QUIC is expected to be a game-changer in improving web application performance. In this paper, we conduct a systematic examination of QUIC's performance over high-speed networks. We find that over fast Internet, the UDP+QUIC+HTTP/3 stack suffers a data rate reduction of up to 45.2% compared to the TCP+TLS+HTTP/2 counterpart. Moreover, the performance gap between QUIC and HTTP/2 grows as the underlying bandwidth increases. We observe this issue on lightweight data transfer clients and major web browsers (Chrome, Edge, Firefox, Opera), on different hosts (desktop, mobile), and over diverse networks (wired broadband, cellular). It affects not only file transfers, but also various applications such as video streaming (up to 9.8% video bitrate reduction) and web browsing. Through rigorous packet trace analysis and kernel- and user-space profiling, we identify the root cause to be high receiver-side processing overhead, in particular, excessive data packets and QUIC's user-space ACKs. We make concrete recommendations for mitigating the observed performance issues.

The two leading solution paradigms for imitation learning (IL), BC and GAIL, each suffers from notable drawbacks. BC, a supervised learning approach to mimic expert actions, is vulnerable to covariate shift. GAIL applies adversarial training to minimize the discrepancy between expert and learner behaviors, which is prone to unstable training and mode collapse. In this work, we propose DC – Distributional Cloning – a novel IL approach for addressing the covariate shift and mode collapse problems simultaneously. DC directly maximizes the likelihood of observed expert and learner demonstrations, and gradually encourages the learner to evolve towards expert behaviors based on an averaging effect. The DC solution framework contains two stages in each training loop, where in stage one the mixed expert and learner state distribution is estimated via SoftFlow, and in stage two the learner policy is trained to match both the expert’s policy and state distribution via ADMM. Experimental evaluation of DC compared with several baselines in 10 different physics-based control tasks reveal superior results in learner policy performance, training stability, and mode distribution preservation.

A key challenge with supervised learning (e.g., image classification) is the shift of data distribution and domain from training to testing datasets, so-called “domain shift” (or “distribution shift”), which usually leads to a reduction of model accuracy. Various meta-learning approaches have been proposed to prevent the accuracy loss by learning an adaptable model with training data, and adapting it to test time data from a new data domain. However, when the domain shift occurs in multiple domain dimensions (e.g., images may be transformed by rotations, transitions, and expansions), the average predictive power of the adapted model will deteriorate. To tackle this problem, we propose a domain disentangled meta-learning (DDML) framework. DDML disentangles the data domain by dimensions, learns the representations of domain dimensions independently, and adapts to the domain of test time data. We evaluate our DDML on image classification problems using three datasets with distribution shifts over multiple domain dimensions. Comparing to various baselines in meta-learning and empirical risk minimization, our DDML approach achieves consistently higher classification accuracy with the test time data. These results demonstrate that domain disentanglement reduces the complexity of the model adaptation, thus increases the model generalizability, and prevents it from overfitting.

Urban traffic status (e.g., traffic speed and volume) is highly dynamic in nature, namely, varying across space and evolving over time. Thus, predicting such traffic dynamics is of great importance to urban development and transportation management. However, it is very challenging to solve this problem due to spatial-temporal dependencies and traffic uncertainties. In this article, we solve the traffic dynamics prediction problem from Bayesian meta-learning perspective and propose a novel continuous spatial-temporal meta-learner (cST-ML), which is trained on a distribution of traffic prediction tasks segmented by historical traffic data with the goal of learning a strategy that can be quickly adapted to related but unseen traffic prediction tasks. cST-ML tackles the traffic dynamics prediction challenges by advancing the Bayesian black-box meta-learning framework through the following new points: (1) cST-ML captures the dynamics of traffic prediction tasks using variational inference, and to better capture the temporal uncertainties within tasks, cST-ML performs as a rolling window within each task; (2) cST-ML has novel designs in architecture, where CNN and LSTM are embedded to capture the spatial-temporal dependencies between traffic status and traffic-related features; (3) novel training and testing algorithms for cST-ML are designed. We also conduct experiments on two real-world traffic datasets (taxi inflow and traffic speed) to evaluate our proposed cST-ML. The experimental results verify that cST-ML can significantly improve the urban traffic prediction performance and outperform all baseline models especially when obvious traffic dynamics and temporal uncertainties are presented.

