The aim of this work is to develop a fully-distributed algorithmic framework for training graph convolutional networks (GCNs). The proposed method is able to exploit the meaningful relational structure of the input data, which are collected by a set of agents that communicate over a sparse network topology. After formulating the centralized GCN training problem, we first show how to make inference in a distributed scenario where the underlying data graph is split among different agents. Then, we propose a distributed gradient descent procedure to solve the GCN training problem. The resulting model distributes computation along three lines: during inference, during back-propagation, and during optimization. Convergence to stationary solutions of the GCN training problem is also established under mild conditions. Finally, we propose an optimization criterion to design the communication topology between agents in order to match with the graph describing data relationships. A wide set of numerical results validate our proposal. To the best of our knowledge, this is the first work combining graph convolutional neural networks with distributed optimization.
Texas Advanced Computing Center（德州高级计算中心）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Chicago（芝加哥大学）；Argonne National Laboratory（阿贡国家实验室）
Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales. The Kronecker-factored Approximate Curvature (K-FAC) was recently proposed as an approximation of the Fisher Information Matrix that can be used in natural gradient optimizers. We investigate here a scalable K-FAC design and its applicability in convolutional neural network (CNN) training at scale. We study optimization techniques such as layer-wise distribution strategies, inverse-free second-order gradient evaluation, and dynamic K-FAC …
Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture has to be manually set by domain experts, generally by a costly trial and error procedure, which often accounts for a large portion of the final system performance. We view this as a limitation and propose a novel training algorithm that automatically optimizes network architecture, by progressively increasing model complexity and then eliminating model redund…
We address the issue of speeding up the training of convolutional neural networks by studying a distributed method adapted to stochastic gradient descent. Our parallel optimization setup uses several threads, each applying individual gradient descents on a local variable. We propose a new way of sharing information between different threads based on gossip algorithms that show good consensus convergence properties. Our method called GoSGD has the advantage to be fully asynchronous and decentralized.
It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy gradient updates resulting from arithmetic with limited numeric precision. One of the well-accepted solutions facilitating the training of low precision fixed point networks is stochastic rounding. However, to the best of our knowledge, the source of the instability in training neural networks with noisy gradient updates has not been well investigated. This wo…
Graph Convolutional Networks (GCNs) is the state-of-the-art method for learning graph-structured data, and training large-scale GCNs requires distributed training across multiple accelerators such that each accelerator is able to hold a partitioned subgraph. However, distributed GCN training incurs prohibitive overhead of communicating node features and feature gradients among partitions for every GCN layer during each training iteration, limiting the achievable training efficiency and model scalability. To this end, we propose PipeGCN, a simple yet effective scheme that hides the communicatio…
Graph Convolutional Networks (GCNs) are known to suffer from performance degradation as the number of layers increases, which is usually attributed to over-smoothing. Despite the apparent consensus, we observe that there exists a discrepancy between the theoretical understanding of over-smoothing and the practical capabilities of GCNs. Specifically, we argue that over-smoothing does not necessarily happen in practice, a deeper model is provably expressive, can converge to global optimum with linear convergence rate, and achieve very high training accuracy as long as properly trained. Despite b…
Graph convolutional networks (GCNs) have been employed as a kind of significant tool on many graph-based applications recently. Inspired by convolutional neural networks (CNNs), GCNs generate the embeddings of nodes by aggregating the information of their neighbors layer by layer. However, the high computational and memory cost of GCNs due to the recursive neighborhood expansion across GCN layers makes it infeasible for training on large graphs. To tackle this issue, several sampling methods during the process of information aggregation have been proposed to train GCNs in a mini-batch Stochast…
CMLA, ENS Paris-Saclay, Université Paris-Saclay（巴黎萨克雷高等师范学院、巴黎萨克雷大学数学与应用数学中心）；L2TI, Université Paris 13（巴黎第十三大学信息处理与交互技术实验室）
