Ensuring reliable operation of cloud networks is critical for cloud service providers to guarantee quality of service for tenants. A promising solution is to design a high-fidelity cloud network validation platform that proactively validates the correctness of all operations before implementing changes to the production network. However, the tight coupling between physical and virtual networks in the cloud poses challenges to achieving high-fidelity cloud network validation. Existing network validation platforms focus primarily on traditional physical networks, while ignoring virtual network validation. Regrettably, neglecting the combined validation of physical and virtual networks will result in inaccurate evaluations. To bridge this gap, we present HifiCNet, a high-fidelity platform that concurrently validates both physical and virtual networks. HifiCNet designs an orchestrator to elegantly coordinate the interaction between physical and virtual networks in the cloud and innovatively adopts an emulator-simulator hybrid architecture to ensure high fidelity and scalability for cloud network validation. Through extensive evaluation based on real topologies and traffic traces, we show that HifiCNet enables high-fidelity validation of cloud network configurations, services, and exceptions. Notably, HifiCNet can leverage 38 servers to establish a physical network comprising 10k hosts, as well as a virtual network consisting of 200k virtual machines.

Visual pattern recognition usually plays important roles in robotics and automation society where the pattern recognition relies on representation learning. Existing representation learning often neglects two important issues, the diversity of intra-class representation and under-exploited label utilization, especially the negative feedback during training process. Fortunately, prototype learning potentially raises label utilization and encourages intra-class diversity. In this paper, we investigate the intra-class diversity and effective updates in prototype learning for enhanced visual pattern recognition. Specifically, we propose a Label-aware multi-Prototype learning, LamPro, by incorporating the label awareness into both prototype formation and update to improve the representation quality. Firstly, we design a supervised contrastive learning to achieve class-discriminative representations. Secondly, we randomly initialize multiple prototypes and update the nearest prototype upon the arrival of instance, to preserve intra-class diversity. Thirdly, we propose a novel Label-guided Adaptive Updating. We separate the prototype updates from the representation optimization and exploit the label indexes to directly implement the prediction feedback. To correct the model optimization directions, we identify the negative feedback, and correct the prototype updates via queries of labels. Finally, we design a memory-based counter to alternately update these deviated prototypes. Experiments verify the effectiveness of our label-aware and joint multi-prototype updating strategies.

Real-world data tends to follow a long-tailed distribution, which greatly challenges the robustness of algorithms. Current long-tailed learning methods usually focus on devising exquisite re-sampling strategies or innovative loss functions to address the class-wise imbalance, yet rarely pay attention to the pervasive problem of attribute imbalance within classes. That is to say, attribute imbalance naturally exists in class imbalance, which brings more complex challenges to current long-tailed learning. In this work, we propose an attribute rebalancing strategy to address imbalance in imbalance. First, we propose attribute-balanced re-sampling, which potentially re-samples the attributes within the class during up/down-sampling to avoid damage to rare attributes. Then, we design an attribute-constrained loss to trade off the intertwined imbalances in class and attribute levels. Comprehensive experiments show that attribute rebalancing can consistently perform well on generalized long-tailed benchmark datasets.

With the advancement of Deep Learning, the performance of speech translation systems has made remarkable progress. However, similar to traditional software, speech translation systems can still suffer from software defects that can lead to incorrect translations with potentially serious consequences. These systems are also vulnerable to real-world environmental interference, making their behavior unpredictable. The black-box nature of deep neural networks renders traditional testing methods ineffective, while the lack of diverse test cases and the challenge of constructing test oracles further hinder the implementation of their testing. To address this, we introduce syntactic structure invariance, a linguistically inspired concept that captures the structural containment between a pair of derivationally related sentences and their corresponding translations. Based on this concept, we propose a novel speech translation testing method, SPlice. SPlice simulates environmental disturbances on a seed speech, disassembles it into a template and speech blocks, and then generates multiple derivational speech pairs by inserting the blocks back into the template. SPlice detects translation errors by checking whether the syntactic structure invariance relation is violated in the translation results corresponding to the speech pairs. To validate SPlice, we experiment with three industrial speech translation systems: Google Translate, Youdao Translator, and Iflytek Translator. With 600 speeches crawled from the BBC as seed tests, SPlice detects 1,640, 1,101, and 1,305 translation errors with around 90.7% precision. The experimental results show that SPlice can effectively detect errors in the speech translation results with high precision, providing valuable information for developers to improve system performance.

Federated Learning (FL) enables distributed clients to collaboratively train models without exposing their private data. However, it is difficult to implement efficient FL due to limited resources. Most existing works compress the transmitted gradients or prune the global model to reduce the resource cost, but leave the compressed or pruned parameters under-optimized, which degrades the training performance. To address this issue, the neural composition technique constructs size-adjustable models by composing low-rank tensors, allowing every parameter in the global model to learn the knowledge from all clients. Nevertheless, some tensors can only be optimized by a small fraction of clients, thus the global model may get insufficient training, leading to a long completion time, especially in heterogeneous edge scenarios. To this end, we enhance the neural composition technique, enabling all parameters to be fully trained. Further, we propose a lightweight FL framework, called Heroes, with enhanced neural composition and adaptive local update. A greedy-based algorithm is designed to adaptively assign the proper tensors and local update frequencies for participating clients according to their heterogeneous capabilities and resource budgets. On this basis, we further propose an extension of Heroes, termed AdaHeroes, which further improves the training performance under the statistical heterogeneity scenario based on an adaptive client selection strategy. Extensive experiments demonstrate that Heroes can reduce traffic consumption by about 72.46% and provide up to$2.76\times $speedup compared to the baselines. Furthermore, with the setting of statistical heterogeneity, AdaHeroes can improve the test accuracy by about 4.77% compared with Heroes and the baselines.

