YZYang Zhang

Yang Zhang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yang Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Collaborative Knowledge Distillation and Reinforcement Learning for Automated Ticket Triage in Large-Scale Production Systems

    by Ruowei Fu, Yang Zhang, Shenglin Zhang, Xin Wu, Wenwei Gu, Feng Wang, Zeyu Che, Xiaozhou Liu, Yongqian Sun, Yu Zhang

    In large-scale enterprise environments, growing system complexity makes failures inevitable, threatening business continuity and customer satisfaction. To maintain system stability, efficient ticket triage is crucial for timely incident resolution. However, it remains a knowledge-intensive task requiring substantial domain expertise and detailed analysis, revealing the limitations of traditional rule-based and text-based methods. Recent advances in large language models (LLMs) offer new possibilities for automating triage through their remarkable reasoning and language capabilities. Yet, in industrial settings, LLMs often struggle to leverage domain-knowledge essential for accurate triage. We present CoTriage , a practical and scalable end-to-end automated ticket triage system, designed and deployed for real-world industrial scenarios. CoTriage leverages novel collaboration between large and small models: a small set of labeled tickets is used to distill high-quality LLM reasoning into a lightweight model, which is further optimized through a self-reinforcement mechanism. The refined triager then acts as a reward model to fine-tune a ticket summarizer using reinforcement learning. Comprehensive experiments conducted in the production environment of ByteDance, a leading global online video service provider, demonstrate the effectiveness of CoTriage, reducing the average triage time to 15.0 seconds and significantly enhancing operational efficiency and accelerating incident resolution in practice.


  • Open Access

    Expanding Guard Reach: Online Learning-Driven Incremental Kernel Panic Diagnosis

    by Yicheng Sui, Xiaotian Wang, Hailin Zhang, Shenglin Zhang, Binhong Jiang, Heng Zheng, Yongqian Sun, Yuzhi Zhang, Yang Zhang, Xin Wu, et al.

  • Open Access

    FaultInsight: Interpreting Hyperscale Data Center Host Faults

    by Tingzhu Bi, Zhang Yang, Yicheng Pan, Yu Zhang, Meng Ma, Xinrui Jiang, Linlin Han, Feng Wang, Xian Liu, Ping Wang

    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.


  • Open Access

    HEAL: Performance Troubleshooting Deep inside Data Center Hosts

    by Yicheng Pan, Yang Zhang, Tingzhu Bi, Linlin Han, Yu Zhang, Meng Ma, Xiangzhuang Shen, Xinrui Jiang, Feng Wang, Xian Liu, et al.

    This study demonstrates the salient facts and challenges of host failure operations in hyperscale data centers. A host incident can involve hundreds of distinct host-level metrics. The faulting mechanism inside the host connects these heterogeneous metrics through direct and indirect correlation, making it extremely difficult to sort out the propagation procedures and the root cause from these intertwined indicators. To deeply understand the failure mechanism inside the host, we develop HEAL -- a novel host metrics analysis toolkit. HEAL discovers dynamic causality in sparse heterogeneous host metrics by combining the strengths of both time series and random variable analysis. It also extracts causal directional hints from causality's asymmetry and historical knowledge, which finally help HEAL produce accurate results given undesirable inputs. Evaluations in our production environment verify that HEAL provides significantly better result accuracy and full-process interpretability than the SOTA baselines. With these advantages, HEAL successfully serves our data center and worldwide product operations and impressively contributes to many other workflows.

  • Open Access

    HEAL: Performance Troubleshooting Deep inside Data Center Hosts

    by Yicheng Pan, Yang Zhang, Tingzhu Bi, Linlin Han, Yu Zhang, Meng Ma, Xiangzhuang Shen, Xinrui Jiang, Feng Wang, Xian Liu, et al.

    This study demonstrates the salient facts and challenges of host failure operations in hyperscale data centers. A host incident can involve hundreds of distinct host-level metrics. The faulting mechanism inside the host connects these heterogeneous metrics through direct and indirect correlation, making it extremely difficult to sort out the propagation procedures and the root cause from these intertwined indicators. To deeply understand the failure mechanism inside the host, we develop HEAL -- a novel host metrics analysis toolkit. HEAL discovers dynamic causality in sparse heterogeneous host metrics by combining the strengths of both time series and random variable analysis. It also extracts causal directional hints from causality's asymmetry and historical knowledge, which finally help HEAL produce accurate results given undesirable inputs. Evaluations in our production environment verify that HEAL provides significantly better result accuracy and full-process interpretability than the SOTA baselines. With these advantages, HEAL successfully serves our data center and worldwide product operations and impressively contributes to many other workflows.

  • Open Access

    HEAL: Performance Troubleshooting Deep inside Data Center Hosts

    by Yicheng Pan, Yang Zhang, Tingzhu Bi, Linlin Han, Yu Zhang, Meng Ma, Xiangzhuang Shen, Xinrui Jiang, Feng Wang, Xian Liu, et al.

    This study demonstrates the salient facts and challenges of host failure operations in hyperscale data centers. A host incident can involve hundreds of distinct host-level metrics, covering broad aspects. The faulting mechanism inside the host connects these heterogeneous metrics through direct and indirect correlation, making it extremely difficult to sort out the propagation procedures and the root cause from these intertwined indicators. To deeply understand the failure mechanism inside the host, we develop HEAL -- a novel host metrics analysis toolkit. HEAL synergistically discovers dynamic causality in sparse heterogeneous host metrics by combining the strengths of both time series and random variable analysis. It can also proactively extract causal directional hints from causality's asymmetry and historical knowledge. Together, these breakthroughs help HEAL produce accurate results given undesirable inputs. Extensive experiments in our production environment verify that HEAL provides significantly better result accuracy and full-process interpretability than the SOTA baselines. With these advantages, HEAL successfully serves our data center and worldwide product operations and impressively contributes to many other workflows.