As mobile networks proliferate, we are experiencing a strong diversification of services, which requires greater flexibility from the existing network. Network slicing is proposed as a promising solution for resource utilization in 5G and future networks to address this dire need. In network slicing, dynamic resource orchestration and network slice management are crucial for maximizing resource utilization. Unfortunately, this process is too complex for traditional approaches to be effective due to a lack of accurate models and dynamic hidden structures. We formulate the problem as a Constrained Markov Decision Process (CMDP) without knowing models and hidden structures. Additionally, we propose to solve the problem using CLARA, a Constrained reinforcement LeArning based Resource Allocation algorithm. In particular, we analyze cumulative and instantaneous constraints using adaptive interior-point policy optimization and projection layer, respectively. Evaluations show that CLARA clearly outperforms baselines in resource allocation with service demand guarantees.

Content Delivery Networks (CDNs) are critical for providing good user experience of cloud services. CDN providers typically collect various multivariate Key Performance Indicators (KPIs) time series to monitor and diagnose system performance. State-of-the-art anomaly detection methods mostly use deep learning to extract the normal patterns of data, due to its superior performance. However, KPI data usually exhibit non-additive Gaussian noise, which makes it difficult for deep learning models to learn the normal patterns, resulting in degraded performance in anomaly detection. In this paper, we propose a robust and noise-resilient anomaly detection mechanism using multivariate KPIs. Our key insight is that different KPIs are constrained by certain time-invariant characteristics of the underlying system, and that explicitly modelling such invariance may help resist noise in the data. We thus propose a novel anomaly detection method called SDFVAE, short for Static and Dynamic Factorized VAE, that learns the representations of KPIs by explicitly factorizing the latent variables into dynamic and static parts. Extensive experiments using real-world data show that SDFVAE achieves a F1-score ranging from 0.92 to 0.99 on both regular and noisy dataset, outperforming state-of-the-art methods by a large margin.

Next-basket recommendation (NBR) is prevalent in e-commerce and retail industry. In this scenario, a user purchases a set of items (a basket) at a time. NBR performs sequential modeling and recommendation based on a sequence of baskets. NBR is in general more complex than the widely studied sequential (session-based) recommendation which recommends the next item based on a sequence of items. Recurrent neural network (RNN) has proved to be very effective for sequential modeling, and thus been adapted for NBR. However, we argue that existing RNNs cannot directly capture item frequency information in the recommendation scenario.

We conduct to our knowledge a first measurement study of commercial 5G performance on smartphones by closely examining 5G networks of three carriers (two mmWave carriers, one mid-band carrier) in three U.S. cities. We conduct extensive field tests on 5G performance in diverse urban environments. We systematically analyze the handoff mechanisms in 5G and their impact on network performance. We explore the feasibility of using location and possibly other environmental information to predict the network performance. We also study the app performance (web browsing and HTTP download) over 5G. Our study consumes more than 15 TB of cellular data. Conducted when 5G just made its debut, it provides a “baseline” for studying how 5G performance evolves, and identifies key research directions on improving 5G users’ experience in a cross-layer manner. We have released the data collected from our study (referred to as 5Gophers) at https://fivegophers.umn.edu/www20.

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their success, there is a dearth of theoretical explorations of GCNN models such as their generalization properties. In this paper, we take a first step towards developing a deeper theoretical understanding of GCNN models by analyzing the stability of single-layer GCNN models and deriving their generalization guarantees in a semi-supervised graph learning setting. In particular, we show that the algorithmic stability of a GCNN model depends upon the largest absolute eigenvalue of its graph convolution filter. Moreover, to ensure the uniform stability needed to provide strong generalization guarantees, the largest absolute eigenvalue must be independent of the graph size. Our results shed new insights on the design of new & improved graph convolution filters with guaranteed algorithmic stability. We evaluate the generalization gap and stability on various real-world graph datasets and show that the empirical results indeed support our theoretical findings. To the best of our knowledge, we are the first to study stability bounds on graph learning in a semi-supervised setting and derive generalization bounds for GCNN models.

It is well-known that online services resort to various cookies to track users through users' online service identifiers (IDs) - in other words, when users access online services, various "fingerprints" are left behind in the cyberspace. As they roam around in the physical world while accessing online services via mobile devices, users also leave a series of "footprints" -- i.e., hints about their physical locations - in the physical world. This poses a potent new threat to user privacy: one can potentially correlate the "fingerprints" left by the users in the cyberspace with "footprints" left in the physical world to infer and reveal leakage of user physical world privacy, such as frequent user locations or mobility trajectories in the physical world - we refer to this problem as user physical world privacy leakage via user cyberspace privacy leakage. In this paper we address the following fundamental question: what kind - and how much - of user physical world privacy might be leaked if we could get hold of such diverse network datasets even without any physical location information. In order to conduct an in-depth investigation of these questions, we utilize the network data collected via a DPI system at the routers within one of the largest Internet operator in Shanghai, China over a duration of one month. We decompose the fundamental question into the three problems: i) linkage of various online user IDs belonging to the same person via mobility pattern mining; ii) physical location classification via aggregate user mobility patterns over time; and iii) tracking user physical mobility. By developing novel and effective methods for solving each of these problems, we demonstrate that the question of user physical world privacy leakage via user cyberspace privacy leakage is not hypothetical, but indeed poses a real potent threat to user privacy.

