Kingsum Chow

Zhichao Sun, Hailiang Zhao, Kingsum Chow

Cloud-Native microservice architectures have become prevalent owing to their inherent flexibility and scalability properties. To satisfy service quality guarantees, cloud providers must implement efficient proactive autoscaling algorithms. However, effective proactive scaling critically depends on accurately estimating end-to-end latency under given resource quotas, which remains highly challenging. Existing methods struggle with the multi-hierarchical nature and dynamic operational contexts of microservice systems. They primarily employ single-scale modeling that fails to capture inherent organizational structures and lacks adaptability to varying workload types. To address these limitations, we propose MSGAF, a Multi-Scale Graph Adaptive Fusion framework with Scene-Aware Learning for microservice latency estimation. Our approach constructs hierarchical graph representations through learnable aggregation-based coarsening, capturing system behaviors across microscopic, mesoscopic, and macroscopic levels. The framework comprises three components: a system state encoding module transforming heterogeneous monitoring data into unified representations, a multi-scale graph adaptive fusion module leveraging graph attention networks for hierarchical feature extraction, and a scene-aware learning module employing specialized expert networks with dynamic weight allocation for context-specific estimation. Additionally, we design and implement a comprehensive non-intrusive monitoring system for real-time data collection. Extensive experiments on benchmark microservice applications demonstrate that MSGAF significantly outperforms state-of-the-art methods across diverse operational scenarios, providing substantial improvements for cloud-native performance optimization.

Zhiwei Ling, Yachen Chang, Hailiang Zhao et al.

Deep neural networks (DNNs) have been widely criticized for their overconfidence when dealing with out-of-distribution (OOD) samples, highlighting the critical need for effective OOD detection to ensure the safe deployment of DNNs in real-world settings. Existing post-hoc OOD detection methods primarily enhance the discriminative power of logit-based approaches by reshaping sample features, yet they often neglect critical information inherent in the features themselves. In this paper, we propose the Class-Aware Relative Feature-based method (CARef), which utilizes the error between a sample's feature and its class-aware average feature as a discriminative criterion. To further refine this approach, we introduce the Class-Aware Decoupled Relative Feature-based method (CADRef), which decouples sample features based on the alignment of signs between the relative feature and corresponding model weights, enhancing the discriminative capabilities of CARef. Extensive experimental results across multiple datasets and models demonstrate that both proposed methods exhibit effectiveness and robustness in OOD detection compared to state-of-the-art methods. Specifically, our two methods outperform the best baseline by 2.82% and 3.27% in AUROC, with improvements of 4.03% and 6.32% in FPR95, respectively.

Zhiwei Ling, Hailiang Zhao, Chao Zhang et al.

Federated Learning (FL) enables collaborative model training across large-scale distributed service nodes while preserving data privacy, making it a cornerstone of intelligent service systems in edge-cloud environments. However, in real-world service-oriented deployments, data generated by heterogeneous users, devices, and application scenarios are inherently non-IID. This severe data heterogeneity critically undermines the convergence stability, generalization ability, and ultimately the quality of service delivered by the global model. To address this challenge, we propose FLood, a novel FL framework inspired by out-of-distribution (OOD) detection. FLood dynamically counteracts the adverse effects of heterogeneity through a dual-weighting mechanism that jointly governs local training and global aggregation. At the client level, it adaptively reweights the supervised loss by upweighting pseudo-OOD samples, thereby encouraging more robust learning from distributionally misaligned or challenging data. At the server level, it refines model aggregation by weighting client contributions according to their OOD confidence scores, prioritizing updates from clients with higher in-distribution consistency and enhancing the global model's robustness and convergence stability. Extensive experiments across multiple benchmarks under diverse non-IID settings demonstrate that FLood consistently outperforms state-of-the-art FL methods in both accuracy and generalization. Furthermore, FLood functions as an orthogonal plug-in module: it seamlessly integrates with existing FL algorithms to boost their performance under heterogeneity without modifying their core optimization logic. These properties make FLood a practical and scalable solution for deploying reliable intelligent services in real-world federated environments.

