This paper presents an approximate wireless communication scheme for federated learning (FL) model aggregation in the uplink transmission. We consider a realistic channel that reveals bit errors during FL model exchange in wireless networks. Our study demonstrates that random bit errors during model transmission can significantly affect FL performance. To overcome this challenge, we propose an approximate communication scheme based on the mathematical and statistical proof that machine learning (ML) model gradients are bounded under certain constraints. This bound enables us to introduce a novel encoding scheme for float-to-binary representation of gradient values and their QAM constellation mapping. Besides, since FL gradients are error-resilient, the proposed scheme simply delivers gradients with errors when the channel quality is satisfactory, eliminating extensive error-correcting codes and/or retransmission. The direct benefits include less overhead and lower latency. The proposed scheme is well-suited for resource-constrained devices in wireless networks. Through simulations, we show that the proposed scheme is effective in reducing the impact of bit errors on FL performance and saves at least half the time than transmission with error correction and retransmission to achieve the same learning performance. In addition, we investigated the effectiveness of bit protection mechanisms in high-order modulation when gray coding is employed and found that this approach considerably enhances learning performance.
相關內容
This paper considers improving wireless communication and computation efficiency in federated learning (FL) via model quantization. In the proposed bitwidth FL scheme, edge devices train and transmit quantized versions of their local FL model parameters to a coordinating server, which aggregates them into a quantized global model and synchronizes the devices. The goal is to jointly determine the bitwidths employed for local FL model quantization and the set of devices participating in FL training at each iteration. We pose this as an optimization problem that aims to minimize the training loss of quantized FL under a per-iteration device sampling budget and delay requirement. However, the formulated problem is difficult to solve without (i) a concrete understanding of how quantization impacts global ML performance and (ii) the ability of the server to construct estimates of this process efficiently. To address the first challenge, we analytically characterize how limited wireless resources and induced quantization errors affect the performance of the proposed FL method. Our results quantify how the improvement of FL training loss between two consecutive iterations depends on the device selection and quantization scheme as well as on several parameters inherent to the model being learned. Then, we show that the FL training process can be described as a Markov decision process and propose a model-based reinforcement learning (RL) method to optimize action selection over iterations. Compared to model-free RL, this model-based RL approach leverages the derived mathematical characterization of the FL training process to discover an effective device selection and quantization scheme without imposing additional device communication overhead. Simulation results show that the proposed FL algorithm can reduce the convergence time.
Federated learning (FL) is a popular privacy-preserving distributed training scheme, where multiple devices collaborate to train machine learning models by uploading local model updates. To improve communication efficiency, over-the-air computation (AirComp) has been applied to FL, which leverages analog modulation to harness the superposition property of radio waves such that numerous devices can upload their model updates concurrently for aggregation. However, the uplink channel noise incurs considerable model aggregation distortion, which is critically determined by the device scheduling and compromises the learned model performance. In this paper, we propose a probabilistic device scheduling framework for over-the-air FL, named PO-FL, to mitigate the negative impact of channel noise, where each device is scheduled according to a certain probability and its model update is reweighted using this probability in aggregation. We prove the unbiasedness of this aggregation scheme and demonstrate the convergence of PO-FL on both convex and non-convex loss functions. Our convergence bounds unveil that the device scheduling affects the learning performance through the communication distortion and global update variance. Based on the convergence analysis, we further develop a channel and gradient-importance aware algorithm to optimize the device scheduling probabilities in PO-FL. Extensive simulation results show that the proposed PO-FL framework with channel and gradient-importance awareness achieves faster convergence and produces better models than baseline methods.
Consider a hiring process with candidates coming from different universities. It is easy to order candidates who have the same background, yet it can be challenging to compare them otherwise. The latter case requires additional costly assessments and can result in sub-optimal hiring decisions. Given an assigned budget, what would be an optimal strategy to select the most qualified candidate? We model the above problem by introducing a new variant of the secretary problem in which sequentially observed candidates are split into two distinct groups. For each new candidate, the decision maker observes its rank among already seen candidates from the same group and can access its rank among all observed candidates at some fixed cost. To tackle this new problem, we introduce and study the family of Dynamic Double Threshold (DDT) algorithms. We show that, with well-chosen parameters, their success probability converges rapidly to 1/e as the budget grows, recovering the optimal success probability from the usual secretary problem. Finally, focusing on the class of memory-less algorithms, we propose an optimal algorithm in the non-asymptotic regime and show that it belongs to the DDT family when the number of candidates is large.
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance. This is crucial when deciding whether a given policy satisfies certain minimal performance/safety criteria before it can be deployed in the real world. To this end, we introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. To form a conservative estimate of the policy's performance, HAMBO hallucinates worst-case trajectories that the policy may take, within the margin of the models' epistemic confidence regions. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return. Finally, we discuss scalable variants of our approach based on Bayesian Neural Networks and empirically demonstrate that they yield reliable and tight lower bounds in various continuous control environments.
This paper studies the online node classification problem under a transductive learning setting. Current methods either invert a graph kernel matrix with $\mathcal{O}(n^3)$ runtime and $\mathcal{O}(n^2)$ space complexity or sample a large volume of random spanning trees, thus are difficult to scale to large graphs. In this work, we propose an improvement based on the \textit{online relaxation} technique introduced by a series of works (Rakhlin et al.,2012; Rakhlin and Sridharan, 2015; 2017). We first prove an effective regret $\mathcal{O}(\sqrt{n^{1+\gamma}})$ when suitable parameterized graph kernels are chosen, then propose an approximate algorithm FastONL enjoying $\mathcal{O}(k\sqrt{n^{1+\gamma}})$ regret based on this relaxation. The key of FastONL is a \textit{generalized local push} method that effectively approximates inverse matrix columns and applies to a series of popular kernels. Furthermore, the per-prediction cost is $\mathcal{O}(\text{vol}({\mathcal{S}})\log 1/\epsilon)$ locally dependent on the graph with linear memory cost. Experiments show that our scalable method enjoys a better tradeoff between local and global consistency.