In this paper, we introduce DICOD, a convolutional sparse coding algorithm which builds shift invariant representations for long signals. This algorithm is designed to run in a distributed setting, with local message passing, making it communication efficient. It is based on coordinate descent and uses locally greedy updates which accelerate the resolution compared to greedy coordinate selection. We prove the convergence of this algorithm and highlight its computational speed-up which is super-linear in the number of cores used. We also provide empirical evidence for the acceleration propertie…
INRIA（法国国家信息与自动化研究所）；Université Paris Saclay（巴黎萨克雷大学）
Convolutional dictionary learning (CDL) estimates shift invariant basis adapted to multidimensional data. CDL has proven useful for image denoising or inpainting, as well as for pattern discovery on multivariate signals. As estimated patterns can be positioned anywhere in signals or images, optimization techniques face the difficulty of working in extremely high dimensions with millions of pixels or time samples, contrarily to standard patch-based dictionary learning. To address this optimization problem, this work proposes a distributed and asynchronous algorithm, employing locally greedy coo…
Clarkson University（克拉克森大学）；New York Power Authority（纽约电力局）；National Renewable Energy Research Laboratory（国家可再生能源研究实验室）
This paper presents a 1-D convolutional graph neural network for fault detection in microgrids. The combination of 1-D convolutional neural networks (1D-CNN) and graph convolutional networks (GCN) helps extract both spatial-temporal correlations from the voltage measurements in microgrids. The fault detection scheme includes fault event detection, fault type and phase classification, and fault location. There are five neural network model training to handle these tasks. Transfer learning and fine-tuning are applied to reduce training efforts. The combined recurrent graph convolutional neural n…
Severe constraints on memory and computation characterizing the Internet-of-Things (IoT) units may prevent the execution of Deep Learning (DL)-based solutions, which typically demand large memory and high processing load. In order to support a real-time execution of the considered DL model at the IoT unit level, DL solutions must be designed having in mind constraints on memory and processing capability exposed by the chosen IoT technology. In this paper, we introduce a design methodology aiming at allocating the execution of Convolutional Neural Networks (CNNs) on a distributed IoT applicatio…
Training Graph Convolutional Networks (GCNs) is expensive as it needs to aggregate data recursively from neighboring nodes. To reduce the computation overhead, previous works have proposed various neighbor sampling methods that estimate the aggregation result based on a small number of sampled neighbors. Although these methods have successfully accelerated the training, they mainly focus on the single-machine setting. As real-world graphs are large, training GCNs in distributed systems is desirable. However, we found that the existing neighbor sampling methods do not work well in a distributed…
The University of Georgia（佐治亚大学）；Innopolis University（因诺波利斯大学）
In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data-modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided a weakly established model based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into tim…
Chalmers University of Technology（查尔姆斯理工大学）；University of Southern California（南加州大学）
Modern machine learning techniques are successfully being adapted to data modeled as graphs. However, many real-world graphs are typically very large and do not fit in memory, often making the problem of training machine learning models on them intractable. Distributed training has been successfully employed to alleviate memory problems and speed up training in machine learning domains in which the input data is assumed to be independently identical distributed (i.i.d). However, distributing the training of non i.i.d data such as graphs that are used as training inputs in Graph Convolutional N…
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to achieve spatial diversity and multiplexing gains. In a frequency division duplex (FDD) multiuser massive MIMO network, each user needs to compress and feedback its downlink CSI to the BS. The CSI overhead scales with the number of antennas, users and subcarriers, and becomes a major bottleneck for the overall spectral efficiency. In this paper, we propose a deep learning (DL)-based CSI compression scheme, called DeepCMC, composed of convolutional layers followed by…
School of Computing, Tokyo Institute of Technology（东京工业大学计算学院）；NVIDIA（英伟达）；Global Scientific Information and Computing Center, Tokyo Institute of Technology（东京工业大学全球科学信息与计算中心）；RIKEN Center for Computational Science（理化学研究所计算科学中心）
Large-scale distributed training of deep neural networks suffer from the generalization gap caused by the increase in the effective mini-batch size. Previous approaches try to solve this problem by varying the learning rate and batch size over epochs and layers, or some ad hoc modification of the batch normalization. We propose an alternative approach using a second-order optimization method that shows similar generalization capability to first-order methods, but converges faster and can handle larger mini-batches. To test our method on a benchmark where highly optimized first-order methods ar…