Peng Chen, Jiaji Zhang, Hailiang Zhao et al.

In modern GPU inference, cache efficiency remains a major bottleneck. In recommendation models, embedding hit rates largely determine throughput, while in large language models, KV-cache misses substantially increase time-to-first-token (TTFT). Heuristic policies such as \textsc{LRU} often struggle under structured access patterns. Learning-based approaches are promising, but in practice face two major limitations: they degrade sharply when predictions are inaccurate, or they gain little even with accurate predictions due to conservative designs. Some also incur high overhead, further limiting practicality. We present \textsc{LCR}, a practical framework for learning-based GPU caching that delivers performance gains while ensuring robustness and efficiency. Its core algorithm, \textsc{LARU}, enhances \textsc{LRU} with machine-learned predictions and dynamically adapts to prediction accuracy through online error estimation. When predictions are accurate, \textsc{LARU} achieves near-optimal performance. With inaccurate predictions, it degrades gracefully to near-\textsc{LRU} performance. With \textsc{LCR}, we bridge the gap between empirical progress and theoretical advances in learning-based caching. Experiments show that \textsc{LCR} delivers consistent gains under realistic conditions. In DLRM and LLM scenarios, it improves throughput by up to 24.2\% and reduces P99 TTFT by up to 28.3\%, outperforming widely used inference systems. Even under poor predictions, its performance remains stable, demonstrating practical robustness.

Wenzhuo Qian, Hailiang Zhao, Tianlv Chen et al.

Microservice architectures have become the de facto standard for building scalable cloud-native applications, yet their distributed nature introduces significant challenges in performance monitoring and resource management. Traditional approaches often rely on per-request latency metrics, which are highly sensitive to transient noise and fail to reflect the holistic behavior of complex, concurrent workloads. In contrast, window-level P95 tail latency provides a stable and meaningful signal that captures both system-wide trends and user-perceived performance degradation. We identify two key shortcomings in existing methods: (i) inadequate handling of heterogeneous data, where traffic-side features propagate across service dependencies and resource-side signals reflect localized bottlenecks, and (ii) the lack of principled architectural designs that effectively distinguish and integrate these complementary modalities. To address these challenges, we propose USRFNet, a deep learning network that explicitly separates and models traffic-side and resource-side features. USRFNet employs GNNs to capture service interactions and request propagation patterns, while gMLP modules independently model cluster resource dynamics. These representations are then fused into a unified system embedding to predict window-level P95 latency with high accuracy. We evaluate USRFNet on real-world microservice benchmarks under large-scale stress testing conditions, demonstrating substantial improvements in prediction accuracy over state-of-the-art baselines.

Jiaji Zhang, Ruichao Sun, Hailiang Zhao et al.

Diffusion models have demonstrated exceptional generative capabilities but are computationally intensive, posing significant challenges for deployment in resource-constrained or latency-sensitive environments. Quantization offers an effective means to reduce model size and computational cost, with post-training quantization (PTQ) being particularly appealing due to its compatibility with pre-trained models without requiring retraining or training data. However, existing PTQ methods for diffusion models often rely on architecture-specific heuristics that limit their generalizability and hinder integration with industrial deployment pipelines. To address these limitations, we propose SegQuant, a unified quantization framework that adaptively combines complementary techniques to enhance cross-model versatility. SegQuant consists of a segment-aware, graph-based quantization strategy (SegLinear) that captures structural semantics and spatial heterogeneity, along with a dual-scale quantization scheme (DualScale) that preserves polarity-asymmetric activations, which is crucial for maintaining visual fidelity in generated outputs. SegQuant is broadly applicable beyond Transformer-based diffusion models, achieving strong performance while ensuring seamless compatibility with mainstream deployment tools.