LLHR: Low Latency and High Reliability CNN Distributed Inference for Resource-Constrained UAV Swarms
Recently, Unmanned Aerial Vehicles (UAVs) have shown impressive performance in many critical applications, such as surveillance, search and rescue operations, environmental monitoring, etc. In many of these applications, the UAVs capture images as well as other sensory data and then send the data processing requests to remote servers. Nevertheless, this approach is not always practical in real-time-based applications due to unstable connections, limited bandwidth, limited energy, and strict end-to-end latency. One promising solution is to divide the inference requests into subtasks that can be distributed among UAVs in a swarm based on the available resources. Moreover, these tasks create intermediate results that need to be transmitted reliably as the swarm moves to cover the area. Our system model deals with real-time requests, aiming to find the optimal transmission power that guarantees higher reliability and low latency. We formulate the Low Latency and High-Reliability (LLHR) distributed inference as an optimization problem, and due to the complexity of the problem, we divide it into three subproblems. In the first subproblem, we find the optimal transmit power of the connected UAVs with guaranteed transmission reliability. The second subproblem aims to find the optimal positions of the UAVs in the grid, while the last subproblem finds the optimal placement of the CNN layers in the available UAVs. We conduct extensive simulations and compare our work to two baseline models demonstrating that our model outperforms the competing models.
Sampling-based planning algorithm is a powerful tool for solving planning problems in high-dimensional state spaces. In this article, we present a novel approach to sampling in the most promising regions, which significantly reduces planning time-consumption. The RRT# algorithm defines the Relevant Region based on the cost-to-come provided by the optimal forward-searching tree. However, it uses the cumulative cost of a direct connection between the current state and the goal state as the cost-to-go. To improve the path planning efficiency, we propose a batch sampling method that samples in a refined Relevant Region with a direct sampling strategy, which is defined according to the optimal cost-to-come and the adaptive cost-to-go, taking advantage of various sources of heuristic information. The proposed sampling approach allows the algorithm to build the search tree in the direction of the most promising area, resulting in a superior initial solution quality and reducing the overall computation time compared to related work. To validate the effectiveness of our method, we conducted several simulations in both $SE(2)$ and $SE(3)$ state spaces. And the simulation results demonstrate the superiorities of proposed algorithm.
Goal-oriented error estimation provides the ability to approximate the discretization error in a chosen functional quantity of interest. Adaptive mesh methods provide the ability to control this discretization error to obtain accurate quantity of interest approximations while still remaining computationally feasible. Traditional discrete goal-oriented error estimates incur linearization errors in their derivation. In this paper, we investigate the role of linearization errors in adaptive goal-oriented error simulations. In particular, we develop a novel two-level goal-oriented error estimate that is free of linearization errors. Additionally, we highlight how linearization errors can facilitate the verification of the adjoint solution used in goal-oriented error estimation. We then verify the newly proposed error estimate by applying it to a model nonlinear problem for several quantities of interest and further highlight its asymptotic effectiveness as mesh sizes are reduced. In an adaptive mesh context, we then compare the newly proposed estimate to a more traditional two-level goal-oriented error estimate. We highlight that accounting for linearization errors in the error estimate can improve its effectiveness in certain situations and demonstrate that localizing linearization errors can lead to more optimal adapted meshes.
Semantic communication (SemCom) has recently been considered a promising solution to guarantee high resource utilization and transmission reliability for future wireless networks. Nevertheless, the unique demand for background knowledge matching makes it challenging to achieve efficient wireless resource management for multiple users in SemCom-enabled networks (SC-Nets). To this end, this paper investigates SemCom from a networking perspective, where two fundamental problems of user association (UA) and bandwidth allocation (BA) are systematically addressed in the SC-Net. First, considering varying knowledge matching states between mobile users and associated base stations, we identify two general SC-Net scenarios, namely perfect knowledge matching-based SC-Net and imperfect knowledge matching-based SC-Net. Afterward, for each SC-Net scenario, we describe its distinctive semantic channel model from the semantic information theory perspective, whereby a concept of bit-rate-to-message-rate transformation is developed along with a new semantics-level metric, namely system throughput in message (STM), to measure the overall network performance. In this way, we then formulate a joint STM-maximization problem of UA and BA for each SC-Net scenario, followed by a corresponding optimal solution proposed. Numerical results in both scenarios demonstrate significant superiority and reliability of our solutions in the STM performance compared with two benchmarks.
Machine-readable representations of privacy policies are door openers for a broad variety of novel privacy-enhancing and, in particular, transparency-enhancing technologies (TETs). In order to generate such representations, transparency information needs to be extracted from written privacy policies. However, respective manual annotation and extraction processes are laborious and require expert knowledge. Approaches for fully automated annotation, in turn, have so far not succeeded due to overly high error rates in the specific domain of privacy policies. In the end, a lack of properly annotated privacy policies and respective machine-readable representations persists and enduringly hinders the development and establishment of novel technical approaches fostering policy perception and data subject informedness. In this work, we present a prototype system for a `Human-in-the-Loop' approach to privacy policy annotation that integrates ML-generated suggestions and ultimately human annotation decisions. We propose an ML-based suggestion system specifically tailored to the constraint of data scarcity prevalent in the domain of privacy policy annotation. On this basis, we provide meaningful predictions to users thereby streamlining the annotation process. Additionally, we also evaluate our approach through a prototypical implementation to show that our ML-based extraction approach provides superior performance over other recently used extraction models for legal documents.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191