arXiv subjects

Zhi-Li Zhang

Publications and source records attributed to Zhi-Li Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2021

CLARA: A Constrained Reinforcement Learning Based Resource Allocation Framework for Network Slicing

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.

cs.NI↗

arXiv2021

Physics-Guided Deep Neural Networks for Power Flow Analysis

Solving power flow (PF) equations is the basis of power flow analysis, which is important in determining the best operation of existing systems, performing security analysis, etc. However, PF equations can be out-of-date or even unavailable due to system dynamics and uncertainties, making traditional numerical approaches infeasible. To address these concerns, researchers have proposed data-driven approaches to solve the PF problem by learning the mapping rules from historical system operation data. Nevertheless, prior data-driven approaches suffer from poor performance and generalizability, due to overly simplified assumptions of the PF problem or ignorance of physical laws governing power systems. In this paper, we propose a physics-guided neural network to solve the PF problem, with an auxiliary task to rebuild the PF model. By encoding different granularity of Kirchhoff's laws and system topology into the rebuilt PF model, our neural-network based PF solver is regularized by the auxiliary task and constrained by the physical laws. The simulation results show that our physics-guided neural network methods achieve better performance and generalizability compared to existing unconstrained data-driven approaches. Furthermore, we demonstrate that the weight matrices of our physics-guided neural networks embody power system physics by showing their similarities with the bus admittance matrices.

cs.LG↗

arXiv2020

$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning

Imitation learning (IL) aims to learn a policy from expert demonstrations that minimizes the discrepancy between the learner and expert behaviors. Various imitation learning algorithms have been proposed with different pre-determined divergences to quantify the discrepancy. This naturally gives rise to the following question: Given a set of expert demonstrations, which divergence can recover the expert policy more accurately with higher data efficiency? In this work, we propose $f$-GAIL, a new generative adversarial imitation learning (GAIL) model, that automatically learns a discrepancy measure from the $f$-divergence family as well as a policy capable of producing expert-like behaviors. Compared with IL baselines with various predefined divergence measures, $f$-GAIL learns better policies with higher data efficiency in six physics-based control tasks.

cs.LG↗

arXiv2020

A Novel Software-based Multi-path RDMA Solutionfor Data Center Networks

In this paper we propose Virtuoso, a purely software-based multi-path RDMA solution for data center networks (DCNs) to effectively utilize the rich multi-path topology for load balancing and reliability. As a "middleware" library operating at the user space, Virtuoso employs three innovative mechanisms to achieve its goal. In contrast to existing hardware-based MP-RDMA solution, Virtuoso can be readily deployed in DCNs with existing RDMA NICs. It also decouples path selection and load balancing mechanisms from hardware features, allowing DCN operators and applications to make flexible decisions by employing the best mechanisms (as "plug-in" software library modules) as needed. Our experiments show that Virtuoso is capable of fully utilizing multiple paths with negligible CPU overheads

cs.NI↗

arXiv2020

Modeling Personalized Item Frequency Information for Next-basket Recommendation

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. Through careful analysis of real-world datasets, we find that {\em personalized item frequency} (PIF) information (which records the number of times that each item is purchased by a user) provides two critical signals for NBR. But, this has been largely ignored by existing methods. Even though existing methods such as RNN based methods have strong representation ability, our empirical results show that they fail to learn and capture PIF. As a result, existing methods cannot fully exploit the critical signals contained in PIF. Given this inherent limitation of RNNs, we propose a simple item frequency based k-nearest neighbors (kNN) method to directly utilize these critical signals. We evaluate our method on four public real-world datasets. Despite its relative simplicity, our method frequently outperforms the state-of-the-art NBR methods -- including deep learning based methods using RNNs -- when patterns associated with PIF play an important role in the data.

cs.IR↗

arXiv2020

A First Look at Commercial 5G Performance on Smartphones

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.

