Federated Topic Model and Model Pruning Based on Variational Autoencoder
Beijing Key Laboratory of Intelligent Communication Software and Multimedia（智能通信软件与多媒体北京重点实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）；School of Economics and Management（经济管理学院）
Chengjie Ma, Yawen Li, Meiyu Liang, Ang Li
备注：
7 pages
发表信息：
In Proceedings of 2023 Chinese Intelligent Automation Conference, 2023: 51-60
Topic modeling has emerged as a valuable tool for discovering patterns and topics within large collections of documents. However, when cross-analysis involves multiple parties, data privacy becomes a critical concern. Federated topic modeling has been developed to address this issue, allowing multiple parties to jointly train models while protecting privacy. However, there are communication and performance challenges in the federated scenario. To solve these problems, this paper proposes a method to establish a federated topic model while ensuring the privacy of each node and uses neural network model pruning to accelerate the model. The client periodically sends cumulative neuron gradients and model weights to the server, and the server prunes the model. To address different requirements, two methods are proposed to determine the pruning rate. The first slowly prunes throughout training, which has limited acceleration during training but can ensure higher accuracy and significantly reduce inference time. The second quickly reaches the target pruning rate early in training and then continues training with a smaller model. This approach may lose more useful information but can complete training faster. Experimental results show that the proposed variational-autoencoder-based federated topic model pruning can greatly accelerate training while maintaining model performance.
Stanford University（斯坦福大学）；Facebook AI Research（Facebook人工智能研究院）
Variational autoencoders (VAE) are directed generative models that learn factorial latent variables. As noted by Burda et al. (2015), these models exhibit the problem of factor over-pruning where a significant number of stochastic factors fail to learn anything and become inactive. This can limit their modeling power and their ability to learn diverse and meaningful latent representations. In this paper, we evaluate several methods to address this problem and propose a more effective model-based approach called the epitomic variational autoencoder (eVAE). The so-called epitomes of this model a…
Technical University of Munich（慕尼黑工业大学）；Mercateo AG（Mercateo公司）
Variational autoencoder (VAE) is a widely used generative model for learning latent representations. Burda et al. in their seminal paper showed that learning capacity of VAE is limited by over-pruning. It is a phenomenon where a significant number of latent variables fail to capture any information about the input data and the corresponding hidden units become inactive. This adversely affects learning diverse and interpretable latent representations. As variational graph autoencoder (VGAE) extends VAE for graph-structured data, it inherits the over-pruning problem. In this paper, we adopt a mo…
Binary Neural Networks (BNNs), neural networks with weights and activations constrained to -1(0) and +1, are an alternative to deep neural networks which offer faster training, lower memory consumption and lightweight models, ideal for use in resource constrained devices while being able to utilize the architecture of their deep neural network counterpart. However, the input binarization step used in BNNs causes a severe accuracy loss. In this paper, we introduce a novel hybrid neural network architecture, Hybrid Binary Neural Network (HyBNN), consisting of a task-independent, general, full-pr…
Probabilistic circuits (PCs) are a tractable representation of probability distributions allowing for exact and efficient computation of likelihoods and marginals. There has been significant recent progress on improving the scale and expressiveness of PCs. However, PC training performance plateaus as model size increases. We discover that most capacity in existing large PC structures is wasted: fully-connected parameter layers are only sparsely used. We propose two operations: pruning and growing, that exploit the sparsity of PC structures. Specifically, the pruning operation removes unimporta…