Rapid urbanization has posed significant burden on urban transportation infrastructures. In today's cities, both private and public transits have clear limitations to fulfill passengers' needs for quality of experience (QoE): Public transits operate along fixed routes with long wait time and total transit time; Private transits, such as taxis, private shuttles and ride-hailing services, provide point-to-point transits with high trip fare. In this paper, we propose CityLines, a transformative urban transit system, employing hybrid hub-and-spoke transit model with shared shuttles. Analogous to Airlines services, the proposed CityLines system routes urban trips among spokes through a few hubs or direct paths, with travel time as short as private transits and fare as low as public transits. CityLines allows both point-to-point connection to improve the passenger QoE, and hub-and-spoke connection to reduce the system operation cost. Our evaluation results show that CityLines framework can achieve both short travel time and high ride-sharing ratio.

The increasing prevalence of sensors and mobile devices has led to an explosive increase of the scale of spatio-temporal data in the form of trajectories. A trajectory aggregate query, as a fundamental functionality for measuring trajectory data, aims to retrieve the statistics of trajectories passing a user-specified spatio-temporal region. A large-scale spatio-temporal database with big disk-resident data takes very long time to produce exact answers to such queries. Hence, approximate query processing with a guaranteed error bound is a promising solution in many scenarios with stringent response-time requirements. In this paper, we study the problem of approximate query processing for trajectory aggregate queries. We show that it boils down to the distinct value estimation problem, which has been proven to be very hard with powerful negative results given that no index is built. By utilizing the well-established spatio-temporal index and introducing an inverted index to trajectory data, we are able to design random index sampling (RIS) algorithm to estimate the answers with a guaranteed error bound. To further improve system scalability, we extend RIS algorithm to concurrent random index sampling (CRIS) algorithm to process a number of trajectory aggregate queries arriving concurrently with overlapping spatio-temporal query regions. To demonstrate the efficacy and efficiency of our sampling and estimation methods, we applied them in a real large-scale user trajectory database collected from a cellular service provider in China. Our extensive evaluation results indicate that both RIS and CRIS outperform exhaustive search for single and concurrent trajectory aggregate queries by two orders of magnitude in terms of the query processing time, while preserving a relative error ratio lower than 10\%, with only 1% search cost of the exhaustive search method.

Directed links -- representing asymmetric social ties or interactions (e.g., "follower-followee") -- arise naturally in many social networks and other complex networks, giving rise to directed graphs (or digraphs) as basic topological models for these networks. Reciprocity, defined for a digraph as the percentage of edges with a reciprocal edge, is a key metric that has been used in the literature to compare different directed networks and provide "hints" about their structural properties: for example, are reciprocal edges generated randomly by chance or are there other processes driving their generation? In this paper we study the problem of maximizing achievable reciprocity for an ensemble of digraphs with the same prescribed in- and out-degree sequences. We show that the maximum reciprocity hinges crucially on the in- and out-degree sequences, which may be intuitively interpreted as constraints on some "social capacities" of nodes and impose fundamental limits on achievable reciprocity. We show that it is NP-complete to decide the achievability of a simple upper bound on maximum reciprocity, and provide conditions for achieving it. We demonstrate that many real networks exhibit reciprocities surprisingly close to the upper bound, which implies that users in these social networks are in a sense more "social" than suggested by the empirical reciprocity alone in that they are more willing to reciprocate, subject to their "social capacity" constraints. We find some surprising linear relationships between empirical reciprocity and the bound. We also show that a particular type of small network motifs that we call 3-paths are the major source of loss in reciprocity for real networks.