cs.NI↗

arXiv2019

Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning

Learning powerful data embeddings has become a center piece in machine learning, especially in natural language processing and computer vision domains. The crux of these embeddings is that they are pretrained on huge corpus of data in a unsupervised fashion, sometimes aided with transfer learning. However currently in the graph learning domain, embeddings learned through existing graph neural networks (GNNs) are task dependent and thus cannot be shared across different datasets. In this paper, we present a first powerful and theoretically guaranteed graph neural network that is designed to learn task-independent graph embeddings, thereafter referred to as deep universal graph embedding (DUGNN). Our DUGNN model incorporates a novel graph neural network (as a universal graph encoder) and leverages rich Graph Kernels (as a multi-task graph decoder) for both unsupervised learning and (task-specific) adaptive supervised learning. By learning task-independent graph embeddings across diverse datasets, DUGNN also reaps the benefits of transfer learning. Through extensive experiments and ablation studies, we show that the proposed DUGNN model consistently outperforms both the existing state-of-art GNN models and Graph Kernels by an increased accuracy of 3% - 8% on graph classification benchmark datasets.

cs.LG↗

arXiv2019

Joint Switch Upgrade and Controller Deployment in Hybrid Software-Defined Networks

To improve traffic management ability, Internet Service Providers (ISPs) are gradually upgrading legacy network devices to programmable devices that support Software-Defined Networking (SDN). The coexistence of legacy and SDN devices gives rise to a hybrid SDN. Existing hybrid SDNs do not consider the potential performance issues introduced by a centralized SDN controller: flow requests processed by a highly loaded controller may experience long tail processing delay; inappropriate multi-controller deployment could increase the propagation delay of flow requests. In this paper, we propose to jointly consider the deployment of SDN switches and their controllers for hybrid SDNs. We formulate the joint problem as an optimization problem that maximizes the number of flows that can be controlled and managed by the SDN and minimizes the propagation delay of flow requests between SDN controllers and switches under a given upgrade budget constraint. We show this problem is NP-hard. To efficiently solve the problem, we propose some techniques (e.g., strengthening the constraints and adding additional valid inequalities) to accelerate the global optimization solver for solving the problem for small networks and an efficient heuristic algorithm for solving it for large networks. The simulation results from real network topologies illustrate the effectiveness of the proposed techniques and show that our proposed heuristic algorithm uses a small number of controllers to manage a high amount of flows with good performance.

cs.NI↗

arXiv2019

Stability and Generalization of Graph Convolutional Neural Networks

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.

cs.LG↗

arXiv2019

RetroFlow: Maintaining Control Resiliency and Flow Programmability for Software-Defined WANs

Providing resilient network control is a critical concern for deploying Software-Defined Networking (SDN) into Wide-Area Networks (WANs). For performance reasons, a Software-Defined WAN is divided into multiple domains controlled by multiple controllers with a logically centralized view. Under controller failures, we need to remap the control of offline switches from failed controllers to other active controllers. Existing solutions could either overload active controllers to interrupt their normal operations or degrade network performance because of increasing the controller-switch communication overhead. In this paper, we propose RetroFlow to achieve low communication overhead without interrupting the normal processing of active controllers during controller failures. By intelligently configuring a set of selected offline switches working under the legacy routing mode, RetroFlow relieves the active controllers from controlling the selected offline switches while maintaining the flow programmability (e.g., the ability to change paths of flows) of SDN. RetroFlow also smartly transfers the control of offline switches with the SDN routing mode to active controllers to minimize the communication overhead from these offline switches to the active controllers. Simulation results show that compared with the baseline algorithm, RetroFlow can reduce the communication overhead up to 52.6% during a moderate controller failure by recovering 100% flows from offline switches and can reduce the communication overhead up to 61.2% during a serious controller failure by setting to recover 90% of flows from offline switches.

