arXiv subjects

Ju Ren

Publications and source records attributed to Ju Ren.

At least 55 records · Page 3Linked to original sources

arXiv2024

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning

In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation policy from static demonstration data, followed by fast finetuning with minimal environmental interaction. We find the naïve combination of existing offline IL and online IL methods tends to behave poorly in this context, because the initial discriminator (often used in online IL) operates randomly and discordantly against the policy initialization, leading to misguided policy optimization and $\textit{unlearning}$ of pretraining knowledge. To overcome this challenge, we propose a principled offline-to-online IL method, named $\texttt{OLLIE}$, that simultaneously learns a near-expert policy initialization along with an $\textit{aligned discriminator initialization}$, which can be seamlessly integrated into online IL, achieving smooth and fast finetuning. Empirically, $\texttt{OLLIE}$ consistently and significantly outperforms the baseline methods in $\textbf{20}$ challenging tasks, from continuous control to vision-based domains, in terms of performance, demonstration efficiency, and convergence speed. This work may serve as a foundation for further exploration of pretraining and finetuning in the context of IL.

cs.LG↗

arXiv2024

Momentum-Based Federated Reinforcement Learning with Interaction and Communication Efficiency

Federated Reinforcement Learning (FRL) has garnered increasing attention recently. However, due to the intrinsic spatio-temporal non-stationarity of data distributions, the current approaches typically suffer from high interaction and communication costs. In this paper, we introduce a new FRL algorithm, named $\texttt{MFPO}$, that utilizes momentum, importance sampling, and additional server-side adjustment to control the shift of stochastic policy gradients and enhance the efficiency of data utilization. We prove that by proper selection of momentum parameters and interaction frequency, $\texttt{MFPO}$ can achieve $\tilde{\mathcal{O}}(H N^{-1}ε^{-3/2})$ and $\tilde{\mathcal{O}}(ε^{-1})$ interaction and communication complexities ($N$ represents the number of agents), where the interaction complexity achieves linear speedup with the number of agents, and the communication complexity aligns the best achievable of existing first-order FL algorithms. Extensive experiments corroborate the substantial performance gains of $\texttt{MFPO}$ over existing methods on a suite of complex and high-dimensional benchmarks.

cs.LG↗

arXiv2024

Federated Offline Policy Optimization with Dual Regularization

Federated Reinforcement Learning (FRL) has been deemed as a promising solution for intelligent decision-making in the era of Artificial Internet of Things. However, existing FRL approaches often entail repeated interactions with the environment during local updating, which can be prohibitively expensive or even infeasible in many real-world domains. To overcome this challenge, this paper proposes a novel offline federated policy optimization algorithm, named $\texttt{DRPO}$, which enables distributed agents to collaboratively learn a decision policy only from private and static data without further environmental interactions. $\texttt{DRPO}$ leverages dual regularization, incorporating both the local behavioral policy and the global aggregated policy, to judiciously cope with the intrinsic two-tier distributional shifts in offline FRL. Theoretical analysis characterizes the impact of the dual regularization on performance, demonstrating that by achieving the right balance thereof, $\texttt{DRPO}$ can effectively counteract distributional shifts and ensure strict policy improvement in each federative learning round. Extensive experiments validate the significant performance gains of $\texttt{DRPO}$ over baseline methods.

cs.LG↗

arXiv2024

You Can Use But Cannot Recognize: Preserving Visual Privacy in Deep Neural Networks

Image data have been extensively used in Deep Neural Network (DNN) tasks in various scenarios, e.g., autonomous driving and medical image analysis, which incurs significant privacy concerns. Existing privacy protection techniques are unable to efficiently protect such data. For example, Differential Privacy (DP) that is an emerging technique protects data with strong privacy guarantee cannot effectively protect visual features of exposed image dataset. In this paper, we propose a novel privacy-preserving framework VisualMixer that protects the training data of visual DNN tasks by pixel shuffling, while not injecting any noises. VisualMixer utilizes a new privacy metric called Visual Feature Entropy (VFE) to effectively quantify the visual features of an image from both biological and machine vision aspects. In VisualMixer, we devise a task-agnostic image obfuscation method to protect the visual privacy of data for DNN training and inference. For each image, it determines regions for pixel shuffling in the image and the sizes of these regions according to the desired VFE. It shuffles pixels both in the spatial domain and in the chromatic channel space in the regions without injecting noises so that it can prevent visual features from being discerned and recognized, while incurring negligible accuracy loss. Extensive experiments on real-world datasets demonstrate that VisualMixer can effectively preserve the visual privacy with negligible accuracy loss, i.e., at average 2.35 percentage points of model accuracy loss, and almost no performance degradation on model training.

