Distributed learning, particularly variants of distributed stochastic gradient descent (DSGD), are widely employed to speed up training by leveraging computational resources of several workers. However, in practise, communication delay becomes a bottleneck due to the significant amount of information that needs to be exchanged between the workers and the parameter server. One of the most efficient strategies to mitigate the communication bottleneck is top-K sparsification. However, top-K sparsification requires additional communication load to represent the sparsity pattern, and the mismatch between the sparsity patterns of the workers prevents exploitation of efficient communication protocols. To address these issues, we introduce a novel majority voting based sparse communication strategy, in which the workers first seek a consensus on the structure of the sparse representation. This strategy provides a significant reduction in the communication load and allows using the same sparsity level in both communication directions. Through extensive simulations on the CIFAR-10 dataset, we show that it is possible to achieve up to x4000 compression without any loss in the test accuracy.
As a promising distributed learning technology, analog aggregation based federated learning over the air (FLOA) provides high communication efficiency and privacy provisioning under the edge computing paradigm. When all edge devices (workers) simultaneously upload their local updates to the parameter server (PS) through commonly shared time-frequency resources, the PS obtains the averaged update only rather than the individual local ones. While such a concurrent transmission and aggregation scheme reduces the latency and communication costs, it unfortunately renders FLOA vulnerable to Byzantin…
Khulna University of Engineering and Technology（库尔纳工程技术大学）
This paper proposes an approach to detect emotion from human speech employing majority voting technique over several machine learning techniques. The contribution of this work is in two folds: firstly it selects those features of speech which is most promising for classification and secondly it uses the majority voting technique that selects the exact class of emotion. Here, majority voting technique has been applied over Neural Network (NN), Decision Tree (DT), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Input vector of NN, DT, SVM and KNN consists of various acoustic and proso…
Federated learning is a distributed machine learning mechanism where local devices collaboratively train a shared global model under the orchestration of a central server, while keeping all private data decentralized. In the system, model parameters and its updates are transmitted instead of raw data, and thus the communication bottleneck has become a key challenge. Besides, recent larger and deeper machine learning models also pose more difficulties in deploying them in a federated environment. In this paper, we design a federated two-stage learning framework that augments prototypical federa…
University of Minnesota, Twin Cities（明尼苏达大学双城分校）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Recent empirical work on stochastic gradient descent (SGD) applied to over-parameterized deep learning has shown that most gradient components over epochs are quite small. Inspired by such observations, we rigorously study properties of Truncated SGD (T-SGD), that truncates the majority of small gradient components to zeros. Considering non-convex optimization problems, we show that the convergence rate of T-SGD matches the order of vanilla SGD. We also establish the generalization error bound for T-SGD. Further, we propose Noisy Truncated SGD (NT-SGD), which adds Gaussian noise to the truncat…
Caltech（加州理工学院）；UC Irvine（加州大学欧文分校）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Training neural networks on large datasets can be accelerated by distributing the workload over a network of machines. As datasets grow ever larger, networks of hundreds or thousands of machines become economically viable. The time cost of communicating gradients limits the effectiveness of using such large machine counts, as may the increased chance of network faults. We explore a particularly simple algorithm for robust, communication-efficient learning---signSGD. Workers transmit only the sign of their gradient vector to a server, and the overall update is decided by a majority vote. This a…
University College London（伦敦大学学院）；Inria（法国国家信息与自动化研究所）；ServiceNow Research（ServiceNow研究院）
We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory. These provide state-of-the-art guarantees on a number of classification tasks. Our central results leverage the Dirichlet posteriors studied recently by Zantedeschi et al. [2021] for training voting classifiers; in contrast to that work our bounds apply to non-randomised votes via the use of margins. Our contributions add perspective to the debate on the "margins theory" proposed by Schapire et al. [1998] for the generalisation of en…
Despite superior training outcomes, adaptive optimization methods such as Adam, Adagrad or RMSprop have been found to generalize poorly compared to Stochastic gradient descent (SGD). These methods tend to perform well in the initial portion of training but are outperformed by SGD at later stages of training. We investigate a hybrid strategy that begins training with an adaptive method and switches to SGD when appropriate. Concretely, we propose SWATS, a simple strategy which switches from Adam to SGD when a triggering condition is satisfied. The condition we propose relates to the projection o…
Amazon AI（亚马逊人工智能）；Caltech（加州理工学院）；UC Santa Barbara（加州大学圣巴巴拉分校）；UC Irvine（加州大学欧文分校）
