Microservice architectures in modern software engineering generate vast quantities of heterogeneous metrics, making fault diagnosis notoriously difficult. Conventional root cause analysis (RCA) methods often struggle with high-dimensional, diverse data where only a small subset of metrics may truly drive the observed failures. In this paper, we propose CAVIAR (Causality-based Analysis via VAE and ICA for Anomaly Root-cause), a two-phase framework for interpretable RCA in large-scale microservice systems. First, we train a variational autoencoder (VAE) enhanced with Independent Component Analysis (ICA) principles to learn a low-dimensional, disentangled representation of normal microservice operation. By enforcing independence among latent variables, we discover semantically coherent factors, such as specific service loads or network-level conditions. Second, when a fault occurs, we treat anomalies as external interventions on some latent factor and optimize an interventional matrix to identify the culprit dimension. This factor is then mapped back to the original metrics for actionable diagnostics.

In this article, the popularly discussed topic, i.e., how to construct available theoretical networked models that certainly capture some structural features popularly observed on realistic networks, is still our focus. Specifically, we first propose an evolving deterministic network \(N(t)\) using three types of growth ways. Then, we study some topological structural parameters including degree distribution, diameter, and clustering coefficient on network \(N(t)\) . The results demonstrate that the proposed network has scale-free feature and small-world property. In the meantime, we obtain an interesting finding, i.e., the first handshake between Fibonacci series and the “pure” preferential attachment mechanism. Next, we enumerate spanning trees on network \(N(t)\) and derive the closed-form solution of spanning trees number. Second, we introduce randomness into the growth process of network \(N(t)\) to further establish evolving stochastic networks \(\mathfrak{N}(t)\) that follow the same degree distribution as network \(N(t)\) and also determine some topological structural parameters so as to investigate effect of randomness on structural properties. We show analytically that such a randomization approach makes the resulting stochastic networks not only to greatly inherit some fundamental structural properties from deterministic network \(N(t)\) but also to considerably improve the robustness of network when encountering deliberate removal of edge. Lastly, we list out some open problems.

Operating and maintaining hyperscale data centers involving millions of service hosts has been an extremely intricate task to tackle for top Internet companies.Incessant system failures cost operators countless hours of browsing through performance metrics to diagnose the underlying root cause to prevent the recurrence.Although many state-of-the-art (SOTA) methods have used time-series causal discovery to construct causal relationships among anomalous metrics, they only focus on homogeneous service-level performance metrics and fail to yield useful insights on heterogeneous host-level metrics.To address the challenge, this study presents FaultInsight, a highly interpretable deep causal host fault diagnosing framework that offers diagnostic insights from various perspectives to reduce human effort in troubleshooting.We evaluate FaultInsight using dozens of incidents collected from our production environment.FaultInsight provides markedly better root cause identification accuracy than SOTA baselines in our incident dataset.It also shows outstanding advantages in terms of deployability in real production systems.Our engineers are deeply impressed by FaultInsight's ability to interpret incidents from multiple perspectives, helping them quickly understand the mechanism behind the faults.

Scale-free networks are prevalently observed in a great variety of complex systems, which triggers various researches relevant to networked models of such type. In this work, we propose a family of growth tree networks \(\mathcal{T}_{t}\) , which turn out to be scale-free, in an iterative manner. As opposed to most of published tree models with scale-free feature, our tree networks have the power-law exponent \(\gamma=1{ + }\ln 5/\ln 2\) that is obviously larger than \(3\) . At the same time, “small-world” property can not be found particularly because models \(\mathcal{T}_{t}\) have an ultra-large diameter \(D_{t}\) (i.e., \(D_{t}\sim|\mathcal{T}_{t}|^{\ln 3/\ln 5}\) ) and a greater average shortest path length \(\langle\mathcal{W}_{t}\rangle\) (namely, \(\langle\mathcal{W}_{t}\rangle\sim|\mathcal{T}_{t}|^{\ln 3/\ln 5}\) ) where \(|\mathcal{T}_{t}|\) represents vertex number. Next, we determine Pearson correlation coefficient and verify that networks \(\mathcal{T}_{t}\) display disassortative mixing structure. In addition, we study random walks on tree networks \(\mathcal{T}_{t}\) and derive exact solution to mean hitting time \(\langle\mathcal{H}_{t}\rangle\) . The results suggest that the analytic formula for quantity \(\langle\mathcal{H}_{t}\rangle\) as a function of vertex number \(|\mathcal{T}_{t}|\) shows a power-law form, i.e., \(\langle\mathcal{H}_{t}\rangle\sim|\mathcal{T}_{t}|^{1+\ln 3/\ln 5}\) . Accordingly, we execute extensive experimental simulations, and demonstrate that empirical analysis is in strong agreement with theoretical results. Lastly, we provide a guide to extend the proposed iterative manner in order to generate more general scale-free tree networks with large diameter.