The State Key Laboratory of Integrated Service Networks, Xidian University（西安电子科技大学综合业务网理论及关键技术国家重点实验室）；Department of Computer Science and Informatics, Emory University（埃默里大学计算机科学与信息学系）；Department of Computer Science, George Mason University（乔治梅森大学计算机科学系）
The Graph Convolutional Network (GCN) has been successfully applied to many graph-based applications. Training a large-scale GCN model, however, is still challenging: Due to the node dependency and layer dependency of the GCN architecture, a huge amount of computational time and memory is required in the training process. In this paper, we propose a parallel and distributed GCN training algorithm based on the Alternating Direction Method of Multipliers (ADMM) to tackle the two challenges simultaneously. We first split GCN layers into independent blocks to achieve layer parallelism. Furthermore…
In recent years, Graph Convolutional Networks (GCNs) have achieved great success in learning from graph-structured data. With the growing tendency of graph nodes and edges, GCN training by single processor cannot meet the demand for time and memory, which led to a boom into distributed GCN training frameworks research. However, existing distributed GCN training frameworks require enormous communication costs between processors since multitudes of dependent nodes and edges information need to be collected and transmitted for GCN training from other processors. To address this issue, we propose …
A Distributed Hybrid Quantum Convolutional Neural Network for Medical Image Classification
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education（教育部智能感知与图像理解重点实验室）；Joint International Research Laboratory of Intelligent Perception and Computation（智能感知与计算联合国际研究实验室）；Collaborative Innovation Center of Quantum Information of Shaanxi Province（陕西省量子信息协同创新中心）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）
Osnabrück University（奥斯纳布吕克大学）；Osnabrück University of Applied Sciences（奥斯纳布吕克应用科学大学）
When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implication, these CNNs are unnecessarily resource intensive to train and deploy, with diminishing beneficial effects on the predictive performance. The features a convolutional layer can process are strictly limited by its receptive field. By layer-wise analyzing the size of the receptive fields, we can reliably predict sequences of layers that will not contribute qualitatively to the test accuracy in the given CNN architec…
IBM T.J. Watson Research Center（IBM T.J. Watson 研究中心）
In a previous work we have detailed the requirements to obtain a maximal performance benefit by implementing fully connected deep neural networks (DNN) in form of arrays of resistive devices for deep learning. This concept of Resistive Processing Unit (RPU) devices we extend here towards convolutional neural networks (CNNs). We show how to map the convolutional layers to RPU arrays such that the parallelism of the hardware can be fully utilized in all three cycles of the backpropagation algorithm. We find that the noise and bound limitations imposed due to analog nature of the computations per…
The increasing popularity of server usage has brought a plenty of anomaly log events, which have threatened a vast collection of machines. Recognizing and categorizing the anomalous events thereby is a much salient work for our systems, especially the ones generate the massive amount of data and harness it for technology value creation and business development. To assist in focusing on the classification and the prediction of anomaly events, and gaining critical insights from system event records, we propose a novel log preprocessing method which is very effective to filter abundant informatio…
The graph convolutional network (GCN) is a go-to solution for machine learning on graphs, but its training is notoriously difficult to scale both in terms of graph size and the number of model parameters. Although some work has explored training on large-scale graphs (e.g., GraphSAGE, ClusterGCN, etc.), we pioneer efficient training of large-scale GCN models (i.e., ultra-wide, overparameterized models) with the proposal of a novel, distributed training framework. Our proposed training methodology, called GIST, disjointly partitions the parameters of a GCN model into several, smaller sub-GCNs t…
The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of these filters and data, called band-limiting, during training. The frequency domain constraints apply to both the feed-forward and back-propagation steps. Experimentally, we observe that Convolutional Neural Networks (CNNs) are resilient to this compression scheme and results suggest that CNNs learn to leverage lower-frequency components. In particular, we f…
Universidade da Beira Interior（贝拉内格罗大学）；Instituto de Telecomunicações（电信研究所）