Training large neural networks requires distributing learning across multiple workers, where the cost of communicating gradients can be a significant bottleneck. signSGD alleviates this problem by transmitting just the sign of each minibatch stochastic gradient. We prove that it can get the best of both worlds: compressed gradients and SGD-level convergence rate. The relative $\ell_1/\ell_2$ geometry of gradients, noise and curvature informs whether signSGD or SGD is theoretically better suited to a particular problem. On the practical side we find that the momentum counterpart of signSGD is a…
Amazon Web Services（亚马逊云科技）；Hong Kong University of Science and Technology（香港科技大学）
Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of distributed neural network training. Using 1-bit quantization, signSGD with majority vote achieves a 32x reduction on communication cost. However, its convergence is based on unrealistic assumptions and can diverge in practice. In this paper, we propose a general distributed compressed SGD with Nesterov's momentum. We consider two-way compression, which compresses the…
Stochastic gradient descent without replacement sampling is widely used in practice for model training. However, the vast majority of SGD analyses assumes data is sampled with replacement, and when the function minimized is strongly convex, an $\mathcal{O}\left(\frac{1}{T}\right)$ rate can be established when SGD is run for $T$ iterations. A recent line of breakthrough works on SGD without replacement (SGDo) established an $\mathcal{O}\left(\frac{n}{T^2}\right)$ convergence rate when the function minimized is strongly convex and is a sum of $n$ smooth functions, and an $\mathcal{O}\left(\frac{…
In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networks employing the sigmoid function as an activation function. Our empirical study shows that a choice of a loss function used in training processes for the network is of prime importance. We found a loss function suitable for sparse signal recovery, which includes a cross entropy-like term and an $L_1$ regularized term. From the experimental results, we observed that the majorit…
We study the performance of stochastic gradient descent (SGD) on smooth and strongly-convex finite-sum optimization problems. In contrast to the majority of existing theoretical works, which assume that individual functions are sampled with replacement, we focus here on popular but poorly-understood heuristics, which involve going over random permutations of the individual functions. This setting has been investigated in several recent works, but the optimal error rates remain unclear. In this paper, we provide lower bounds on the expected optimization error with these heuristics (using SGD wi…
The Blavatnik School of Computer Science（布拉瓦尼克计算机科学学院）；Tel Aviv University（特拉维夫大学）
This work presents a new distributed Byzantine tolerant federated learning algorithm, HoldOut SGD, for Stochastic Gradient Descent (SGD) optimization. HoldOut SGD uses the well known machine learning technique of holdout estimation, in a distributed fashion, in order to select parameter updates that are likely to lead to models with low loss values. This makes it more effective at discarding Byzantine workers inputs than existing methods that eliminate outliers in the parameter-space of the learned model. HoldOut SGD first randomly selects a set of workers that use their private data in order …
Crowdsourcing has become an effective and popular tool for human-powered computation to label large datasets. Since the workers can be unreliable, it is common in crowdsourcing to assign multiple workers to one task, and to aggregate the labels in order to obtain results of high quality. In this paper, we provide finite-sample exponential bounds on the error rate (in probability and in expectation) of general aggregation rules under the Dawid-Skene crowdsourcing model. The bounds are derived for multi-class labeling, and can be used to analyze many aggregation methods, including majority votin…
National Kapodistrian Univ. of Athens (NKUA/UoA)（雅典国立卡波季斯特里安大学）；University of Houston (UH)（休斯顿大学）
In this paper, a novel approach for the optimal combination of binary classifiers is proposed. The classifier combination problem is approached from a Game Theory perspective. The proposed framework of adapted weighted majority rules (WMR) is tested against common rank-based, Bayesian and simple majority models, as well as two soft-output averaging rules. Experiments with ensembles of Support Vector Machines (SVM), Ordinary Binary Tree Classifiers (OBTC) and weighted k-nearest-neighbor (w/k-NN) models on benchmark datasets indicate that this new adaptive WMR model, employing local accuracy est…
Ensemble-based approaches are very effective in various fields in raising the accuracy of its individual members, when some voting rule is applied for aggregating the individual decisions. In this paper, we investigate how to find and characterize the ensembles having the highest accuracy if the total cost of the ensemble members is bounded. This question leads to Knapsack problem with non-linear and non-separable objective function in binary and multiclass classification if the majority voting is chosen for the aggregation. As the conventional solving methods cannot be applied for this task, …
Johannes Kepler University Linz（约翰内斯·开普勒大学林茨分校）；JKU LIT SAL；Institute of Signal Processing（信号处理研究所）
In recent years, machine learning methods became increasingly important for a manifold number of applications. However, they often suffer from high computational requirements impairing their efficient use in real-time systems, even when employing dedicated hardware accelerators. Ensemble learning methods are especially suitable for hardware acceleration since they can be constructed from individual learners of low complexity and thus offer large parallelization potential. For classification, the outputs of these learners are typically combined by majority voting, which often represents the bot…
