Federated learning is a decentralized approach for training models on distributed devices, by summarizing local changes and sending aggregate parameters from local models to the cloud rather than the data itself. In this research we employ the idea of transfer learning to federated training for next word prediction (NWP) and conduct a number of experiments demonstrating enhancements to current baselines for which federated NWP models have been successful. Specifically, we compare federated training baselines from randomly initialized models to various combinations of pretraining approaches including pretrained word embeddings and whole model pretraining followed by federated fine tuning for NWP on a dataset of Stack Overflow posts. We realize lift in performance using pretrained embeddings without exacerbating the number of required training rounds or memory footprint. We also observe notable differences using centrally pretrained networks, especially depending on the datasets used. Our research offers effective, yet inexpensive, improvements to federated NWP and paves the way for more rigorous experimentation of transfer learning techniques for federated learning.
Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections
National Center for Tumor Diseases (NCT)（国家肿瘤中心）；Translational Surgical Oncology（转化外科肿瘤学）；Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology（医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）；DKFZ, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD Dresden University of Technology（德累斯顿大学技术大学医学系和德累斯顿癌症研究中心）；Helmholtz-Zentrum Dresden-Rossendorf (HZDR)（德累斯顿-罗斯多夫亥姆霍兹中心）；Centre for Tactile Internet with Human-in-the-Loop (CeTI), TU Dresden（具有人类在环的触觉互联网中心，德累斯顿技术大学）；Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden（visceral、胸外科和血管外科，医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）；Weldon School of Biomedical Engineering, Purdue University（生物医学工程韦尔登学校，普渡大学）；Medical Oncology, NCT, University Hospital Heidelberg, Germany（医学肿瘤学，国家肿瘤中心，海德堡大学医院，德国）；Medicine I, Faculty of Medicine and University Hospital Carl Gustav Carus, TU Dresden（医学I，医学系和图林根大学技术大学卡尔·古斯塔夫·卡尔医院）
A Step Toward Federated Pretraining of Multimodal Large Language Models
MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统实验室）；King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；Pengcheng Laboratory（鹏城实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS)（中国科学院大学人工智能学院）
We propose a practical approach based on federated learning to solve out-of-domain issues with continuously running embedded speech-based models such as wake word detectors. We conduct an extensive empirical study of the federated averaging algorithm for the "Hey Snips" wake word based on a crowdsourced dataset that mimics a federation of wake word users. We empirically demonstrate that using an adaptive averaging strategy inspired from Adam in place of standard weighted model averaging highly reduces the number of communication rounds required to reach our target performance. The associated u…
We show that a word-level recurrent neural network can predict emoji from text typed on a mobile keyboard. We demonstrate the usefulness of transfer learning for predicting emoji by pretraining the model using a language modeling task. We also propose mechanisms to trigger emoji and tune the diversity of candidates. The model is trained using a distributed on-device learning framework called federated learning. The federated model is shown to achieve better performance than a server-trained model. This work demonstrates the feasibility of using federated learning to train production-quality mo…
Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards without revealing what individual users type. We demonstrate that any participant in federated learning can introduce hidden backdoor functionality into the joint global model, e.g., to ensure that an image classifier assigns an attacker-chosen label to images with certain features, or that a word predictor completes certain sentences with an attacker-chosen wo…
Federated learning with differential privacy, i.e. private federated learning (PFL), makes it possible to train models on private data distributed across users' devices without harming privacy. PFL is efficient for models, such as neural networks, that have a fixed number of parameters, and thus a fixed-dimensional gradient vector. Such models include neural-net language models, but not tokenizers, the topic of this work. Training a tokenizer requires frequencies of words from an unlimited vocabulary, and existing methods for finding an unlimited vocabulary need a separate privacy budget. A wo…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
Federated learning has made an important contribution to data privacy-preserving. Many previous works are based on the assumption that the data are independently identically distributed (IID). As a result, the model performance on non-identically independently distributed (non-IID) data is beyond expectation, which is the concrete situation. Some existing methods of ensuring the model robustness on non-IID data, like the data-sharing strategy or pretraining, may lead to privacy leaking. In addition, there exist some participants who try to poison the model with low-quality data. In this paper,…