Federated learning (FL) has recently gained tremendous attention in edge computing and the Internet of Things, due to its capability of enabling clients to perform model training at the network edge or end devices (i.e., clients). However, these end devices are usually resource-constrained without the ability to train large-scale models. In order to accelerate the training of large-scale models on these devices, we incorporate Split Learning (SL) into Federated Learning (FL), and propose a novel FL framework, termedPairingFL. Specifically, we split a full model into a bottom model and a top model, and arrange participating clients into pairs, each of which collaboratively trains the two partial models as one client does in typical FL. Driven by the advantages of SL and FL, PairingFL is able to relax the computation burden on clients and protect model privacy. However, considering the features of system and statistical heterogeneity in edge networks, it is challenging to pair the clients by carefully developing the strategies of client partitioning and matching for efficient model training. To this end, we first theoretically analyze the convergence property of PairingFL, and obtain a convergence upper bound. Guided by this, we then design a greedy and efficient algorithm, which makes the joint decision of client partitioning and matching, so as to well balance the trade-off between convergence rate and model accuracy. The performance of PairingFL is evaluated through extensive simulation experiments. The experimental results demonstrate that PairingFL can speed up the training process by$4.6\times $compared to baselines when achieving the corresponding convergence accuracy.

Increased videos captured by widely deployed cameras are being analyzed by computer vision-based Deep Neural Networks (DNNs) on servers rather than being streamed for humans. Unfortunately, the conventional codecs (e.g., H.26x and MPEG-x) originally designed for video streaming lack content-aware feature extraction and hinder machine-centric video analytics, making it difficult to achieve the required high accuracy with tolerable delay. Neural codecs (e.g., autoencoder) now hold impressive compression performance and have been widely advocated in video streaming. While autoencoder shows transformative potential, the application in video analytics is hampered by low accuracy in detecting small objects of high-resolution videos and the serious challenges posed by multi-video streaming. To this end, we propose AdaStreamer with adaptive neural codecs to enable real machine-centric high-accuracy multi-video analytics. We also investigate how to achieve optimal accuracy under delay constraints via careful scheduling in Compression Ratios (CRs, the ratio of the compressed size to the original data size) and bandwidth allocation, and further propose a Markov-based Adaptive Compression and Bandwidth Allocation algorithm (MACBA). We have practically developed a prototype of AdaStreamer, based on which extensive experiments verify its accuracy improvement (up to 15%) compared to state-of-the-art coding and streaming solutions.

Recently, Hierarchical Federated Learning (HFL) stands out as a cutting-edge approach to efficiently learn knowledge from massive data on edge devices or clients. To alleviate the computation/communication burden of training large-scale models on resource-constrained clients, Hierarchical Split Federated Learning (HSFL), which splits an entire model into a top and bottom (sub-)model and offloads the training of the top model to the edge server, has been proposed. Nonetheless, there are two key issues, i.e., system heterogeneity and dynamic contexts, hindering the application of effective HSFL. In response, we present an efficient HSFL method, termed AdaHSFL, which introduces intra-cluster gradient feedback regulation and inter-cluster updating frequencies optimization to enhance training efficiency. Concretely, intra-cluster gradient feedback regulation enables edge servers to instantly process incoming smashed data and calculate gradients using top model copies on background threads, while inter-cluster updating frequencies optimization adjusts edge cluster updating frequencies to align the training duration across all clusters with that of the fastest cluster. Furthermore, AdaHSFL explores to jointly implement these two strategies to eliminate the idle waiting time both intra- and intercluster incurred by synchronization barriers. Rigorous performance evaluation demonstrates that AdaHSFL can improve the accuracy by $3.9 \%-25.5 \%$ within given time budgets, compared with the baselines.

Continuously orchestrating in-network model aggregations for federated learning faces fundamental challenges such as the combinatorial nature of traffic reduction, the dynamic trade-offs between system overhead and model convergence, and the unpredictable inputs from uncertain system environments. In this work, we model a nonlinear mixed-integer program to optimize the long-term total cost of federated learning computation overhead, traffic reduction, network delay, and programmable switch reconfigurations over time. To attack the lexicographic minimax, submodular, and online nature of this problem, we propose a polynomial-time algorithmic framework to judiciously designate the timing of reconfigurations, while designing and invoking a linearized transformation for selecting routing paths, a greedy sub-algorithm for selecting aggregation locations, and an online learning sub-algorithm for controlling federated learning convergence. We demonstrate our rigorous mathematical insights behind our algorithms, and prove the competitive ratio as the performance guarantee. Using trace-driven evaluations, we have validated our approach's superiority over existing methods.

Monitoring and anomaly detection of key performance indicators (KPIs) are crucial for large Internet companies to maintain the reliability of their Web services. Influenced by human behavior and schedules, the KPIs of Web services typically exhibit seasonal characteristics. These characteristics may be complex as different KPIs exhibit differences in trend, multiple periods, and noise behaviors. However, existing anomaly detection methods typically only model one fixed pattern of seasonal KPIs, which may lead to performance degradation when dealing with diverse seasonal KPIs. In this work, we propose a novel anomaly detection model for seasonal KPIs,Diner, which incorporates multiple interpretable components. It is able to capture the additive and multiplicative trends, multiple periods, and seasonal noise in intricate seasonal KPIs, making it easily adaptable to different types of seasonal KPIs. Additionally, we present a set of evaluation criteria for generic time series anomaly detection tasks, which prove more effective in handling ambiguous manual labels and various anomaly events. Experiments are conducted on three real-world datasets, and the performanceDinersurpassed both the statistical baseline and the state-of-the-art deep learning baselines.