Prediction of annual crop yields at a county granularity is important for national food production and price stability. In this paper, towards the goal of better crop yield prediction, leveraging recent graph signal processing (GSP) tools to exploit spatial correlation among neighboring counties, we denoise relevant features via graph spectral filtering that are inputs to a deep learning prediction model. Specifically, we first construct a combinatorial graph with edge weights that encode county-to-county similarities in soil and location features via metric learning. We then denoise features via a maximum a posteriori (MAP) formulation with a graph Laplacian regularizer (GLR). We focus on the challenge to estimate the crucial weight parameter $\mu$, trading off the fidelity term and GLR, that is a function of noise variance in an unsupervised manner. We first estimate noise variance directly from noise-corrupted graph signals using a graph clique detection (GCD) procedure that discovers locally constant regions. We then compute an optimal $\mu$ minimizing an approximate mean square error function via bias-variance analysis. Experimental results from collected USDA data show that using denoised features as input, performance of a crop yield prediction model can be improved noticeably.

Such advantage enables humans to conduct reasoning under the "what-if" circumstances, and shows the Counterfactual, serving as one emerging type of model explanation, potential actions to take for altering model decisions. Essentially, has attracted tons of attentions recently from both industry and counterfactuals are hypothetical data samples synthesized within academia. Different from the conventional feature-based explanations certain distributions, which may not necessarily exist in the real (e.g., attributions), counterfactuals are a series of hypothetical world. Given a loan rejection case for example, valid counterfactuals samples which can flip model decisions with minimal perturbations would suggest some specific changes on the profile to make on queries. Given valid counterfactuals, humans are capable of reasoning it approved, such as increasing annual income from $60, 000 to under "what-if" circumstances, so as to better understand $80, 000 or improving education level from High-School to College. the model decision boundaries. However, releasing counterfactuals Nevertheless, releasing model explanations could be risky, since could be detrimental, since it may unintentionally leak sensitive meaningful explanations always contain additional information on information to adversaries, which brings about higher risks on how model works. Adversaries may purposely collect those released both model security and data privacy. To bridge the gap, in this explanations to infer model properties, which can cause serious paper, we propose a novel framework to generate differentially issues on both model security [22] and data privacy [42]. Counterfactual private counterfactual (DPC) without touching the deployed model explanation can make such threat even more significant, or explanation set, where noises are injected for protection while considering the fact that it directly reveals the decision boundaries maintaining the explanation roles of counterfactual.

Decomposing a complex time series into trend, seasonality, and remainder components is an important primitive that facilitates time series anomaly detection, change point detection, and forecasting. Although numerous batch algorithms are known for time series decomposition, none operate well in an online scalable setting where high throughput and real-time response are paramount. In this paper, we propose OnlineSTL, a novel online algorithm for time series decomposition which is highly scalable and is deployed for real-time metrics monitoring on high-resolution, high-ingest rate data. Experiments on different synthetic and real world time series datasets demonstrate that OnlineSTL achieves orders of magnitude speedups (100x) while maintaining quality of decomposition.

We provide a convergence analysis of gradient descent for the problem of agnostically learning a single ReLU function under Gaussian distributions. Unlike prior work that studies the setting of zero bias, we consider the more challenging scenario when the bias of the ReLU function is non-zero. Our main result establishes that starting from random initialization, in a polynomial number of iterations gradient descent outputs, with high probability, a ReLU function that achieves a competitive error guarantee when compared to the error of the best ReLU function. We also provide finite sample guarantees, and these techniques generalize to a broader class of marginal distributions beyond Gaussians.

Anomaly detection (AD), separating anomalies from normal data, has many applications across domains, from security to healthcare. While most previous works were shown to be effective for cases with fully or partially labeled data, that setting is in practice less common due to labeling being particularly tedious for this task. In this paper, we focus on fully unsupervised AD, in which the entire training dataset, containing both normal and anomalous samples, is unlabeled. To tackle this problem effectively, we propose to improve the robustness of one-class classification trained on self-supervised representations using a data refinement process. Our proposed data refinement approach is based on an ensemble of one-class classifiers (OCCs), each of which is trained on a disjoint subset of training data. Representations learned by self-supervised learning on the refined data are iteratively updated as the data refinement improves. We demonstrate our method on various unsupervised AD tasks with image and tabular data. With a 10% anomaly ratio on CIFAR-10 image data / 2.5% anomaly ratio on Thyroid tabular data, the proposed method outperforms the state-of-the-art one-class classifier by 6.3 AUC and 12.5 average precision / 22.9 F1-score.