We propose algorithms to train production-quality n-gram language models using federated learning. Federated learning is a distributed computation platform that can be used to train global models for portable devices such as smart phones. Federated learning is especially relevant for applications handling privacy-sensitive data, such as virtual keyboards, because training is performed without the users' data ever leaving their devices. While the principles of federated learning are fairly generic, its methodology assumes that the underlying models are neural networks. However, virtual keyboard…
Automatically mining sentiment tendency contained in natural language is a fundamental research to some artificial intelligent applications, where solutions alternate with challenges. Transfer learning and multi-task learning techniques have been leveraged to mitigate the supervision sparsity and collaborate multiple heterogeneous domains correspondingly. Recent years, the sensitive nature of users' private data raises another challenge for sentiment classification, i.e., data privacy protection. In this paper, we resort to federated learning for multiple domain sentiment classification under …
Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eavesdropping attacker can effectively recover image data from gradients transmitted during federated learning. However, little progress has been made in recovering text data. In this paper, we present a novel attack method FILM for federated learning of language models (LMs). For the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences. Unlike image-recovery methods that ar…
Personalization methods in federated learning aim to balance the benefits of federated and local training for data availability, communication cost, and robustness to client heterogeneity. Approaches that require clients to communicate all model parameters can be undesirable due to privacy and communication constraints. Other approaches require always-available or stateful clients, impractical in large-scale cross-device settings. We introduce Federated Reconstruction, the first model-agnostic framework for partially local federated learning suitable for training and inference at scale. We mot…
Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）
Large scale contextual representation models, such as BERT, have significantly advanced natural language processing (NLP) in recently years. However, in certain area like healthcare, accessing diverse large scale text data from multiple institutions is extremely challenging due to privacy and regulatory reasons. In this article, we show that it is possible to both pretrain and fine tune BERT models in a federated manner using clinical texts from different silos without moving the data.
University of Michigan（密歇根大学）；University of Cambridge（剑桥大学）；Nokia Bell Labs（诺基亚贝尔实验室）
Federated learning is generally used in tasks where labels are readily available (e.g., next word prediction). Relaxing this constraint requires design of unsupervised learning techniques that can support desirable properties for federated training: robustness to statistical/systems heterogeneity, scalability with number of participants, and communication efficiency. Prior work on this topic has focused on directly extending centralized self-supervised learning techniques, which are not designed to have the properties listed above. To address this situation, we propose Orchestra, a novel unsup…
Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaining to the communication and computation costs associated with clients' devices. These costs are strongly correlated with the size of the model being trained, and are significant for state-of-the-art automatic speech recognition models. We propose using federated dropout to reduce the size of client models while training a full-size model server-side. We provide empirical evidence of the effectiveness of federated dro…
A significant bottleneck in federated learning (FL) is the network communication cost of sending model updates from client devices to the central server. We present a comprehensive empirical study of the statistics of model updates in FL, as well as the role and benefits of various compression techniques. Motivated by these observations, we propose a novel method to reduce the average communication cost, which is near-optimal in many use cases, and outperforms Top-K, DRIVE, 3LC and QSGD on Stack Overflow next-word prediction, a realistic and challenging FL benchmark. This is achieved by examin…
Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the framework to poison the global model for an adversarial purpose. This paper investigates the feasibility of model poisoning for backdoor attacks through rare word embeddings of NLP models. In text classification, less than 1% of adversary clients suffices to manipulate the model output without any drop in the performance on clean sentences. For a less complex…
DP2FL: Dual Prompt Personalized Federated Learning in Foundation Models
College of Software, Jilin University（吉林大学软件学院）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Computer Science and Engineering, Changchun University of Technology（长春理工大学计算机科学与工程学院）
Establishing how a set of learners can provide privacy-preserving federated learning in a fully decentralized (peer-to-peer, no coordinator) manner is an open problem. We propose the first privacy-preserving consensus-based algorithm for the distributed learners to achieve decentralized global model aggregation in an environment of high mobility, where the communication graph between the learners may vary between successive rounds of model aggregation. In particular, in each round of global model aggregation, the Metropolis-Hastings method is applied to update the weighted adjacency matrix bas…