Artificial Intelligence algorithms have been steadily increasing in popularity and usage. Deep Learning, allows neural networks to be trained using huge datasets and also removes the need for human extracted features, as it automates the feature learning process. In the hearth of training deep neural networks, such as Convolutional Neural Networks, we find backpropagation, that by computing the gradient of the loss function with respect to the weights of the network for a given input, it allows the weights of the network to be adjusted to better perform in the given task. In this paper, we pro…
Peking University（北京大学）；Samsung Research China - Beijing (SRC-B)（三星中国研究院北京分院）；Beijing Institute of Big Data Research (BIBDR)（北京大数据研究院）
Graph Convolutional Networks(GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised(M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popul…
Imagination Technologies（想象力科技）；University of Warwick（华威大学）
Graph Convolutional Networks (GCNs) are extensively utilized for deep learning on graphs. The large data sizes of graphs and their vertex features make scalable training algorithms and distributed memory systems necessary. Since the convolution operation on graphs induces irregular memory access patterns, designing a memory- and communication-efficient parallel algorithm for GCN training poses unique challenges. We propose a highly parallel training algorithm that scales to large processor counts. In our solution, the large adjacency and vertex-feature matrices are partitioned among processors…
IBM Research – Zurich（IBM苏黎世研究院）；Queen’s University of Belfast（贝尔法斯特女王大学）
We propose an incremental training method that partitions the original network into sub-networks, which are then gradually incorporated in the running network during the training process. To allow for a smooth dynamic growth of the network, we introduce a look-ahead initialization that outperforms the random initialization. We demonstrate that our incremental approach reaches the reference network baseline accuracy. Additionally, it allows to identify smaller partitions of the original state-of-the-art network, that deliver the same final accuracy, by using only a fraction of the global number…
This paper presents an iterative pruning strategy for Convolutional Network Fabrics (CNF) in presence of noisy training and testing data. With the continuous increase in size of neural network models, various authors have developed pruning approaches to build more compact network structures requiring less resources, while preserving performance. As we show in this paper, because of their intrinsic structure and function, Convolutional Network Fabrics are ideal candidates for pruning. We present a series of pruning strategies that can significantly reduce both the final network size and require…
We propose DoReFa-Net, a method to train convolutional neural networks that have low bitwidth weights and activations using low bitwidth parameter gradients. In particular, during backward pass, parameter gradients are stochastically quantized to low bitwidth numbers before being propagated to convolutional layers. As convolutions during forward/backward passes can now operate on low bitwidth weights and activations/gradients respectively, DoReFa-Net can use bit convolution kernels to accelerate both training and inference. Moreover, as bit convolutions can be efficiently implemented on CPU, F…
We consider the classical problem of scheduling task graphs corresponding to complex applications on distributed computing systems. A number of heuristics have been previously proposed to optimize task scheduling with respect to metrics such as makespan and throughput. However, they tend to be slow to run, particularly for larger problem instances, limiting their applicability in more dynamic systems. Motivated by the goal of solving these problems more rapidly, we propose, for the first time, a graph convolutional network-based scheduler (GCNScheduler). By carefully integrating an inter-task …
Courant Institute of Mathematical Sciences（库朗数学科学研究所）；New York University（纽约大学）
Convolutional networks are one of the most widely employed architectures in computer vision and machine learning. In order to leverage their ability to learn complex functions, large amounts of data are required for training. Training a large convolutional network to produce state-of-the-art results can take weeks, even when using modern GPUs. Producing labels using a trained network can also be costly when dealing with web-scale datasets. In this work, we present a simple algorithm which accelerates training and inference by a significant factor, and can yield improvements of over an order of…
School of Electrical Engineering（电气工程学院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））；Daejeon, Republic of Korea（大邱，韩国）
There were many algorithms to substitute the back-propagation (BP) in the deep neural network (DNN) training. However, they could not become popular because their training accuracy and the computational efficiency were worse than BP. One of them was direct feedback alignment (DFA), but it showed low training performance especially for the convolutional neural network (CNN). In this paper, we overcome the limitation of the DFA algorithm by combining with the conventional BP during the CNN training. To improve the training stability, we also suggest the feedback weight initialization method by a…