cs.CR↗

arXiv2024

RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection

Embedding watermarks into models has been widely used to protect model ownership in federated learning (FL). However, existing methods are inadequate for protecting the ownership of personalized models acquired by clients in personalized FL (PFL). This is due to the aggregation of the global model in PFL, resulting in conflicts over clients' private watermarks. Moreover, malicious clients may tamper with embedded watermarks to facilitate model leakage and evade accountability. This paper presents a robust watermark embedding scheme, named RobWE, to protect the ownership of personalized models in PFL. We first decouple the watermark embedding of personalized models into two parts: head layer embedding and representation layer embedding. The head layer belongs to clients' private part without participating in model aggregation, while the representation layer is the shared part for aggregation. For representation layer embedding, we employ a watermark slice embedding operation, which avoids watermark embedding conflicts. Furthermore, we design a malicious watermark detection scheme enabling the server to verify the correctness of watermarks before aggregating local models. We conduct an exhaustive experimental evaluation of RobWE. The results demonstrate that RobWE significantly outperforms the state-of-the-art watermark embedding schemes in FL in terms of fidelity, reliability, and robustness.

cs.CR↗

arXiv2023

PoPeC: PAoI-Centric Task Offloading with Priority over Unreliable Channels

Freshness-aware computation offloading has garnered great attention recently in the edge computing arena, with the aim of promptly obtaining up-to-date information and minimizing the transmission of outdated data. However, most of the existing work assumes that wireless channels are reliable and neglect the dynamics and stochasticity thereof. In addition, varying priorities of offloading tasks along with heterogeneous computing units also pose significant challenges in effective task scheduling and resource allocation. To address these challenges, we cast the freshness-aware task offloading problem as a multi-priority optimization problem, considering the unreliability of wireless channels, the heterogeneity of edge servers, and prioritized users. Based on the nonlinear fractional programming and ADMM-Consensus method, we propose a joint resource allocation and task offloading algorithm to solve the original problem iteratively. To improve communication efficiency, we further devise a distributed asynchronous variant for the proposed algorithm. We rigorously analyze the performance and convergence of the proposed algorithms and conduct extensive simulations to corroborate their efficacy and superiority over the existing baselines.

cs.NI↗

arXiv2023

Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer

While large language models (LLMs) are empowered with broad knowledge, their task-specific performance is often suboptimal. It necessitates fine-tuning LLMs with task-specific data, but such data may be inaccessible due to privacy concerns. In this paper, we propose a novel approach to enhance LLMs with smaller language models (SLMs) that are trained on clients using their private task-specific data. To enable mutual enhancement between LLMs and SLMs, we propose CrossLM, where the SLMs promote the LLM to generate task-specific high-quality data, and both the LLM and SLMs are enhanced with the generated data. We evaluate CrossLM using publicly accessible language models across a range of benchmark tasks. The results demonstrate that CrossLM significantly enhances the task-specific performance of SLMs on clients and the LLM on the cloud server simultaneously while preserving the LLM's generalization capability.

cs.AI↗

arXiv2023

SYSFLOW: Efficient Execution Platform for IoT Devices

Traditional executable delivery models pose challenges for IoT devices with limited storage, necessitating the download of complete executables and dependencies. Network solutions like NFS, designed for data files, encounter high IO overhead for irregular access patterns. This paper introduces SYSFLOW, a lightweight network-based executable delivery system for IoT. SYSFLOW delivers on-demand, redirecting local disk IO to the server through optimized network IO. To optimize cache hit rates, SYSFLOW employs server-side action-based prefetching, reducing latency by 45.1% to 75.8% compared to native Linux filesystems on SD cards. In wired environments, SYSFLOW's latency is up to 67.7% lower than NFS. In wireless scenarios, SYSFLOW performs 22.9% worse than Linux, comparable with Linux and outperforming NFS by up to 60.7%. While SYSFLOW's power consumption may be 6.7% higher than NFS, it offers energy savings due to lower processing time.