Influence diffusion and influence maximization in large-scale online social networks (OSNs) have been extensively studied because of their impacts on enabling effective online viral marketing. Existing studies focus on social networks with only friendship relations, whereas the foe or enemy relations that commonly exist in many OSNs, e.g., Epinions and Slashdot, are completely ignored. In this paper, we make the first attempt to investigate the influence diffusion and influence maximization in OSNs with both friend and foe relations, which are modeled using positive and negative edges on signed networks. In particular, we extend the classic voter model to signed networks and analyze the dynamics of influence diffusion of two opposite opinions. We first provide systematic characterization of both short-term and long-term dynamics of influence diffusion in this model, and illustrate that the steady state behaviors of the dynamics depend on three types of graph structures, which we refer to as balanced graphs, anti-balanced graphs, and strictly unbalanced graphs. We then apply our results to solve the influence maximization problem and develop efficient algorithms to select initial seeds of one opinion that maximize either its short-term influence coverage or long-term steady state influence coverage. Extensive simulation results on both synthetic and real-world networks, such as Epinions and Slashdot, confirm our theoretical analysis on influence diffusion dynamics, and demonstrate that our influence maximization algorithms perform consistently better than other heuristic algorithms.

The ability to accurately and scalably classify network traffic is of critical importance to a wide range of management tasks of large networks, such as tier-1 ISP networks and global enterprise networks. Guided by the practical constraints and requirements of traffic classification in large networks, in this article, we explore the design of an accurate and scalable machine learning based flow-level traffic classification system, which is trained on a dataset of flow-level data that has been annotated with application protocol labels by a packet-level classifier. Our system employs a lightweight modular architecture , which combines a series of simple linear binary classifiers, each of which can be efficiently implemented and trained on vast amounts of flow data in parallel, and embraces three key innovative mechanisms, weighted threshold sampling, logistic calibration , and intelligent data partitioning , to achieve scalability while attaining high accuracy. Evaluations using real traffic data from multiple locations in a large ISP show that our system accurately reproduces the labels of the packet level classifier when runs on (unlabeled) flow records, while meeting the scalability and stability requirements of large ISP networks. Using training and test datasets that are two months apart and collected from two different locations, the flow error rates are only 3% for TCP flows and 0.4% for UDP flows. We further show that such error rates can be reduced by combining the information of spatial distributions of flows, or collective traffic statistics , during classification. We propose a novel two-step model, which seamlessly integrates these collective traffic statistics into the existing traffic classification system. Experimental results display performance improvement on all traffic classes and an overall error rate reduction by 15%. In addition to a high accuracy, at runtime, our implementation easily scales to classify traffic on 10Gbps links.

In this paper, we propose a method, where the labeling of the data set is carried out in a semi-supervised manner with user-specified guarantees about the quality of the labeling. In our scheme, we assume that for each class, we have some heuristics available, each of which can identify instances of one particular class. The heuristics are assumed to have reasonable performance but they do not need to cover all instances of the class nor do they need to be perfectly reliable. We further assume that we have an infallible expert, who is willing to manually label a few instances. The aim of the algorithm is to exploit the cluster structure of the problem, the predictions by the imperfect heuristics and the limited perfect labels provided by the expert to classify (label) the instances of the data set with guaranteed precision (specificed by the user) with regards to each class. The specified precision is not always attainable, so the algorithm is allowed to classify some instances as dontknow. The algorithm is evaluated by the number of instances labeled by the expert, the number of dontknow instances (global coverage) and the achieved quality of the labeling. On the KDD Cup Network Intrusion data set containing 500,000 instances, we managed to label 96.6% of the instances while guaranteeing a nominal precision of 90% (with 95% confidence) by having the expert label 630 instances; and by having the expert label 1200 instances, we managed to guarantee 95% nominal precision while labeling 96.4% of the data. We also provide a case study of applying our scheme to label the network traffic collected at a large campus network.

Estimating the number of false negatives for a classifier when the true outcome of the classification is ascertained only for a limited number of instances is an important problem, with a wide range of applications from epidemiology to computer/network security. The frequently applied method is random sampling. However, when the target (positive) class of the classification is rare, which is often the case with network intrusions and diseases, this simple method results in excessive sampling. In this paper, we propose an approach that exploits the cluster structure of the data to significantly reduce the amount of sampling needed while guaranteeing an estimation accuracy specified by the user. The basic idea is to cluster the data and divide the clusters into a set of “strata”, such that the proportion of positive instances in the stratum is very low, very high or in between, respectively. By taking advantage of the different characteristics of the strata, more efficient estimation strategies can be applied, thereby significantly reducing the amount of required sampling. We also develop a computationally efficient clustering algorithm – referred to as class-focused partitioning – which uses the (imperfect) labels predicted by the classifier as additional guidance. We evaluated our method on the KDDCup network intrusion data set. Our method achieved better precision and accuracy with a 5% sample than the best trial of simple random sampling with 40% samples.