Federated Learning (FL) is an approach to collaboratively train a model across multiple parties without sharing data between parties or an aggregator. It is used both in the consumer domain to protect personal data as well as in enterprise settings, where dealing with data domicile regulation and the pragmatics of data silos are the main drivers. While gradient boosted tree implementations such as XGBoost have been very successful for many use cases, its federated learning adaptations tend to be very slow due to using cryptographic and privacy methods and have not experienced widespread use. We propose the Party-Adaptive XGBoost (PAX) for federated learning, a novel implementation of gradient boosting which utilizes a party adaptive histogram aggregation method, without the need for data encryption. It constructs a surrogate representation of the data distribution for finding splits of the decision tree. Our experimental results demonstrate strong model performance, especially on non-IID distributions, and significantly faster training run-time across different data sets than existing federated implementations. This approach makes the use of gradient boosted trees practical in enterprise federated learning.
University of Warwick（华威大学）；Meta AI；University of Virginia（弗吉尼亚大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
There is great demand for scalable, secure, and efficient privacy-preserving machine learning models that can be trained over distributed data. While deep learning models typically achieve the best results in a centralized non-secure setting, different models can excel when privacy and communication constraints are imposed. Instead, tree-based approaches such as XGBoost have attracted much attention for their high performance and ease of use; in particular, they often achieve state-of-the-art results on tabular data. Consequently, several recent works have focused on translating Gradient Boost…
V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection
Fraunhofer Institute for Transportation and Infrastructure Systems IVI（弗劳恩霍夫交通与基础设施系统研究所IVI）；Technical University of Munich（慕尼黑工业大学）；Sony AI（索尼人工智能研究所）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）
We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss suRface Aggregation (FLoRA), the first FL-HPO solution framework that can address use cases of tabular data and gradient boosting training algorithms in addition to stochastic gradient descent/neural networks commonly addressed in the FL literature. The framework enables single-shot FL-HPO, by first identifying a good set of hyper-parameters that are used in a **single** FL training. Thus, it enables FL-HPO solutions with minimal additional communicati…
Disentangling data distribution for Federated Learning
Shenzhen International Graduate School, THU（清华大学深圳国际研究生院）；AI Lab, Webank（微众银行AI实验室）；Department of Computer Science and Engineering, HKUST（香港科技大学计算机科学与工程学系）
University of Nevada, Reno（内华达大学里诺分校）；IBM Research（IBM研究院）；University of Virginia（弗吉尼亚大学）
Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks. This paper focuses on characterizing and understanding its impact on backdooring attacks in federated learning through comprehensive experiments using synthetic and the LEAF benchmarks. The initial impression driven by our experimental results suggests that data heterogeneity is the dominant factor in the effectiveness of attacks and it may be a redemption for defending against backdooring as it makes the attack less efficient, more chal…
Hyperparameter optimization (HPO) is crucial for machine learning algorithms to achieve satisfactory performance, whose progress has been boosted by related benchmarks. Nonetheless, existing efforts in benchmarking all focus on HPO for traditional centralized learning while ignoring federated learning (FL), a promising paradigm for collaboratively learning models from dispersed data. In this paper, we first identify some uniqueness of HPO for FL algorithms from various aspects. Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting. …
In conventional federated learning (FL), differential privacy (DP) guarantees can be obtained by injecting additional noise to local model updates before transmitting to the parameter server (PS). In the wireless FL scenario, we show that the privacy of the system can be boosted by exploiting over-the-air computation (OAC) and anonymizing the transmitting devices. In OAC, devices transmit their model updates simultaneously and in an uncoded fashion, resulting in a much more efficient use of the available spectrum. We further exploit OAC to provide anonymity for the transmitting devices. The pr…
University of Twente（特文特大学）；Renmin University of China（中国人民大学）；Peking University（北京大学）
In this paper, we propose a gradient boosting algorithm for large-scale regression problems called \textit{Gradient Boosted Binary Histogram Ensemble} (GBBHE) based on binary histogram partition and ensemble learning. From the theoretical perspective, by assuming the Hölder continuity of the target function, we establish the statistical convergence rate of GBBHE in the space $C^{0,α}$ and $C^{1,0}$, where a lower bound of the convergence rate for the base learner demonstrates the advantage of boosting. Moreover, in the space $C^{1,0}$, we prove that the number of iterations to achieve the fast…
Federated learning (FL) has become a prevalent distributed machine learning paradigm with improved privacy. After learning, the resulting federated model should be further personalized to each different client. While several methods have been proposed to achieve personalization, they are typically limited to a single local device, which may incur bias or overfitting since data in a single device is extremely limited. In this paper, we attempt to realize personalization beyond a single client. The motivation is that during FL, there may exist many clients with similar data distribution, and thu…
Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning
Institute for Neuroinformatics, Ruhr University Bochum（波鸿鲁尔大学神经信息学研究所）；Monash University（莫纳什大学）；Case Western Reserve University（凯斯西储大学）；Carenostics（Carenostics公司）
Exploiting Test-Time Augmentation in Federated Learning for Brain Tumor MRI Classification
Institute of Exact and Technological Sciences, Federal University of Viçosa - UFV, Rio Paranaíba-MG, Brazil（精确与技术科学研究所，弗拉维亚联邦大学-UFV，里奥帕拉纳伊巴-MG，巴西）；Department of Computing, Federal University of São Carlos, São Carlos-SP, Brazil（计算系，萨o卡洛斯联邦大学，萨o卡洛斯-SP，巴西）
Department of Medical Data Science（医学数据科学系）；Wakayama Medical University（福冈医疗大学）；Department of Biomedical Sciences and Informatics（生物医学科学与信息学系）；Doshisha University（多摩大学）；Department of Biostatistics（生物统计学系）
Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院清华-伯克利深圳学院）；Tsinghua University（清华大学）
In a modern power system, real-time data on power generation/consumption and its relevant features are stored in various distributed parties, including household meters, transformer stations and external organizations. To fully exploit the underlying patterns of these distributed data for accurate power prediction, federated learning is needed as a collaborative but privacy-preserving training scheme. However, current federated learning frameworks are polarized towards addressing either the horizontal or vertical separation of data, and tend to overlook the case where both are present. Further…
On Electric Vehicle Energy Demand Forecasting and the Effect of Federated Learning
Department of Informatics, University of Piraeus（信息学院，比雷埃克斯大学）；Center for Power and Energy Systems, INESC TEC（能源系统中心，INESC TEC）；Department of Statistics and Insurance Science, University of Piraeus（统计与保险科学系，比雷埃克斯大学）
In this paper, we study the problem of federated learning over a wireless channel with user sampling, modeled by a Gaussian multiple access channel, subject to central and local differential privacy (DP/LDP) constraints. It has been shown that the superposition nature of the wireless channel provides a dual benefit of bandwidth efficient gradient aggregation, in conjunction with strong DP guarantees for the users. Specifically, the central DP privacy leakage has been shown to scale as $\mathcal{O}(1/K^{1/2})$, where $K$ is the number of users. It has also been shown that user sampling coupled …
Shenzhen University（深圳大学）；Macquarie University（麦考瑞大学）；Georgia State University（佐治亚州立大学）
Federated Learning (FL) is an emerging decentralized learning framework through which multiple clients can collaboratively train a learning model. However, a major obstacle that impedes the wide deployment of FL lies in massive communication traffic. To train high dimensional machine learning models (such as CNN models), heavy communication traffic can be incurred by exchanging model updates via the Internet between clients and the parameter server (PS), implying that the network resource can be easily exhausted. Compressing model updates is an effective way to reduce the traffic amount. Howev…
Efficient Federated Learning with Enhanced Privacy via Lottery Ticket Pruning in Edge Computing
Tsinghua University（清华大学）；JD Explore Academy（京东探索研究院）；Hong Kong Polytechnic University（香港理工大学）；Nanjing University of Science and Technology（南京理工大学）；Shenzhen Wisdom and Strategy Technology Co., Ltd.（深圳智略科技有限公司）
FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework
Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究院）；School of Data Science, The Chinese University of HongKong (Shenzhen)（香港中文大学（深圳）数据科学学院）；School of Computer Science, Northwest Polytechnical University（西北工业大学计算机学院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）
University of California, Davis（加州大学戴维斯分校）；Google Research（谷歌研究院）
In this paper, we present a novel massively parallel algorithm for accelerating the decision tree building procedure on GPUs (Graphics Processing Units), which is a crucial step in Gradient Boosted Decision Tree (GBDT) and random forests training. Previous GPU based tree building algorithms are based on parallel multi-scan or radix sort to find the exact tree split, and thus suffer from scalability and performance issues. We show that using a histogram based algorithm to approximately find the best split is more efficient and scalable on GPU. By identifying the difference between classical GPU…
Gradient boosted decision trees (GBDTs) are widely used in machine learning, and the output of current GBDT implementations is a single variable. When there are multiple outputs, GBDT constructs multiple trees corresponding to the output variables. The correlations between variables are ignored by such a strategy causing redundancy of the learned tree structures. In this paper, we propose a general method to learn GBDT for multiple outputs, called GBDT-MO. Each leaf of GBDT-MO constructs predictions of all variables or a subset of automatically selected variables. This is achieved by consideri…
Department of Electronic Science, Xiamen University（厦门大学电子科学系）
Gradient boosted decision trees (GBDT) is the leading algorithm for many commercial and academic data applications. We give a deep analysis of this algorithm, especially the histogram technique, which is a basis for the regulized distribution with compact support. We present three new modifications. 1) Share memory technique to reduce memory usage. In many cases, it only need the data source itself and no extra memory. 2) Implicit merging for "merge overflow problem"."merge overflow" means that merge some small datasets to huge datasets, which are too huge to be solved. By implicit merging, we…