Hyperparameters tuning is a time-consuming approach, particularly when the architecture of the neural network is decided as part of this process. For instance, in convolutional neural networks (CNNs), the selection of the number and the characteristics of the hidden (convolutional) layers may be decided. This implies that the search process involves the training of all these candidate network architectures. This paper describes a proposal to reuse the weights of hidden (convolutional) layers among different trainings to shorten this process. The rationale is that if a set of convolutional laye…
University of Chinese Academy of Sciences（中国科学院大学）
Deep learning refers to the shining branch of machine learning that is based on learning levels of representations. Convolutional Neural Networks (CNN) is one kind of deep neural network. It can study concurrently. In this article, we gave a detailed analysis of the process of CNN algorithm both the forward process and back propagation. Then we applied the particular convolutional neural network to implement the typical face recognition problem by java. Then, a parallel strategy was proposed in section4. In addition, by measuring the actual time of forward and backward computing, we analysed t…
Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is still not clear. This paper demonstrates that max-pooling dropout is equivalent to randomly picking activation based on a multinomial distribution at training time. In light of this insight, we advocate employing our proposed probabilistic weighted pooling, instead of commonly used max-pooling, to act as model averaging at test time. Empirical evidence validates the superiority of …
Data imbalance remains one of the open challenges in the contemporary machine learning. It is especially prevalent in case of medical data, such as histopathological images. Traditional data-level approaches for dealing with data imbalance are ill-suited for image data: oversampling methods such as SMOTE and its derivatives lead to creation of unrealistic synthetic observations, whereas undersampling reduces the amount of available data, critical for successful training of convolutional neural networks. To alleviate the problems associated with over- and undersampling we propose a novel two-st…
Deep Learning techniques have achieved remarkable results in many domains. Often, training deep learning models requires large datasets, which may require sensitive information to be uploaded to the cloud to accelerate training. To adequately protect sensitive information, we propose distributed layer-partitioned training with step-wise activation functions for privacy-preserving deep learning. Experimental results attest our method to be simple and effective.
Hunan University（湖南大学）；National Supercomputing Center in Changsha（长沙国家超级计算中心）；COMSATS University Islamabad（伊斯兰堡COMSATS大学）；Qatar University（卡塔尔大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Tsinghua University（清华大学）
Benefitting from large-scale training datasets and the complex training network, Convolutional Neural Networks (CNNs) are widely applied in various fields with high accuracy. However, the training process of CNNs is very time-consuming, where large amounts of training samples and iterative operations are required to obtain high-quality weight parameters. In this paper, we focus on the time-consuming training process of large-scale CNNs and propose a Bi-layered Parallel Training (BPT-CNN) architecture in distributed computing environments. BPT-CNN consists of two main components: (a) an outer-l…
University of Toronto（多伦多大学）；The Hospital for Sick Children（病童医院）；Lunenfeld-Tanenbaum Research Institute, Sinai Health System（西奈健康系统 Lunenfeld-Tanenbaum 研究所）；Sunnybrook Research Institute（新宁布鲁克研究所）
Receiver operating characteristic (ROC) curve is an informative tool in binary classification and Area Under ROC Curve (AUC) is a popular metric for reporting performance of binary classifiers. In this paper, first we present a comprehensive review of ROC curve and AUC metric. Next, we propose a modified version of AUC that takes confidence of the model into account and at the same time, incorporates AUC into Binary Cross Entropy (BCE) loss used for training a Convolutional neural Network for classification tasks. We demonstrate this on three datasets: MNIST, prostate MRI, and brain MRI. Furth…
Peking University（北京大学）；Beijing Institute of Big Data Research (BIBDR)（北京大数据研究院）
The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversarial regularization method based on both labeled and unlabeled data, on the supervised loss of GCN to enhance its generalization performance. By imposing virtually adversarial smoothness on the posterior distribution in semi-supervised learning, VAT yields improvement on the Symmetr…
Rice University（莱斯大学）；Technical University of Munich（慕尼黑工业大学）
Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem arises in recent approaches for solving inverse problems such as the deep image prior or the deep decoder. We show that for this setup, channel normalization, which centers and normalizes each channel individually, avoids vanishing gradients, whereas, without normalization, gradients vanish which prevents efficient optimization. This effect prevails in deep singl…