Since the proposal of Granger causality, many researchers have followed the idea and developed extensions to the original algorithm. The classic Granger causality test aims to detect the existence of the static causal relationship. Notably, a fundamental assumption underlying most previous studies is the stationarity of causality, which requires the causality between variables to keep stable. However, this study argues that it is easy to break in real-world scenarios. Fortunately, our paper presents an essential observation: if we consider a sufficiently short window when discovering the rapidly changing causalities, they will keep approximately static and thus can be detected using the static way correctly. In light of this, we develop EffCause, bringing dynamics into classic Granger causality. Specifically, to efficiently examine the causalities on different sliding window lengths, we design two optimization schemes in EffCause and demonstrate the advantage of EffCause through extensive experiments on both simulated and real-world datasets. The results validate that EffCause achieves state-of-the-art accuracy in continuous causal discovery tasks while achieving faster computation. Case studies from cloud system failure analysis and traffic flow monitoring show that EffCause effectively helps us understand real-world time-series data and solve practical problems.

As known, the commonly-utilized ways to determine mean first-passage time F for random walk on networks are mainly based on Laplacian spectra. However, methods of this type can become prohibitively complicated and even fail to work when the Laplacian matrix of network under consideration is difficult to describe in the first place. In this paper, we propose an effective approach to determining quantity F on some widely-studied tree networks. To this end, we first build up a general formula between Wiener index W and F on a tree. This enables us to convert issues to answer into calculation of W on networks in question. As opposed to most of previous work focusing on deterministic growth trees, our goal is to consider stochastic case. Towards this end, we establish a principled framework where randomness is introduced into the process of growing trees. As an immediate consequence, the previously published results upon deterministic cases are thoroughly covered by formulas established in this paper. Additionally, it is also straightforward to obtain Kirchhoff index on our tree networks using the proposed approach. Most importantly, our approach is more manageable than some other methods including spectral technique in situations considered herein

Intensive monitoring and anomaly diagnosis have become a knotty problem for modern microservice architecture due to the dynamics of service dependency. While most previous studies rely heavily on ample monitoring metrics, we raise a fundamental but always neglected issue - the diagnostic metric integrity problem. This paper solves the problem by proposing MicroCU – a novel approach to diagnose microservice systems using very sparse API logs. We design a structure named dynamic causal curves to portray time-varying service dependencies and a temporal dynamics discovery algorithm based on Granger causal intervals. Our algorithm generates a smoother space of causal curves and designs the concept of causal unimodalization to calibrate the causality infidelities brought by missing metrics. Finally, a path search algorithm on dynamic causality graphs is proposed to pinpoint the root cause. Experiments on commercial system cases show that MicroCU outperforms many state-of-the-art approaches and reflects the superiorities of causal unimodalization to raw metric imputation.

In this work, we propose a principled framework using Vertex-based and Edge-based uniform generation mechanisms to build stochastic uniform growth tree networks that have a wide range of applications in various fields including physics, engineering, chemistry, ect., and then uncover the associated structural features analytically. When considering vertex-degree distribution, there exist three different classes of forms in the thermodynamic limit, i.e., exponential distribution, power-law distribution along with multiple-point distribution. At meantime, three distinct structural shapes are observed in the study of fractal phenomena, that is, fractal feature, critical phenomenon and non-fractal property. In addition, we obtain the analytical solution to fractal dimension for fractal structure from the probability point of view. More importantly, some well-known models, for instance, Vicsek fractal and T-graph, fall into our framework. Next, we precisely consider two families of stochastic uniform growth tree networks generated through the proposed framework. Specifically, we derive the analytic solution to mean hitting time$\langle \mathcal {H}\rangle$for measuring efficiency of delivering information on networks in a random-walk-based manner, and find that the introduction of randomness certainly enriches the scaling exponent of quantity$\langle \mathcal {H}\rangle$. Finally, we conduct extensive experiments, which suggests that computer simulations are in good agreement with theoretical analysis.