cs.NI↗

arXiv2023

Learning from Limited Heterogeneous Training Data: Meta-Learning for Unsupervised Zero-Day Web Attack Detection across Web Domains

Recently unsupervised machine learning based systems have been developed to detect zero-day Web attacks, which can effectively enhance existing Web Application Firewalls (WAFs). However, prior arts only consider detecting attacks on specific domains by training particular detection models for the domains. These systems require a large amount of training data, which causes a long period of time for model training and deployment. In this paper, we propose RETSINA, a novel meta-learning based framework that enables zero-day Web attack detection across different domains in an organization with limited training data. Specifically, it utilizes meta-learning to share knowledge across these domains, e.g., the relationship between HTTP requests in heterogeneous domains, to efficiently train detection models. Moreover, we develop an adaptive preprocessing module to facilitate semantic analysis of Web requests across different domains and design a multi-domain representation method to capture semantic correlations between different domains for cross-domain model training. We conduct experiments using four real-world datasets on different domains with a total of 293M Web requests. The experimental results demonstrate that RETSINA outperforms the existing unsupervised Web attack detection methods with limited training data, e.g., RETSINA needs only 5-minute training data to achieve comparable detection performance to the existing methods that train separate models for different domains using 1-day training data. We also conduct real-world deployment in an Internet company. RETSINA captures on average 126 and 218 zero-day attack requests per day in two domains, respectively, in one month.

cs.CR↗

arXiv2023

CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning

This work aims to tackle a major challenge in offline Inverse Reinforcement Learning (IRL), namely the reward extrapolation error, where the learned reward function may fail to explain the task correctly and misguide the agent in unseen environments due to the intrinsic covariate shift. Leveraging both expert data and lower-quality diverse data, we devise a principled algorithm (namely CLARE) that solves offline IRL efficiently via integrating "conservatism" into a learned reward function and utilizing an estimated dynamics model. Our theoretical analysis provides an upper bound on the return gap between the learned policy and the expert policy, based on which we characterize the impact of covariate shift by examining subtle two-tier tradeoffs between the exploitation (on both expert and diverse data) and exploration (on the estimated dynamics model). We show that CLARE can provably alleviate the reward extrapolation error by striking the right exploitation-exploration balance therein. Extensive experiments corroborate the significant performance gains of CLARE over existing state-of-the-art algorithms on MuJoCo continuous control tasks (especially with a small offline dataset), and the learned reward is highly instructive for further learning.

cs.LG↗

arXiv2021

Efficient Federated Meta-Learning over Multi-Access Wireless Networks

Federated meta-learning (FML) has emerged as a promising paradigm to cope with the data limitation and heterogeneity challenges in today's edge learning arena. However, its performance is often limited by slow convergence and corresponding low communication efficiency. In addition, since the available radio spectrum and IoT devices' energy capacity are usually insufficient, it is crucial to control the resource allocation and energy consumption when deploying FML in practical wireless networks. To overcome the challenges, in this paper, we rigorously analyze each device's contribution to the global loss reduction in each round and develop an FML algorithm (called NUFM) with a non-uniform device selection scheme to accelerate the convergence. After that, we formulate a resource allocation problem integrating NUFM in multi-access wireless systems to jointly improve the convergence rate and minimize the wall-clock time along with energy cost. By deconstructing the original problem step by step, we devise a joint device selection and resource allocation strategy to solve the problem with theoretical guarantees. Further, we show that the computational complexity of NUFM can be reduced from $O(d^2)$ to $O(d)$ (with the model dimension $d$) via combining two first-order approximation techniques. Extensive simulation results demonstrate the effectiveness and superiority of the proposed methods in comparison with existing baselines.

