Microservices improve the scalability and flexibility of monolithic architectures to accommodate the evolution of software systems, but the complexity and dynamics of microservices challenge system reliability. Ensuring microservice quality requires efficient failure diagnosis, including detection and triage. Failure detection involves identifying anomalous behavior within the system, while triage entails classifying the failure type and directing it to the engineering team for resolution. Unfortunately, current approaches reliant on single-modal monitoring data, such as metrics, logs, or traces, cannot capture all failures and neglect interconnections among multimodal data, leading to erroneous diagnoses. Recent multimodal data fusion studies struggle to achieve deep integration, limiting diagnostic accuracy due to insufficiently captured interdependencies. Therefore, we proposeUniDiag, which leverages temporal knowledge graphs to fuse multimodal data for effective failure diagnosis.UniDiagapplies a simple yet effective stream-based anomaly detection method to reduce computational cost and a novel microservice-oriented graph embedding method to represent the state of systems comprehensively. To assess the performance ofUniDiag, we conduct extensive evaluation experiments using datasets from two benchmark microservice systems, demonstrating its superiority over existing methods and affirming the efficacy of multimodal data fusion. Additionally, we have publicly made the code and data available to facilitate further research.

Abstract To improve phone screen surface detection efficiency, an optimized YOLOv5s model (OYm) based on GhostNet(YOLOv5GHOSTs) and BottleneckCSP is proposed. For a given target sample, OYm could effectively reduce the computation of GFLOPS and detection time by optimizing the network structure. The detection results show that the mean average precision_0.5 (mAP_0.5) exceeds 95%, and the average detection rate is 16 ms. Compared with the traditional YOLOv5s model, the loss of average accuracy is ensured to be controlled within 3%, the detection frame rate of OYm is risen by 56.25%, and GFLOPS is decreased by 64.2%. The principle of OYm is explained in detail, and the proposed model is then experimentally validated.

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization.Unfortunately, training a large summarization model is generally infeasible due to the inadequacy of dialogue data with annotated summaries.Most existing works for low-resource dialogue summarization directly pretrain models in other domains, e.g., the news domain, but they generally neglect the huge difference between dialogues and conventional articles.To bridge the gap between out-of-domain pretraining and indomain fine-tuning, in this work, we propose a multi-source pretraining paradigm to better leverage the external summary data.Specifically, we exploit large-scale in-domain nonsummary data to separately pretrain the dialogue encoder and the summary decoder.The combined encoder-decoder model is then pretrained on the out-of-domain summary data using adversarial critics, aiming to facilitate domain-agnostic summarization.The experimental results on two public datasets show that with only limited training data, our approach achieves competitive performance and generalizes well in different dialogue scenarios.