Geodesic distance, sometimes called shortest path length, has proven useful in a great variety of applications, such as information retrieval on networks including treelike networked models. Here, our goal is to analytically determine the exact solutions to geodesic distances on two different families of growth trees which are recursively created upon an arbitrary tree$\mathcal {T}$using two types of well-known operations, first-order subdivision and ($1,m$)-star-fractal operation. Different from commonly-used methods, for instance, spectral techniques, for addressing such a problem on growth trees using a single edge as seed in the literature, we propose a novel method for deriving closed-form solutions on the presented trees completely. Meanwhile, our technique is more general and convenient to implement compared to those previous methods mainly because there are not complicated calculations needed. In addition, the closed-form expression of mean first-passage time ($MFPT$) for random walk on each member in tree families is also readily obtained according to connection of our obtained results to effective resistance of corresponding electric networks. The results suggest that the two topological operations above are sharply different from each other due to$MFPT$for random walks, and, however, have likely to show the similar performance, at least, on geodesic distance.

Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine which visual features are most characteristic of the considered categories. To alleviate this issue, we propose a method that additionally takes into account the names of the image classes. While the use of class names has already been explored in previous work, our approach differs in two key aspects. First, while previous work has aimed to directly predict visual prototypes from word embeddings, we found that better results can be obtained by treating visual and text-based prototypes separately. Second, we propose a simple strategy for learning class name embeddings using the BERT language model, which we found to substantially outperform the GloVe vectors that were used in previous work. We furthermore propose a strategy for dealing with the high dimensionality of these vectors, inspired by models for aligning cross-lingual word embeddings. We provide experiments on miniImageNet, CUB and tieredImageNet, showing that our approach consistently improves the state-of-the-art in metric-based FSL.

Scene text recognition (STR) has experienced increasing popularity both in academia and in industry. Regarding STR as a sequence prediction task, most state-of-the-art (SOTA) approaches employ the attention-based encoder-decoder architecture to recognize texts. However, these methods still struggle in localizing the precise alignment center associated with the current character, which is also named as the attention drift phenomenon. One major reason is that directly converting low-quality or distorted word images to sequential features may introduce confusing information and thus mislead the network. To address the problem, this paper proposes a cascade attention network. The model is composed of three novel attention modules: a vanilla attention module that attends to sequential features from the horizontal direction, a cross-network attention module to take advantage of both one-dimension contextual information and two-dimension visual distributions, and an aspects fusion attention module to fuse spatial and channel-wise information. Accordingly, the network manages to yield distinguished and refined representations correlated to the target sequence. Compared to SOTA methods, experimental results on seven benchmarks demonstrate the superiority of our framework in recognizing scene texts on various conditions.

The high complexity and dynamics of the microservice architecture make its application diagnosis extremely challenging. Static troubleshooting approaches may fail to obtain reliable model applies for frequently changing situations. Even if we know the calling dependency of services, we lack a more dynamic diagnosis mechanism due to the existence of indirect fault propagation. Besides, algorithm based on single metric usually fail to identify the root cause of anomaly, as single type of metric is not enough to characterize the anomalies occur in diverse services. In view of this, we design a novel tool, named AutoMAP, which enables dynamic generation of service correlations and automated diagnosis leveraging multiple types of metrics. In AutoMAP, we propose the concept of anomaly behavior graph to describe the correlations between services associated with different types of metrics. Two binary operations, as well as a similarity function on behavior graph are defined to help AutoMAP choose appropriate diagnosis metric in any particular scenario. Following the behavior graph, we design a heuristic investigation algorithm by using forward, self, and backward random walk, with an objective to identify the root cause services. To demonstrate the strengths of AutoMAP, we develop a prototype and evaluate it in both simulated environment and real-work enterprise cloud system. Experimental results clearly indicate that AutoMAP achieves over 90% precision, which significantly outperforms other selected baseline methods. AutoMAP can be quickly deployed in a variety of microservice-based systems without any system knowledge. It also supports introduction of various expert knowledge to improve accuracy.