms and filters high-dimensional voice data to identify and contain sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY's on-device performance and explore optimization techniques, including model quantization and knowledge distillation, to enable private, accurate and efficient representation learning on resource-constrained devices. Our results show that EDGY runs in tens of milliseconds with 0.2% relative improvement in "zero-shot" ABX score or minimal performance penalties of approximately 5.95% word error rate (WER) in learning linguistic representations from raw voice signals, using a CPU and a single-core ARM processor without specialized hardware.