cs.LG↗

arXiv2021

TODG: Distributed Task Offloading with Delay Guarantees for Edge Computing

Edge computing has been an efficient way to provide prompt and near-data computing services for resource-and-delay sensitive IoT applications via computation offloading. Effective computation offloading strategies need to comprehensively cope with several major issues, including the allocation of dynamic communication and computational resources, the deadline constraints of heterogeneous tasks, and the requirements for computationally inexpensive and distributed algorithms. However, most of the existing works mainly focus on part of these issues, which would not suffice to achieve expected performance in complex and practical scenarios. To tackle this challenge, in this paper, we systematically study a distributed computation offloading problem with hard delay constraints, where heterogeneous computational tasks require continually offloading to a set of edge servers via a limiting number of stochastic communication channels. The task offloading problem is then cast as a delay-constrained long-term stochastic optimization problem under unknown priori statistical knowledge. To resolve this problem, we first provide a technical path to transform and decompose it into several slot-level subproblems, then we develop a distributed online algorithm, namely TODG, to efficiently allocate the resources and schedule the offloading tasks with delay guarantees. Further, we present a comprehensive analysis for TODG, in terms of the optimality gap, the delay guarantees, and the impact of system parameters. Extensive simulation results demonstrate the effectiveness and efficiency of TODG.

cs.NI↗

arXiv2021

Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning

In order to meet the requirements for performance, safety, and latency in many IoT applications, intelligent decisions must be made right here right now at the network edge. However, the constrained resources and limited local data amount pose significant challenges to the development of edge AI. To overcome these challenges, we explore continual edge learning capable of leveraging the knowledge transfer from previous tasks. Aiming to achieve fast and continual edge learning, we propose a platform-aided federated meta-learning architecture where edge nodes collaboratively learn a meta-model, aided by the knowledge transfer from prior tasks. The edge learning problem is cast as a regularized optimization problem, where the valuable knowledge learned from previous tasks is extracted as regularization. Then, we devise an ADMM based federated meta-learning algorithm, namely ADMM-FedMeta, where ADMM offers a natural mechanism to decompose the original problem into many subproblems which can be solved in parallel across edge nodes and the platform. Further, a variant of inexact-ADMM method is employed where the subproblems are `solved' via linear approximation as well as Hessian estimation to reduce the computational cost per round to $\mathcal{O}(n)$. We provide a comprehensive analysis of ADMM-FedMeta, in terms of the convergence properties, the rapid adaptation performance, and the forgetting effect of prior knowledge transfer, for the general non-convex case. Extensive experimental studies demonstrate the effectiveness and efficiency of ADMM-FedMeta, and showcase that it substantially outperforms the existing baselines.

cs.LG↗

arXiv2019

Cache-Enabled Coordinated Mobile Edge Network: Opportunities and Challenges

Cache-enabled coordinated mobile edge network is an emerging network architecture, wherein serving nodes located at the network edge have the capabilities of baseband signal processing and caching files at their local cache. The main goals of such an emerging network architecture are to alleviate the burden on fronthaul links, while achieving low-latency high rate content delivery, say on the order of the millisecond level end-to-end content delivery latency. Consequently, the application of delaysensitive and content-aware has been executed in close proximity to end users. In this article, an outlook of research directions, challenges, and opportunities is provided and discussed in depth. We first introduce the cache-enabled coordinated mobile edge network architecture, and then discuss the key technical challenges and opening research issues that need to be addressed for this architecture. Then, to reduce the delivery latency and the burden on fronthaul links, new cache-enabled physical layer transmission schemes are discussed. Finally, artificial intelligence based cache-enabled communications are discussed as future research directions. Numerical studies show that several gains are achieved by caching popular content at the network edge with proper coordinated transmission schemes.

eess.SP↗

arXiv2019

Cloud-Edge Coordinated Processing: Low-Latency Multicasting Transmission

Recently, edge caching and multicasting arise as two promising technologies to support high-data-rate and low-latency delivery in wireless communication networks. In this paper, we design three transmission schemes aiming to minimize the delivery latency for cache-enabled multigroup multicasting networks. In particular, full caching bulk transmission scheme is first designed as a performance benchmark for the ideal situation where the caching capability of each enhanced remote radio head (eRRH) is sufficient large to cache all files. For the practical situation where the caching capability of each eRRH is limited, we further design two transmission schemes, namely partial caching bulk transmission (PCBT) and partial caching pipelined transmission (PCPT) schemes. In the PCBT scheme, eRRHs first fetch the uncached requested files from the baseband unit (BBU) and then all requested files are simultaneously transmitted to the users. In the PCPT scheme, eRRHs first transmit the cached requested files while fetching the uncached requested files from the BBU. Then, the remaining cached requested files and fetched uncached requested files are simultaneously transmitted to the users. The design goal of the three transmission schemes is to minimize the delivery latency, subject to some practical constraints. Efficient algorithms are developed for the low-latency cloud-edge coordinated transmission strategies. Numerical results are provided to evaluate the performance of the proposed transmission schemes and show that the PCPT scheme outperforms the PCBT scheme in terms of the delivery latency criterion.