Using Machine Learning and Deep Learning to predict cognitive tasks from electroencephalography (EEG) signals is a rapidly advancing field in Brain-Computer Interfaces (BCI). In contrast to the fields of computer vision and natural language processing, the data amount of these trials is still rather tiny. Developing a PC-based machine learning technique to increase the participation of non-expert end-users could help solve this data collection issue. We created a novel algorithm for machine learning called Time Majority Voting (TMV). In our experiment, TMV performed better than cutting-edge al…
Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information
Massachusetts Institute of Technology（麻省理工学院）；School of Engineering and Applied Sciences（工程与应用科学学院）；Harvard University（哈佛大学）；Data Science, The University of Chicago（数据科学，芝加哥大学）
Deep Neural Networks (DNNs) are prone to overfitting and hence have high variance. Overfitted networks do not perform well for a new data instance. So instead of using a single DNN as classifier we propose an ensemble of seven independent DNN learners by varying only the input to these DNNs keeping their architecture and intrinsic properties same. To induce variety in the training input, for each of the seven DNNs, one-seventh of the data is deleted and replenished by bootstrap sampling from the remaining samples. We have proposed a novel technique for combining the prediction of the DNN learn…
VoteGCL: Enhancing Graph-based Recommendations with Majority-Voting LLM-Rerank Augmentation
Center for AI Research, VinUniversity（越南 Vin 大学人工智能研究中心）；The Chinese University of Hong Kong（香港中文大学）；RMIT University（皇家墨尔本理工大学）；VNU University of Engineering and Technology（越南工程与技术大学）
Dept. of Electrical and Computer Engineering（电气与计算机工程系）；Carnegie Mellon University（卡内基梅隆大学）；Dept. of Electrical Engineering（电气工程系）；Bilkent University（比尔肯特大学）
Obtaining high-quality parallel corpora is of paramount importance for training NMT systems. However, as many language pairs lack adequate gold-standard training data, a popular approach has been to mine so-called "pseudo-parallel" sentences from paired documents in two languages. In this paper, we outline some problems with current methods, propose computationally economical solutions to those problems, and demonstrate success with novel methods on the Tatoeba similarity search benchmark and on a downstream task, namely NMT. We uncover the effect of resource-related factors (i.e. how much mon…
Derandomizing Simultaneous Confidence Regions for Band-Limited Functions by Improved Norm Bounds and Majority-Voting Schemes
HUN-REN SZTAKI: Institute for Computer Science and Control, Hungarian Research Network（匈牙利研究网络：计算机科学与控制研究所）；Department of Probability Theory and Statistics, Institute of Mathematics, Eötvös Loránd University (ELTE)（概率论与统计学系，数学研究所，欧多尼·洛朗德大学（ELTE））；Institute of Mathematics, Eötvös Loránd University (ELTE)（数学研究所，欧多尼·洛朗德大学（ELTE））；Budapest University of Technology and Economics (BME)（布达佩斯技术与经济大学（BME））
Playtika Brain；Yandex School of Data Science（Yandex数据科学学院）；Tel Aviv University（特拉维夫大学）；Technion – Israel Institute of Technology（以色列理工学院）
There is a striking relationship between a three hundred years old Political Science theorem named "Condorcet's jury theorem" (1785), which states that majorities are more likely to choose correctly when individual votes are often correct and independent, and a modern Machine Learning concept called "Strength of Weak Learnability" (1990), which describes a method for converting a weak learning algorithm into one that achieves arbitrarily high accuracy and stands in the basis of Ensemble Learning. Albeit the intuitive statement of Condorcet's theorem, we could not find a compact and simple rigo…
Wisdom of the crowd revealed a striking fact that the majority answer from a crowd is often more accurate than any individual expert. We observed the same story in machine learning--ensemble methods leverage this idea to combine multiple learning algorithms to obtain better classification performance. Among many popular examples is the celebrated Random Forest, which applies the majority voting rule in aggregating different decision trees to make the final prediction. Nonetheless, these aggregation rules would fail when the majority is more likely to be wrong. In this paper, we extend the idea…
We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In our final model, we combine the output of CNN models using "average voting", "majority voting" and "optimal weights" methods. Furthermore, we exploit the ensemble library by deploying a Random Forest model as a meta-learner. The ensemble method with random forest as meta-learner s…
LASTIMI, High School of Technology Mohammed V University in Rabat Sale, Morocco；LASTIMI, Mohammedia School of Engineers Mohammed V University in Rabat Rabat, Morocco；CISIEV. Faculty of Science；Technology in Marrakech Cadi Ayyad University Marrakech, Morocco
Coronary artery disease (CAD) is one of the most common cardiac diseases worldwide and causes disability and economic burden. It is the world's leading and most serious cause of mortality, with approximately 80% of deaths reported in low- and middle-income countries. The preferred and most precise diagnostic tool for CAD is angiography, but it is invasive, expensive, and technically demanding. However, the research community is increasingly interested in the computer-aided diagnosis of CAD via the utilization of machine learning (ML) methods. The purpose of this work is to present an e-diagnos…
NYU Polytechnic School of Engineering（纽约大学理工学院）；Courant Institute of Mathematical Sciences（库朗数学科学研究所）；Google Research（谷歌研究院）；Facebook（脸书）
We consider supervised learning with random decision trees, where the tree construction is completely random. The method is popularly used and works well in practice despite the simplicity of the setting, but its statistical mechanism is not yet well-understood. In this paper we provide strong theoretical guarantees regarding learning with random decision trees. We analyze and compare three different variants of the algorithm that have minimal memory requirements: majority voting, threshold averaging and probabilistic averaging. The random structure of the tree enables us to adapt these method…