cs.NI↗

arXiv2018

R-BBG$_2$: Recursive Bipartition of Bi-connected Graphs

Given an undirected graph $G(V, E)$, it is well known that partitioning a graph $G$ into $q$ connected subgraphs of equal or specificed sizes is in general NP-hard problem. On the other hand, it has been shown that the q-partition problem is solvable in polynomial time for q-connected graphs. For example, efficient polynomial time algorithms for finding 2-partition (bipartition) or 3-partition of 2-connected or 3-connected have been developed in the literature. In this paper, we are interested in the following problem: given a bi-connected graph $G$ of size $n$, can we partition it into two (connected) sub-graphs, $G[V_1]$ and $G[V_2]$ of sizes $n_1$ and $n_2$ such as both $G[V_1]$ and $G[V_2]$ are also bi-connected (and $n_1+n_2=n$)? We refer to this problem as the recursive bipartition problem of bi-connected graphs, denoted by R-BBG$_2$. We show that a ploynomial algorithm exists to both decide the recursive bipartion problem R-BBG$_2$ and find the corresponding bi-connected subgraphs when such a recursive bipartition exists.

cs.DS↗

arXiv2018

Learning and Management for Internet-of-Things: Accounting for Adaptivity and Scalability

Internet-of-Things (IoT) envisions an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. The unique features of IoT include extreme heterogeneity, massive number of devices, and unpredictable dynamics partially due to human interaction. These call for foundational innovations in network design and management. Ideally, it should allow efficient adaptation to changing environments, and low-cost implementation scalable to massive number of devices, subject to stringent latency constraints. To this end, the overarching goal of this paper is to outline a unified framework for online learning and management policies in IoT through joint advances in communication, networking, learning, and optimization. From the network architecture vantage point, the unified framework leverages a promising fog architecture that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations target online approaches adaptive to different degrees of nonstationarity in IoT dynamics, and their scalable model-free implementation under limited feedback that motivates blind or bandit approaches. The proposed framework aspires to offer a stepping stone that leads to systematic designs and analysis of task-specific learning and management schemes for IoT, along with a host of new research directions to build on.

eess.SY↗

arXiv2018

Graph Capsule Convolutional Neural Networks

Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in \cite{hinton2011transforming} and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve especially graph classification problem which current GCNN models find challenging. Through extensive experiments, we show that our proposed Graph Capsule Network can significantly outperforms both the existing state-of-art deep learning methods and graph kernels on graph classification benchmark datasets.

stat.ML↗

arXiv2018

Revisiting Non-Progressive Influence Models: Scalable Influence Maximization

While influence maximization in social networks has been studied extensively in computer science community for the last decade the focus has been on the progressive influence models, such as independent cascade (IC) and Linear threshold (LT) models, which cannot capture the reversibility of choices. In this paper, we present the Heat Conduction (HC) model which is a non-progressive influence model with real-world interpretations. We show that HC unifies, generalizes, and extends the existing nonprogressive models, such as the Voter model [1] and non-progressive LT [2]. We then prove that selecting the optimal seed set of influential nodes is NP-hard for HC but by establishing the submodularity of influence spread, we can tackle the influence maximization problem with a scalable and provably near-optimal greedy algorithm. We are the first to present a scalable solution for influence maximization under nonprogressive LT model, as a special case of the HC model. In sharp contrast to the other greedy influence maximization methods, our fast and efficient C2GREEDY algorithm benefits from two analytically computable steps: closed-form computation for finding the influence spread as well as the greedy seed selection. Through extensive experiments on several large real and synthetic networks, we show that C2GREEDY outperforms the state-of-the-art methods, in terms of both influence spread and scalability.