Automatic Speech Recognition models require large amount of speech data for training, and the collection of such data often leads to privacy concerns. Federated learning has been widely used and is considered to be an effective decentralized technique by collaboratively learning a shared prediction model while keeping the data local on different clients devices. However, the limited computation and communication resources on clients devices present practical difficulties for large models. To overcome such challenges, we propose Federated Pruning to train a reduced model under the federated set…
Estimation of the value-at-risk (VaR) of a large portfolio of assets is an important task for financial institutions. As the joint log-returns of asset prices can often be projected to a latent space of a much smaller dimension, the use of a variational autoencoder (VAE) for estimating the VaR is a natural suggestion. To ensure the bottleneck structure of autoencoders when learning sequential data, we use a temporal VAE (TempVAE) that avoids an auto-regressive structure for the observation variables. However, the low signal- to-noise ratio of financial data in combination with the auto-pruning…
Although variational autoencoders (VAE) are successfully used to obtain meaningful low-dimensional representations for high-dimensional data, the characterization of critical points of the loss function for general observation models is not fully understood. We introduce a theoretical framework that is based on a connection between $β$-VAE and generalized linear models (GLM). The equality between the activation function of a $β$-VAE and the inverse of the link function of a GLM enables us to provide a systematic generalization of the loss analysis for $β$-VAE based on the assumption that the o…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；Stevens Neuroimaging and Informatics Institute, University of Southern California（南加州大学史蒂文斯神经影像与信息学研究所）
Federated training of large deep neural networks can often be restrictive due to the increasing costs of communicating the updates with increasing model sizes. Various model pruning techniques have been designed in centralized settings to reduce inference times. Combining centralized pruning techniques with federated training seems intuitive for reducing communication costs -- by pruning the model parameters right before the communication step. Moreover, such a progressive model pruning approach during training can also reduce training times/costs. To this end, we propose FedSparsify, which pe…
Tsinghua University（清华大学）；Huawei Wireless Technology Lab（华为无线技术实验室）；Hong Kong University of Science and Technology（香港科技大学）
Federated learning (FL) has prevailed as an efficient and privacy-preserved scheme for distributed learning. In this work, we mainly focus on the optimization of computation and communication in FL from a view of pruning. By adopting layer-wise pruning in local training and federated updating, we formulate an explicit FL pruning framework, FedLP (Federated Layer-wise Pruning), which is model-agnostic and universal for different types of deep learning models. Two specific schemes of FedLP are designed for scenarios with homogeneous local models and heterogeneous ones. Both theoretical and exper…
George Washington University（乔治华盛顿大学）；Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）
One of the biggest challenges in Federated Learning (FL) is that client devices often have drastically different computation and communication resources for local updates. To this end, recent research efforts have focused on training heterogeneous local models obtained by pruning a shared global model. Despite empirical success, theoretical guarantees on convergence remain an open question. In this paper, we present a unifying framework for heterogeneous FL algorithms with {\em arbitrary} adaptive online model pruning and provide a general convergence analysis. In particular, we prove that und…
We introduce ADMM-pruned Compressive AutoEncoder (CAE-ADMM) that uses Alternative Direction Method of Multipliers (ADMM) to optimize the trade-off between distortion and efficiency of lossy image compression. Specifically, ADMM in our method is to promote sparsity to implicitly optimize the bitrate, different from entropy estimators used in the previous research. The experiments on public datasets show that our method outperforms the original CAE and some traditional codecs in terms of SSIM/MS-SSIM metrics, at reasonable inference speed.