In recent years, substantial progress has been made on Graph Convolutional Networks (GCNs). However, the computing of GCN usually requires a large memory space for keeping the entire graph. In consequence, GCN is not flexible enough, especially for large scale graphs in complex real-world applications. Fortunately, methods based on Matrix Factorization (MF) naturally support constructing mini-batches, and thus are more friendly to distributed computing compared with GCN. Accordingly, in this paper, we analyze the connections between GCN and MF, and simplify GCN as matrix factorization with uni…
In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obvious existence of such complex relationships in many real-world networks naturaly motivates the problem of learning with hypergraphs. A popular learning paradigm is hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabeled vertices in a hypergraph. Motivated by the fact that a graph convolutional netw…
New York University（纽约大学）；Facebook AI Research（脸书人工智能研究院）
The availability of large labeled datasets has allowed Convolutional Network models to achieve impressive recognition results. However, in many settings manual annotation of the data is impractical; instead our data has noisy labels, i.e. there is some freely available label for each image which may or may not be accurate. In this paper, we explore the performance of discriminatively-trained Convnets when trained on such noisy data. We introduce an extra noise layer into the network which adapts the network outputs to match the noisy label distribution. The parameters of this noise layer can b…
HKUST-Qualcomm Joint Innovation and Research Laboratory（香港科技大学-高通联合创新研究实验室）；Dept. ECE, Hong Kong University of Science and Technology（香港科技大学电子及计算机工程系）
With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy efficiency of distributed learning in real life. This paper describes a novel approach of training DNNs exploiting the redundancy and the weight asymmetry potential of conventional backpropagation. We demonstrate that with negligible classification accuracy loss, the proposed approach outperforms the prior arts by 5x in terms of energy efficiency.
City University of Hong Kong（香港城市大学）；HKUST（香港科技大学）；Microsoft Research（微软研究院）
The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact on training time. To tackle the problem, we design a new distributed training system called Stanza. Stanza exploits the fact that in many models such as convolution neural networks, most data exchange is attributed to the fully connected layers, while most computation is carried o…
We present batch virtual adversarial training (BVAT), a novel regularization method for graph convolutional networks (GCNs). BVAT addresses the shortcoming of GCNs that do not consider the smoothness of the model's output distribution against local perturbations around the input. We propose two algorithms, sample-based BVAT and optimization-based BVAT, which are suitable to promote the smoothness of the model for graph-structured data by either finding virtual adversarial perturbations for a subset of nodes far from each other or generating virtual adversarial perturbations for all nodes with …
School of Optoelectronic, Beijing Institute of Technology（北京理工大学光电学院）；Graduate School at Shenzhen, Tsinghua University（清华大学深圳研究生院）；BGI Research（华大研究院）
In this paper, we propose the nonlinearity generation method to speed up and stabilize the training of deep convolutional neural networks. The proposed method modifies a family of activation functions as nonlinearity generators (NGs). NGs make the activation functions linear symmetric for their inputs to lower model capacity, and automatically introduce nonlinearity to enhance the capacity of the model during training. The proposed method can be considered an unusual form of regularization: the model parameters are obtained by training a relatively low-capacity model, that is relatively easy t…
Convolutional neural networks are very popular nowadays. Training neural networks is not an easy task. Each convolution corresponds to a structured transformation matrix. In order to help avoid the exploding/vanishing gradient problem, it is desirable that the singular values of each transformation matrix are not large/small in the training process. We propose three new regularization terms for a convolutional kernel tensor to constrain the singular values of each transformation matrix. We show how to carry out the gradient type methods, which provides new insight about the training of convolu…
Recent works show that Graph Neural Networks (GNNs) are highly non-robust with respect to adversarial attacks on both the graph structure and the node attributes, making their outcomes unreliable. We propose the first method for certifiable (non-)robustness of graph convolutional networks with respect to perturbations of the node attributes. We consider the case of binary node attributes (e.g. bag-of-words) and perturbations that are L_0-bounded. If a node has been certified with our method, it is guaranteed to be robust under any possible perturbation given the attack model. Likewise, we can …
