Effectively localizing root causes of performance anomalies is crucial to enabling the rapid recovery and loss mitigation of microservice applications in the cloud. Depending on the granularity of the causes that can be localized, a service operator may take different actions, e.g., restarting or migrating services if only faulty services can be localized (namely, coarse-grained) or scaling resources if specific indicative metrics on the faulty service can be localized (namely, fine-grained). Prior research mainly focuses on coarse-grained faulty service localization, and there is now a growing interest in fine-grained root cause localization to identify faulty services and metrics. Causal inference (CI) based methods have gained popularity recently for root cause localization, but currently used CI methods have limitations, such as the linear causal relations assumption and strict data distribution requirements. To tackle these challenges, we propose a framework named CausalRCA to implement fine-grained, automated, and real-time root cause localization. The CausalRCA uses a gradient-based causal structure learning method to generate weighted causal graphs and a root cause inference method to localize root cause metrics. We conduct coarse- and fine-grained root cause localization to evaluate the localization performance of CausalRCA. Experimental results show that CausalRCA has significantly outperformed baseline methods in localization accuracy, e.g., the average AC@3 of the fine-grained root cause metric localization in the faulty service is 0.719, and the average increase is 10% compared with baseline methods. In addition, the average Avg@5 has improved by 9.43%.
相關內容
Pini and Vantini (2017) introduced the interval-wise testing procedure which performs local inference for functional data defined on an interval domain, where the output is an adjusted p-value function that controls for type I errors. We extend this idea to a general setting where domain is a Riemannian manifolds. This requires new methodology such as how to define adjustment sets on product manifolds and how to approximate the test statistic when the domain has non-zero curvature. We propose to use permutation tests for inference and apply the procedure in three settings: a simulation on a "chameleon-shaped" manifold and two applications related to climate change where the manifolds are a complex subset of $S^2$ and $S^2 \times S^1$, respectively. We note the tradeoff between type I and type II errors: increasing the adjustment set reduces the type I error but also results in smaller areas of significance. However, some areas still remain significant even at maximal adjustment.
Diffusion models are a class of probabilistic generative models that have been widely used as a prior for image processing tasks like text conditional generation and inpainting. We demonstrate that these models can be adapted to make predictions and provide uncertainty quantification for chaotic dynamical systems. In these applications, diffusion models can implicitly represent knowledge about outliers and extreme events; however, querying that knowledge through conditional sampling or measuring probabilities is surprisingly difficult. Existing methods for conditional sampling at inference time seek mainly to enforce the constraints, which is insufficient to match the statistics of the distribution or compute the probability of the chosen events. To achieve these ends, optimally one would use the conditional score function, but its computation is typically intractable. In this work, we develop a probabilistic approximation scheme for the conditional score function which provably converges to the true distribution as the noise level decreases. With this scheme we are able to sample conditionally on nonlinear userdefined events at inference time, and matches data statistics even when sampling from the tails of the distribution.
We study the problem of model selection in causal inference, specifically for the case of conditional average treatment effect (CATE) estimation under binary treatments. Unlike model selection in machine learning, there is no perfect analogue of cross-validation as we do not observe the counterfactual potential outcome for any data point. Towards this, there have been a variety of proxy metrics proposed in the literature, that depend on auxiliary nuisance models estimated from the observed data (propensity score model, outcome regression model). However, the effectiveness of these metrics has only been studied on synthetic datasets as we can access the counterfactual data for them. We conduct an extensive empirical analysis to judge the performance of these metrics introduced in the literature, and novel ones introduced in this work, where we utilize the latest advances in generative modeling to incorporate multiple realistic datasets. Our analysis suggests novel model selection strategies based on careful hyperparameter tuning of CATE estimators and causal ensembling.
Latent dynamical models are commonly used to learn the distribution of a latent dynamical process that represents a sequence of noisy data samples. However, producing samples from such models with high fidelity is challenging due to the complexity and variability of latent and observation dynamics. Recent advances in diffusion-based generative models, such as DDPM and NCSN, have shown promising alternatives to state-of-the-art latent generative models, such as Neural ODEs, RNNs, and Normalizing flow networks, for generating high-quality sequential samples from a prior distribution. However, their application in modeling sequential data with latent dynamical models is yet to be explored. Here, we propose a novel latent variable model named latent dynamical implicit diffusion processes (LDIDPs), which utilizes implicit diffusion processes to sample from dynamical latent processes and generate sequential observation samples accordingly. We tested LDIDPs on synthetic and simulated neural decoding problems. We demonstrate that LDIDPs can accurately learn the dynamics over latent dimensions. Furthermore, the implicit sampling method allows for the computationally efficient generation of high-quality sequential data samples from the latent and observation spaces.
A Digital Twin (DT) is a virtual replica of a physical object or system, created to monitor, analyze, and optimize its behavior and characteristics. A Spatial Digital Twin (SDT) is a specific type of digital twin that emphasizes the geospatial aspects of the physical entity, incorporating precise location and dimensional attributes for a comprehensive understanding within its spatial environment. The current body of research on SDTs primarily concentrates on analyzing their potential impact and opportunities within various application domains. As building an SDT is a complex process and requires a variety of spatial computing technologies, it is not straightforward for practitioners and researchers of this multi-disciplinary domain to grasp the underlying details of enabling technologies of the SDT. In this paper, we are the first to systematically analyze different spatial technologies relevant to building an SDT in layered approach (starting from data acquisition to visualization). More specifically, we present the key components of SDTs into four layers of technologies: (i) data acquisition; (ii) spatial database management \& big data analytics systems; (iii) GIS middleware software, maps \& APIs; and (iv) key functional components such as visualizing, querying, mining, simulation and prediction. Moreover, we discuss how modern technologies such as AI/ML, blockchains, and cloud computing can be effectively utilized in enabling and enhancing SDTs. Finally, we identify a number of research challenges and opportunities in SDTs. This work serves as an important resource for SDT researchers and practitioners as it explicitly distinguishes SDTs from traditional DTs, identifies unique applications, outlines the essential technological components of SDTs, and presents a vision for their future development along with the challenges that lie ahead.
Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit a graph neural network (GNN) on a learnable graph to the dynamics. They use one-step message-passing GNNs -- intuitively the right choice since non-locality of multi-step or spectral GNNs may confuse direct and indirect interactions. But the \textit{effective} interaction graph depends on the sampling rate and it is rarely localized to direct neighbors, leading to local minima for the one-step model. In this work, we propose a \textit{dynamical graph prior} (DYGR) for relational inference. The reason we call it a prior is that, contrary to established practice, it constructively uses error amplification in high-degree non-local polynomial filters to generate good gradients for graph learning. To deal with non-uniqueness, DYGR simultaneously fits a ``shallow'' one-step model with shared graph topology. Experiments show that DYGR reconstructs graphs far more accurately than earlier methods, with remarkable robustness to under-sampling. Since appropriate sampling rates for unknown dynamical systems are not known a priori, this robustness makes DYGR suitable for real applications in scientific machine learning.
Inspired by the remarkable success of artificial neural networks across a broad spectrum of AI tasks, variational quantum circuits (VQCs) have recently seen an upsurge in quantum machine learning applications. The promising outcomes shown by VQCs, such as improved generalization and reduced parameter training requirements, are attributed to the robust algorithmic capabilities of quantum computing. However, the current gradient-based training approaches for VQCs do not adequately accommodate the fact that trainable parameters (or weights) are typically used as angles in rotational gates. To address this, we extend the concept of weight re-mapping for VQCs, as introduced by K\"olle et al. (2023). This approach unambiguously maps the weights to an interval of length $2\pi$, mirroring data rescaling techniques in conventional machine learning that have proven to be highly beneficial in numerous scenarios. In our study, we employ seven distinct weight re-mapping functions to assess their impact on eight classification datasets, using variational classifiers as a representative example. Our results indicate that weight re-mapping can enhance the convergence speed of the VQC. We assess the efficacy of various re-mapping functions across all datasets and measure their influence on the VQC's average performance. Our findings indicate that weight re-mapping not only consistently accelerates the convergence of VQCs, regardless of the specific re-mapping function employed, but also significantly increases accuracy in certain cases.
Spatio-temporal forecasting is challenging attributing to the high nonlinearity in temporal dynamics as well as complex location-characterized patterns in spatial domains, especially in fields like weather forecasting. Graph convolutions are usually used for modeling the spatial dependency in meteorology to handle the irregular distribution of sensors' spatial location. In this work, a novel graph-based convolution for imitating the meteorological flows is proposed to capture the local spatial patterns. Based on the assumption of smoothness of location-characterized patterns, we propose conditional local convolution whose shared kernel on nodes' local space is approximated by feedforward networks, with local representations of coordinate obtained by horizon maps into cylindrical-tangent space as its input. The established united standard of local coordinate system preserves the orientation on geography. We further propose the distance and orientation scaling terms to reduce the impacts of irregular spatial distribution. The convolution is embedded in a Recurrent Neural Network architecture to model the temporal dynamics, leading to the Conditional Local Convolution Recurrent Network (CLCRN). Our model is evaluated on real-world weather benchmark datasets, achieving state-of-the-art performance with obvious improvements. We conduct further analysis on local pattern visualization, model's framework choice, advantages of horizon maps and etc.
Causal inference is a critical research topic across many domains, such as statistics, computer science, education, public policy and economics, for decades. Nowadays, estimating causal effect from observational data has become an appealing research direction owing to the large amount of available data and low budget requirement, compared with randomized controlled trials. Embraced with the rapidly developed machine learning area, various causal effect estimation methods for observational data have sprung up. In this survey, we provide a comprehensive review of causal inference methods under the potential outcome framework, one of the well known causal inference framework. The methods are divided into two categories depending on whether they require all three assumptions of the potential outcome framework or not. For each category, both the traditional statistical methods and the recent machine learning enhanced methods are discussed and compared. The plausible applications of these methods are also presented, including the applications in advertising, recommendation, medicine and so on. Moreover, the commonly used benchmark datasets as well as the open-source codes are also summarized, which facilitate researchers and practitioners to explore, evaluate and apply the causal inference methods.
In recent years, mobile devices have gained increasingly development with stronger computation capability and larger storage. Some of the computation-intensive machine learning and deep learning tasks can now be run on mobile devices. To take advantage of the resources available on mobile devices and preserve users' privacy, the idea of mobile distributed machine learning is proposed. It uses local hardware resources and local data to solve machine learning sub-problems on mobile devices, and only uploads computation results instead of original data to contribute to the optimization of the global model. This architecture can not only relieve computation and storage burden on servers, but also protect the users' sensitive information. Another benefit is the bandwidth reduction, as various kinds of local data can now participate in the training process without being uploaded to the server. In this paper, we provide a comprehensive survey on recent studies of mobile distributed machine learning. We survey a number of widely-used mobile distributed machine learning methods. We also present an in-depth discussion on the challenges and future directions in this area. We believe that this survey can demonstrate a clear overview of mobile distributed machine learning and provide guidelines on applying mobile distributed machine learning to real applications.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191