Federated learning (FL) is a heavily promoted approach for training ML models on sensitive data, e.g., text typed by users on their smartphones. FL is expressly designed for training on data that are unbalanced and non-iid across the participants. To ensure privacy and integrity of the fedeated model, latest FL approaches use differential privacy or robust aggregation. We look at FL from the \emph{local} viewpoint of an individual participant and ask: (1) do participants have an incentive to participate in FL? (2) how can participants \emph{individually} improve the quality of their local mode…
Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic speech recognition (ASR). One way of compressing the embedding and softmax layers is to substitute larger units such as words with smaller sub-units such as characters. However, often the sub-unit models perform poorly compared to the larger unit models. We propose WEST, an algorith…
Purdue University（普渡大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）
Traditional learning-based approaches to student modeling generalize poorly to underrepresented student groups due to biases in data availability. In this paper, we propose a methodology for predicting student performance from their online learning activities that optimizes inference accuracy over different demographic groups such as race and gender. Building upon recent foundations in federated learning, in our approach, personalized models for individual student subgroups are derived from a global model aggregated across all student models via meta-gradient updates that account for subgroup …
This paper presents a study on the use of federated learning to train an ASR model based on a wav2vec 2.0 model pre-trained by self supervision. Carried out on the well-known TED-LIUM 3 dataset, our experiments show that such a model can obtain, with no use of a language model, a word error rate of 10.92% on the official TED-LIUM 3 test set, without sharing any data from the different users. We also analyse the ASR performance for speakers depending to their participation to the federated learning. Since federated learning was first introduced for privacy purposes, we also measure its ability …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Purdue University（普渡大学）；Microsoft（微软）；Nokia Bell Labs（诺基亚贝尔实验室）
Federated learning is a promising framework for learning over decentralized data spanning multiple regions. This approach avoids expensive central training data aggregation cost and can improve privacy because distributed sites do not have to reveal privacy-sensitive data. In this paper, we develop a privacy-preserving decentralized aggregation protocol for federated learning. We formulate the distributed aggregation protocol with the Alternating Direction Method of Multiplier (ADMM) and examine its privacy weakness. Unlike prior work that use Differential Privacy or homomorphic encryption for…
Label Granularity Skew in Federated Learning with Hierarchical Image Classification
School of Computer Science and Engineering, Soongsil University（崇实大学计算机科学与工程学院）；School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）
University of Maryland（马里兰大学）；Google（谷歌）；Johns Hopkins University（约翰斯·霍普金斯大学）；New York University（纽约大学）
Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is limited because their updates are quickly drowned out by those of many other users. Existing attacks do not account for future behaviors of other users, and thus require many sequential updates and their effects are quickly erased. We propose an attack that anticipates and accounts for the entire federated learning pipeline, including behaviors of other clients, a…
University of Cambridge（剑桥大学）；Avignon University（阿维尼翁大学）；Telecom Paris（巴黎电信）；University of Oxford（牛津大学）；Adap GmbH（Adap有限责任公司）
Training Automatic Speech Recognition (ASR) models under federated learning (FL) settings has attracted a lot of attention recently. However, the FL scenarios often presented in the literature are artificial and fail to capture the complexity of real FL systems. In this paper, we construct a challenging and realistic ASR federated experimental setup consisting of clients with heterogeneous data distributions using the French and Italian sets of the CommonVoice dataset, a large heterogeneous dataset containing thousands of different speakers, acoustic environments and noises. We present the fir…
University of Tokyo（东京大学）；United Nations University（联合国大学）
With increasingly more sophisticated phishing campaigns in recent years, phishing emails lure people using more legitimate-looking personal contexts. To tackle this problem, instead of traditional heuristics-based algorithms, more adaptive detection systems such as natural language processing (NLP)-powered approaches are essential to understanding phishing text representations. Nevertheless, concerns surrounding the collection of phishing data that might cover confidential information hinder the effectiveness of model learning. We propose a decentralized phishing email detection framework call…
PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks
Department of Computer Science, Virginia Tech（维吉尼亚理工大学计算机科学系）；US DEVCOM Army Research Laboratory（美国陆军研发实验室）；Department of Computer Science, Old Dominion University（旧 Dominion 大学计算机科学系）；Department of Electrical and Computer Engineering, University of Arizona（亚利桑那大学电气与计算机工程系）
A Selective Homomorphic Encryption Approach for Faster Privacy-Preserving Federated Learning
A. Korkmaz Dept. of Electrical Engineering \& Computer Science, The University of Missouri, Columbia, USA P. Rao Dept. of Electrical Engineering \& Computer Science, The University of Missouri, Columbia, USA
UNESCO Chair in Data Privacy（联合国教科文组织数据隐私教席）；CYBERCAT-Center for Cybersecurity Research of Catalonia（CYBERCAT-加泰罗尼亚网络安全研究中心）；Universitat Rovira i Virgili（罗维拉-威尔吉利大学）
The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private data may, when sent to the model manager, leak information on those private data. Even more obvious are security attacks, whereby one or several malicious peers return wrong model updates in order to disrupt the learning process and lead to a wrong model being learned. In this paper we build a federated learning framework that offers privacy to the participati…
KTH Royal Institute of Technology（瑞典皇家理工学院）；RISE Research Institutes of Sweden（瑞典研究院）
Large scale contextual representation models have significantly advanced NLP in recent years, understanding the semantics of text to a degree never seen before. However, they need to process large amounts of data to achieve high-quality results. Joining and accessing all these data from multiple sources can be extremely challenging due to privacy and regulatory reasons. Federated Learning can solve these limitations by training models in a distributed fashion, taking advantage of the hardware of the devices that generate the data. We show the viability of training NLP models, specifically Word…
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods. Recent findings have shown that the accuracy and robustness of unsupervised word translation (UWT) can be improved by making use of visual observations, which are universal representations across languages. In this work, we investigate the potential of using not only visual observations but also pretrained language-image models for enabling a more efficient and robust UWT. Specifically, we develop a novel UWT method dubbed Word Alignment using Language-Image Pretraining (WALIP), which…
Clinical notes in electronic health records contain highly heterogeneous writing styles, including non-standard terminology or abbreviations. Using these notes in predictive modeling has traditionally required preprocessing (e.g. taking frequent terms or topic modeling) that removes much of the richness of the source data. We propose a pretrained hierarchical recurrent neural network model that parses minimally processed clinical notes in an intuitive fashion, and show that it improves performance for discharge diagnosis classification tasks on the Medical Information Mart for Intensive Care I…
We examine the effects of contrastive visual semantic pretraining by comparing the geometry and semantic properties of contextualized English language representations formed by GPT-2 and CLIP, a zero-shot multimodal image classifier which adapts the GPT-2 architecture to encode image captions. We find that contrastive visual semantic pretraining significantly mitigates the anisotropy found in contextualized word embeddings from GPT-2, such that the intra-layer self-similarity (mean pairwise cosine similarity) of CLIP word embeddings is under .25 in all layers, compared to greater than .95 in t…
Universidade da Coruña（拉科鲁尼亚大学）；CITIC, Ciencias de la Computación y Tecnologías de la Información (CC&TI)（CITIC，计算机科学与信息技术（CC&TI））；University of Copenhagen, Department of Computer Science（哥本哈根大学计算机科学系）；Google Research, Berlin（谷歌研究院柏林分院）；Google Research（谷歌研究院）；Berlin（柏林（注：此处仅保留机构名本身，Berlin为城市名，按要求不提取额外信息，故仅提取Google Research））
Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups such as constituent and dependency parsing. This paper addresses this problem and does full parsing (on English) relying only on pretraining architectures -- and no decoding. We first cast constituent and dependency parsing as sequence tagging. We then use a single feed-forward layer to directly map word vectors to labels that encode a linearized tree. This is used to: (i) see how far we ca…
ImageNet-1K serves as the primary dataset for pretraining deep learning models for computer vision tasks. ImageNet-21K dataset, which is bigger and more diverse, is used less frequently for pretraining, mainly due to its complexity, low accessibility, and underestimation of its added value. This paper aims to close this gap, and make high-quality efficient pretraining on ImageNet-21K available for everyone. Via a dedicated preprocessing stage, utilization of WordNet hierarchical structure, and a novel training scheme called semantic softmax, we show that various models significantly benefit fr…
Previous text-based depression detection is commonly based on large user-generated data. Sparse scenarios like clinical conversations are less investigated. This work proposes a text-based multi-task BGRU network with pretrained word embeddings to model patients' responses during clinical interviews. Our main approach uses a novel multi-task loss function, aiming at modeling both depression severity and binary health state. We independently investigate word- and sentence-level word-embeddings as well as the use of large-data pretraining for depression detection. To strengthen our findings, we …