cs.SI↗

arXiv2018

Random Walk Fundamental Tensor and Its Applications to Network Analysis

We first present a comprehensive review of various random walk metrics used in the literature and express them in a consistent framework. We then introduce fundamental tensor -- a generalization of the well-known fundamental matrix -- and show that classical random walk metrics can be derived from it in a unified manner. We provide a collection of useful relations for random walk metrics that are useful and insightful for network studies. To demonstrate the usefulness and efficacy of the proposed fundamental tensor in network analysis, we present four important applications: 1) unification of network centrality measures, 2) characterization of (generalized) network articulation points, 3) identification of network most influential nodes, and 4) fast computation of network reachability after failures.

cs.DM↗

arXiv2018

Fast Distance Sensitivity Oracle for Multiple Failures

When a network is prone to failures, it is very expensive to compute the shortest paths every time from the scratch. Distance sensitivity oracle provides this privilege to find the new shortest paths faster and with lower cost by once pre-computing an oracle in advance. Although several efficient solutions are proposed in the literature to support the single failure, few efforts are done to devise an efficient method regarding the case of multiple failures. In this paper, we present a novel distance sensitivity oracle based on Markov Tensor Theory \cite{golnari2017markov} to support replacement path queries $(*,t,\mathcal{F})$ in general directed and weighted networks facing the set of failures $\mathcal{F}$. In contrast to the existing work, there is no limitation on maximum failure size supported by our oracle and there is no need to know the size of failure for constructing the oracle. The specifications of our oracle are: space size of $O(n^2)$, pre-process time of $O(n^ω)$, where $ω$ is the exponent of fast matrix multiplication, and query time of $O(m)$ for answering to replacement path query of $(*,t,\mathcal{F})$ which computes the replacement (shortest) paths from all nodes to target $t$ at once. While the computation time for regular shortest path methods, such as Dijkstra's, is $O(m+nlogn)$ for each query after a failure, our algorithm can save a considerable computational time when the size of failure set $|\mathcal{F}|$ is $O(m^{1/ω})$ or less and the network is sparse $O(m)<O(nlogn)$.

cs.DS↗

arXiv2018

Avoidance Markov Metrics and Node Pivotality Ranking

We introduce the avoidance Markov metrics and theories which provide more flexibility in the design of random walk and impose new conditions on the walk to avoid (or transit) a specific node (or a set of nodes) before the stopping criteria. These theories help with applications that cannot be modeled by classical Markov chains and require more flexibility and intricacy in their modeling. Specifically, we use them for the pivotality ranking of the nodes in a network reachabilities. More often than not, it is not sufficient simply to know whether a source node $s$ can reach a target node $t$ in the network and additional information associated with reachability, such as how long or how many possible ways node $s$ may take to reach node $t$, is required. In this paper, we analyze the pivotality of the nodes which capture how pivotal a role that a node $k$ or a subset of nodes $S$ may play in the reachability from node $s$ to node $t$ in a given network. Through some synthetic and real-world network examples, we show that these metrics build a powerful ranking tool for the nodes based on their pivotality in the reachability.

cs.DM↗

arXiv2017

Joint Cache Resource Allocation and Request Routing for In-network Caching Services

In-network caching is recognized as an effective solution to offload content servers and the network. A cache service provider (SP) always has incentives to better utilize its cache resources by taking into account diverse roles that content providers (CPs) play, e.g., their business models, traffic characteristics, preferences. In this paper, we study the cache resource allocation problem in a Multi-Cache Multi-CP environment. We propose a cache partitioning approach, where each cache can be partitioned into slices with each slice dedicated to a content provider. We propose a content-oblivious request routing algorithm, to be used by individual caches, that optimizes the routing strategy for each CP. We associate with each content provider a utility that is a function of its content delivery performance, and formulate an optimization problem with the objective to maximize the sum of utilities over all content providers. We establish the biconvexity of the problem, and develop decentralized (online) algorithms based on convexity of the subproblem. The proposed model is further extended to bandwidth-constrained and minimum-delay scenarios, for which we prove fundamental properties, and develop efficient algorithms. Finally, we present numerical results to show the efficacy of our mechanism and the convergence of our algorithms.

cs.NI↗