Exploring Federated Pruning for Large Language Models
The University of Hong Kong（香港大学）；Southern University of Science and Technology（南方科技大学）；Sun Yat-sen University（中山大学）；Guangming Laboratory（光明实验室）；Hangzhou Dianzi University（杭州电子科技大学）
Hong Kong University of Science and Technology（香港科技大学）；University of Science and Technology China（中国科学技术大学）；University of Cambridge（剑桥大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）
Federated learning alleviates the privacy risk in distributed learning by transmitting only the local model updates to the central server. However, it faces challenges including statistical heterogeneity of clients' datasets and resource constraints of client devices, which severely impact the training performance and user experience. Prior works have tackled these challenges by combining personalization with model compression schemes including quantization and pruning. However, the pruning is data-dependent and thus must be done on the client side which requires considerable computation cost.…
Pruning-aware Loss Functions for STOI-Optimized Pruned Recurrent Autoencoders for the Compression of the Stimulation Patterns of Cochlear Implants at Zero Delay
Artificial neural network has achieved unprecedented success in a wide variety of domains such as classifying, predicting and recognizing objects. This success depends on the availability of big data since the training process requires massive and representative data sets. However, data collection is often prevented by privacy concerns and people want to take control over their sensitive information during both training and using processes. To address this problem, we propose a privacy-preserving method for the distributed system, Stochastic Channel-Based Federated Learning (SCBF), which enabl…
The traditional approach in FL tries to learn a single global model collaboratively with the help of many clients under the orchestration of a central server. However, learning a single global model might not work well for all clients participating in the FL under data heterogeneity. Therefore, the personalization of the global model becomes crucial in handling the challenges that arise with statistical heterogeneity and the non-IID distribution of data. Unlike prior works, in this work we propose a new approach for obtaining a personalized model from a client-level objective. This further mot…
Modeling Quantum Federated Autoencoder for Anomaly Detection in IoT Networks
School of Information Technology Deakin University Geelong, Australia（信息技术学院，德金大学，澳大利亚吉朗）；School of Information Technology Deakin University Geelong, Melbourne（信息技术学院，德金大学，澳大利亚吉朗墨尔本）；School of Information Technology, Deakin University, Geelong, Australia（信息技术学院，德金大学，澳大利亚吉朗）
Iowa State University（爱荷华州立大学）；University of Minnesota（明尼苏达大学）
Federated Learning (FL) has emerged as a new paradigm for training machine learning models distributively without sacrificing data security and privacy. Learning models on edge devices such as mobile phones is one of the most common use cases for FL. However, Non-identical independent distributed~(non-IID) data in edge devices easily leads to training failures. Especially, over-parameterized machine learning models can easily be over-fitted on such data, hence, resulting in inefficient federated learning and poor model performance. To overcome the over-fitting issue, we proposed an adaptive dy…
Yale University（耶鲁大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Stanford Institute for Human-Centered Artificial Intelligence（斯坦福人类中心人工智能研究所）；Imperial College London（帝国理工学院）
Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a datacenter. To overcome this challenge, we propose PruneFL -- a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maint…
Beijing University of Posts and Telecommunications（北京邮电大学）
In this letter, we study a wireless federated learning (FL) system where network pruning is applied to local users with limited resources. Although pruning is beneficial to reduce FL latency, it also deteriorates learning performance due to the information loss. Thus, a trade-off problem between communication and learning is raised. To address this challenge, we quantify the effects of network pruning and packet error on the learning performance by deriving the convergence rate of FL with a non-convex loss function. Then, closed-form solutions for pruning control and bandwidth allocation are p…
Federated Learning (FL) is a privacy-preserving distributed deep learning paradigm that involves substantial communication and computation effort, which is a problem for resource-constrained mobile and IoT devices. Model pruning/sparsification develops sparse models that could solve this problem, but existing sparsification solutions cannot satisfy at the same time the requirements for low bidirectional communication overhead between the server and the clients, low computation overhead at the clients, and good model accuracy, under the FL assumption that the server does not have access to raw …
Machine learning has been applied to almost all fields of computer science over the past decades. The introduction of GANs allowed for new possibilities in fields of medical research and text prediction. However, these new fields work with ever more privacy-sensitive data. In order to maintain user privacy, a combination of federated learning, differential privacy and GANs can be used to work with private data without giving away a users' privacy. Recently, two implementations of such combinations have been published: DP-Fed-Avg GAN and GS-WGAN. This paper compares their performance and introd…
How Pruning Reshapes Features: Sparse Autoencoder Analysis of Weight-Pruned Language Models
organization= VRAIN -- Valencian Research Institute for Artificial Intelligence, Universitat Polit\`ecnica de Val\`encia , city= Valencia , country= Spain；organization= Department of Economics；organization= Department of Business Organisation, Universitat Polit\`ecnica de Val\`encia , city= Valencia , country= Spain
