In practice, training using federated learning can be orders of magnitude slower than standard centralized training. This severely limits the amount of experimentation and tuning that can be done, making it challenging to obtain good performance on a given task. Server-side proxy data can be used to run training simulations, for instance for hyperparameter tuning. This can greatly speed up the training pipeline by reducing the number of tuning runs to be performed overall on the true clients. However, it is challenging to ensure that these simulations accurately reflect the dynamics of the real federated training. In particular, the proxy data used for simulations often comes as a single centralized dataset without a partition into distinct clients, and partitioning this data in a naive way can lead to simulations that poorly reflect real federated training. In this paper we address the challenge of how to partition centralized data in a way that reflects the statistical heterogeneity of the true federated clients. We propose a fully federated, theoretically justified, algorithm that efficiently learns the distribution of the true clients and observe improved server-side simulations when using the inferred distribution to create simulated clients from the centralized data.
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）
Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is the recently proposed method FedAUX, an augmentation of federated distillation with robust results on even highly heterogeneous client data. FedAUX is a partially $(ε, δ)$-differentially private method, insofar as the clients' private data is protected in only part of the training it takes part in. This work contributes a fully differentially private modification, termed FedAUXfdp. We further contribute an upper bound…
While client sampling is a central operation of current state-of-the-art federated learning (FL) approaches, the impact of this procedure on the convergence and speed of FL remains under-investigated. In this work, we provide a general theoretical framework to quantify the impact of a client sampling scheme and of the clients heterogeneity on the federated optimization. First, we provide a unified theoretical ground for previously reported sampling schemes experimental results on the relationship between FL convergence and the variance of the aggregation weights. Second, we prove for the first…
Dirichlet-multinomial (DMN) distribution is commonly used to model over-dispersion in count data. Precise and fast numerical computation of the DMN log-likelihood function is important for performing statistical inference using this distribution, and remains a challenge. To address this, we use mathematical properties of the gamma function to derive a closed form expression for the DMN log-likelihood function. Compared to existing methods, calculation of the closed form has a lower computational complexity, hence is much faster without comprimising computational accuracy.
The multinomial and related distributions have long been used to model categorical, count-based data in fields ranging from bioinformatics to natural language processing. Commonly utilized variants include the standard multinomial and the Dirichlet multinomial distributions due to their computational efficiency and straightforward parameter estimation process. However, these distributions make strict assumptions about the mean, variance, and covariance between the categorical features being modeled. If these assumptions are not met by the data, it may result in poor parameter estimates and los…
The Hong Kong Polytechnic University（香港理工大学）；Beijing Institute of Technology（北京理工大学）
Facing the challenge of statistical diversity in client local data distribution, personalized federated learning (PFL) has become a growing research hotspot. Although the state-of-the-art methods with model similarity-based pairwise collaboration have achieved promising performance, they neglect the fact that model aggregation is essentially a collaboration process within the coalition, where the complex multiwise influences take place among clients. In this paper, we first apply Shapley value (SV) from coalition game theory into the PFL scenario. To measure the multiwise collaboration among a…
Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT
Quantum Cloud Computing and Distributed Systems (qCLOUDS) Lab（量子云计算与分布式系统实验室）；School of Computing and Information Systems（计算与信息系统学院）；The University of Melbourne, Australia（墨尔本大学）
Federated learning aims to collaboratively train a strong global model by accessing users' locally trained models but not their own data. A crucial step is therefore to aggregate local models into a global model, which has been shown challenging when users have non-i.i.d. data. In this paper, we propose a novel aggregation algorithm named FedBE, which takes a Bayesian inference perspective by sampling higher-quality global models and combining them via Bayesian model Ensemble, leading to much robust aggregation. We show that an effective model distribution can be constructed by simply fitting …
FedSCAM (Federated Sharpness-Aware Minimization with Clustered Aggregation and Modulation): Scam-resistant SAM for Robust Federated Optimization in Heterogeneous Environments
Department of Computer Science, Lahore University of Management Sciences, Lahore, Pakistan（计算机科学系，拉合尔管理科学大学，拉合尔，巴基斯坦）
OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement
National University of Defense Technology（国防科技大学）；Hebei University of Technology（河北工业大学）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区网络空间科学与技术学院）
High-Energy Concentration for Federated Learning in Frequency Domain
State Key Laboratory of Integrated Services Networks, Xidian University（信息服务网络国家重点实验室，西安电子科技大学）；College of Electrical and Information Engineering, Hunan University（湖南大学电气与信息工程学院）
Choose A Table: Tensor Dirichlet Process Multinomial Mixture Model with Graphs for Passenger Trajectory Clustering
University of Cologne（科隆大学）；Arizona State University（亚利桑那州立大学）；Tsinghua University（清华大学）；McGill University（麦吉尔大学）；The Hong Kong University of Science and Technology（香港科技大学）；HKUST-GZ（香港科技大学（广州））
Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning
Department of Computer, Control；Management Engineering Sapienza University of Rome Rome, Italy；Telef\'onica Research Barcelona, Spain；Keysight AI Labs Barcelona, Spain
In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method widely used in statistical modeling as a dimension reduction tool and combine it with LDA. In this variable selection model for LDA (vsLDA), topics are multinomial distributions over a subset of the vocabulary, and by excluding words that are not informative for finding the latent topic structure of the corpus, vsLDA finds topics that are more robust and discri…
Rethinking Clustered Federated Learning in NOMA Enhanced Wireless Networks
School of Electrical and Electronic Engineering, The University of Manchester（曼彻斯特大学电气与电子工程学院）；Khalifa University（哈利法大学）；Department of Electrical Engineering and Computer Science, Khalifa University（哈利法大学电气工程与计算机科学系）；Department of Electrical and Electronic Engineering, University of Manchester（曼彻斯特大学电气与电子工程学院）
Tensor Dirichlet Process Multinomial Mixture Model for Passenger Trajectory Clustering
University of Cologne（科隆大学）；Arizona State University（亚利桑那州立大学）；Tsinghua University（清华大学）；McGill University（麦吉尔大学）；The Hong Kong University of Science and Technology（香港科技大学）；HKUST (Guangzhou Campus)（香港科技大学（广州校区））
University of Pretoria（比勒陀利亚大学）；Center for Artificial Intelligence Research (CAIR)（人工智能研究中心（CAIR））
Most topic models are constructed under the assumption that documents follow a multinomial distribution. The Poisson distribution is an alternative distribution to describe the probability of count data. For topic modelling, the Poisson distribution describes the number of occurrences of a word in documents of fixed length. The Poisson distribution has been successfully applied in text classification, but its application to topic modelling is not well documented, specifically in the context of a generative probabilistic model. Furthermore, the few Poisson topic models in literature are admixtu…
Hierarchical mixtures of Unigram models for short text clustering: The role of Beta-Liouville priors
Department of Precision and Regenerative Medicine and Jonian Area (DiMePRe-J)（精准与再生医学系及乔尼亚区）；University of Bari Aldo Moro（巴里阿尔多·莫罗大学）；Sirio Astronomical Observatory（西里奥天文台）；Grotte di Castellana srl（卡斯特尔纳纳洞窟有限公司）
In this technical report, we present jLDADMM---an easy-to-use Java toolkit for conventional topic models. jLDADMM is released to provide alternatives for topic modeling on normal or short texts. It provides implementations of the Latent Dirichlet Allocation topic model and the one-topic-per-document Dirichlet Multinomial Mixture model (i.e. mixture of unigrams), using collapsed Gibbs sampling. In addition, jLDADMM supplies a document clustering evaluation to compare topic models. jLDADMM is open-source and available to download at: https://github.com/datquocnguyen/jLDADMM
Politecnico di Milano（米兰理工大学）；Technische Universität Dresden（德累斯顿工业大学）
Survival analysis studies time-modeling techniques for an event of interest occurring for a population. Survival analysis found widespread applications in healthcare, engineering, and social sciences. However, the data needed to train survival models are often distributed, incomplete, censored, and confidential. In this context, federated learning can be exploited to tremendously improve the quality of the models trained on distributed data while preserving user privacy. However, federated survival analysis is still in its early development, and there is no common benchmarking dataset to test …
Chemistry research has both high material and computational costs to conduct experiments. Institutions thus consider chemical data to be valuable and there have been few efforts to construct large public datasets for machine learning. Another challenge is that different intuitions are interested in different classes of molecules, creating heterogeneous data that cannot be easily joined by conventional distributed training. In this work, we introduce federated heterogeneous molecular learning to address these challenges. Federated learning allows end-users to build a global model collaborativel…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；Duke University（杜克大学）；Sun Yat-sen University（中山大学）
Non-negative matrix factorization (NMF) based topic modeling is widely used in natural language processing (NLP) to uncover hidden topics of short text documents. Usually, training a high-quality topic model requires large amount of textual data. In many real-world scenarios, customer textual data should be private and sensitive, precluding uploading to data centers. This paper proposes a Federated NMF (FedNMF) framework, which allows multiple clients to collaboratively train a high-quality NMF based topic model with locally stored data. However, standard federated learning will significantly …