There has been an increased interest in applying machine learning techniques on relational structured-data based on an observed graph. Often, this graph is not fully representative of the true relationship amongst nodes. In these settings, building a generative model conditioned on the observed graph allows to take the graph uncertainty into account. Various existing techniques either rely on restrictive assumptions, fail to preserve topological properties within the samples or are prohibitively expensive for larger graphs. In this work, we introduce the node copying model for constructing a distribution over graphs. Sampling of a random graph is carried out by replacing each node's neighbors by those of a randomly sampled similar node. The sampled graphs preserve key characteristics of the graph structure without explicitly targeting them. Additionally, sampling from this model is extremely simple and scales linearly with the nodes. We show the usefulness of the copying model in three tasks. First, in node classification, a Bayesian formulation based on node copying achieves higher accuracy in sparse data settings. Second, we employ our proposed model to mitigate the effect of adversarial attacks on the graph topology. Last, incorporation of the model in a recommendation system setting improves recall over state-of-the-art methods.

This paper focuses on online kernel learning over a decentralized network. Each agent in the network receives continuous streaming data locally and works collaboratively to learn a nonlinear prediction function that is globally optimal in the reproducing kernel Hilbert space with respect to the total instantaneous costs of all agents. In order to circumvent the curse of dimensionality issue in traditional online kernel learning, we utilize random feature (RF) mapping to convert the non-parametric kernel learning problem into a fixed-length parametric one in the RF space. We then propose a novel learning framework named Online Decentralized Kernel learning via Linearized ADMM (ODKLA) to efficiently solve the online decentralized kernel learning problem. To further improve the communication efficiency, we add the quantization and censoring strategies in the communication stage and develop the Quantized and Communication-censored ODKLA (QC-ODKLA) algorithm. We theoretically prove that both ODKLA and QC-ODKLA can achieve the optimal sublinear regret $\mathcal{O}(\sqrt{T})$ over $T$ time slots. Through numerical experiments, we evaluate the learning effectiveness, communication, and computation efficiencies of the proposed methods.

In pace with the electronic technology development and the production technology improvement, industrial robot Give Scope to the Advantage in social services and industrial production. However, due to long-term mechanical wear and structural deformation, the absolute positioning accuracy is low, which greatly hinders the development of manufacturing industry. Calibrating the kinematic parameters of the robot is an effective way to address it. However, the main measuring equipment such as laser trackers and coordinate measuring machines are expensive and need special personnel to operate. Additionally, in the measurement process, due to the influence of many environmental factors, measurement noises are generated, which will affect the calibration accuracy of the robot. Basing on these, we have done the following work: a) developing a robot calibration method based on plane constraint to simplify measurement steps; b) employing Square-root Culture Kalman Filter (SCKF) algorithm for reducing the influence of measurement noises; c) proposing a novel algorithm for identifying kinematic parameters based on SCKF algorithm and Levenberg Marquardt (LM) algorithm to achieve the high calibration accuracy; d) adopting the dial indicator as the measuring equipment for slashing costs. The enough experiments verify the effectiveness of the proposed calibration algorithm and experimental platform.

Abstract--High-dimensional and incomplete (HDI) data holds tremendous interactive information in various industrial applications. A latent factor (LF) model is remarkably effective in extracting valuable information from HDI data with stochastic gradient decent (SGD) algorithm. However, an SGD-based LFA model suffers from slow convergence since it only considers the current learning error. To address this critical issue, this paper proposes a Nonlinear PID-enhanced Adaptive Latent Factor (NPALF) model with two-fold ideas: 1) rebuilding the learning error via considering the past learning errors following the principle of a nonlinear PID controller; b) implementing all parameters adaptation effectively following the principle of a particle swarm optimization (PSO) algorithm. Experience results on four representative HDI datasets indicate that compared with five state-of-the-art LFA models, the NPALF model achieves better convergence rate and prediction accuracy for missing data of an HDI data.

The requirement to trace and process moving objects in the contemporary era gradually increases since numerous applications quickly demand precise moving object locations. The Map-matching method is employed as a preprocessing technique, which matches a moving object point on a corresponding road. However, most of the GPS trajectory datasets include stay-points irregularity, which makes map-matching algorithms mismatch trajectories to irrelevant streets. Therefore, determining the stay-point region in GPS trajectory datasets results in better accurate matching and more rapid approaches. In this work, we cluster stay-points in a trajectory dataset with DBSCAN and eliminate redundant data to improve the efficiency of the map-matching algorithm by lowering processing time. We reckoned our proposed method's performance and exactness with a ground truth dataset compared to a fuzzy-logic based map-matching algorithm. Fortunately, our approach yields 27.39% data size reduction and 8.9% processing time reduction with the same accurate results as the previous fuzzy-logic based map-matching approach.