cs.IT↗

arXiv2019

Hybrid Precoder Design for Cache-enabled Millimeter Wave Radio Access Networks

In this paper, we study the design of a hybrid precoder, consisting of an analog and a digital precoder, for the delivery phase of downlink cache-enabled millimeter wave (mmWave) radio access networks (CeMm-RANs). In CeMm-RANs, enhanced remote radio heads (eRRHs), which are equipped with local cache and baseband signal processing capabilities in addition to the basic functionalities of conventional RRHs, are connected to the baseband processing unit via fronthaul links. Two different fronthaul information transfer strategies are considered, namely, hard fronthaul information transfer, where hard information of uncached requested files is transmitted via the fronthaul links to a subset of eRRHs, and soft fronthaul information transfer, where the fronthaul links are used to transmit quantized baseband signals of uncached requested files. The hybrid precoder is optimized for maximization of the minimum user rate under a fronthaul capacity constraint, an eRRH transmit power constraint, and a constant-modulus constraint on the analog precoder. The resulting optimization problem is non-convex, and hence the global optimal solution is difficult to obtain. Therefore, convex approximation methods are employed to tackle the non-convexity of the achievable user rate, the fronthaul capacity constraint, and the constant modulus constraint on the analog precoder. Then, an effective algorithm with provable convergence is developed to solve the approximated optimization problem. Simulation results are provided to evaluate the performance of the proposed algorithms, where fully digital precoding is used as benchmark. The results reveal that except for the case of a large fronthaul link capacity, soft fronthaul information transfer is preferable for CeMm-RANs.

cs.IT↗

arXiv2018

An Incentive-Aware Job Offloading Control Framework for Mobile Edge Computing

This paper considers a scenario in which an access point (AP) is equipped with a mobile edge server of finite computing power, and serves multiple resource-hungry mobile users by charging users a price. Pricing provides users with incentives in offloading. However, existing works on pricing are based on abstract concave utility functions (e.g, the logarithm function), giving no dependence on physical layer parameters. To that end, we first introduce a novel utility function, which measures the cost reduction by offloading as compared with executing jobs locally. Based on this utility function we then formulate two offloading games, with one maximizing individual's interest and the other maximizing the overall system's interest. We analyze the structural property of the games and admit in closed form the Nash Equilibrium and the Social Equilibrium, respectively. The proposed expressions are functions of the user parameters such as the weights of computational time and energy, the distance from the AP, thus constituting an advancement over prior economic works that have considered only abstract functions. Finally, we propose an optimal pricing-based scheme, with which we prove that the interactive decision-making process with self-interested users converges to a Nash Equilibrium point equal to the Social Equilibrium point.

cs.IT↗

arXiv2015

Dynamic Channel Access for Energy Efficient Data Gathering in Cognitive Radio Sensor Networks

Wireless sensor networks (WSNs) operating in the license-free spectrum suffer from uncontrolled interference as those spectrum bands become increasingly crowded. The emerging cognitive radio sensor networks (CRSNs) provide a promising solution to address this challenge by enabling sensor nodes to opportunistically access licensed channels. However, since sensor nodes have to consume considerable energy to support CR functionalities, such as channel sensing and switching, the opportunistic channel accessing should be carefully devised for improving the energy efficiency in CRSN. To this end, we investigate the dynamic channel accessing problem to improve the energy efficiency for a clustered CRSN. Under the primary users' protection requirement, we study the resource allocation issues to maximize the energy efficiency of utilizing a licensed channel for intra-cluster and inter-cluster data transmission, respectively. With the consideration of the energy consumption in channel sensing and switching, we further determine the condition when sensor nodes should sense and switch to a licensed channel for improving the energy efficiency, according to the packet loss rate of the license-free channel. In addition, two dynamic channel accessing schemes are proposed to identify the channel sensing and switching sequences for intra-cluster and inter-cluster data transmission, respectively. Extensive simulation results demonstrate that the proposed channel accessing schemes can significantly reduce the energy consumption in CRSNs.

cs.NI↗