Search

Despite their success in real data synthesis, diffusion models (DMs) often suffer from slow and costly training and sampling issues, limiting their broader applications. To mitigate this, we propose a Fast Diffusion Model (FDM) which improves the diffusion process of DMs from a stochastic optimization perspective to speed up both training and sampling. Specifically, we first find that the diffusion process of DMs accords with the stochastic optimization process of stochastic gradient descent (SGD) on a stochastic time-variant problem. Note that momentum SGD uses both the current gradient and an extra momentum, achieving more stable and faster convergence. We are inspired to introduce momentum into the diffusion process to accelerate both training and sampling. However, this comes with the challenge of deriving the noise perturbation kernel from the momentum-based diffusion process. To this end, we frame the momentum-based process as a Damped Oscillation system whose critically damped state -- the kernel solution -- avoids oscillation and thus has a faster convergence speed of the diffusion process. Empirical results show that our FDM can be applied to several popular DM frameworks, e.g. VP, VE, and EDM, and reduces their training cost by about 50% with comparable image synthesis performance on CIFAR-10, FFHQ, and AFHQv2 datasets. Moreover, FDM decreases their sampling steps by about $3\times$ to achieve similar performance under the same deterministic samplers. The code is available at https://github.com/sail-sg/FDM.

While the use of graph-structured data in various fields is becoming increasingly popular, it also raises concerns about the potential unauthorized exploitation of personal data for training commercial graph neural network (GNN) models, which can compromise privacy. To address this issue, we propose a novel method for generating unlearnable graph examples. By injecting delusive but imperceptible noise into graphs using our Error-Minimizing Structural Poisoning (EMinS) module, we are able to make the graphs unexploitable. Notably, by modifying only $5\%$ at most of the potential edges in the graph data, our method successfully decreases the accuracy from ${77.33\%}$ to ${42.47\%}$ on the COLLAB dataset., Comment: This paper is accepted as a poster for NDSS 2023

End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing critical edges and thus manipulating the classification results. Current defenses, due to their persistent utilization of global-optimization-based end-to-end training schemes, inherently encapsulate the vulnerabilities of GNNs. This is specifically evidenced in their inability to defend against targeted secondary attacks. In this paper, we propose the Graph Agent Network (GAgN) to address the aforementioned vulnerabilities of GNNs. GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent. Through the decentralized interactions between agents, they can learn to infer global perceptions to perform tasks including inferring embeddings, degrees and neighbor relationships for given nodes. This empowers nodes to filtering adversarial edges while carrying out classification tasks. Furthermore, agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks. We prove that single-hidden-layer multilayer perceptrons (MLPs) are theoretically sufficient to achieve these functionalities. Experimental results show that GAgN effectively implements all its intended capabilities and, compared to state-of-the-art defenses, achieves optimal classification accuracy on the perturbed datasets.

In deep learning, different kinds of deep networks typically need different optimizers, which have to be chosen after multiple trials, making the training process inefficient. To relieve this issue and consistently improve the model training speed across deep networks, we propose the ADAptive Nesterov momentum algorithm, Adan for short. Adan first reformulates the vanilla Nesterov acceleration to develop a new Nesterov momentum estimation (NME) method, which avoids the extra overhead of computing gradient at the extrapolation point. Then Adan adopts NME to estimate the gradient's first- and second-order moments in adaptive gradient algorithms for convergence acceleration. Besides, we prove that Adan finds an $\epsilon$-approximate first-order stationary point within $O(\epsilon^{-3.5})$ stochastic gradient complexity on the non-convex stochastic problems (e.g., deep learning problems), matching the best-known lower bound. Extensive experimental results show that Adan consistently surpasses the corresponding SoTA optimizers on vision, language, and RL tasks and sets new SoTAs for many popular networks and frameworks, e.g., ResNet, ConvNext, ViT, Swin, MAE, DETR, GPT-2, Transformer-XL, and BERT. More surprisingly, Adan can use half of the training cost (epochs) of SoTA optimizers to achieve higher or comparable performance on ViT, GPT-2, MAE, e.t.c., and also shows great tolerance to a large range of minibatch size, e.g., from 1k to 32k. Code is released at https://github.com/sail-sg/Adan, and has been used in multiple popular deep learning frameworks or projects.

For unsupervised pretraining, mask-reconstruction pretraining (MRP) approaches, e.g. MAE and data2vec, randomly mask input patches and then reconstruct the pixels or semantic features of these masked patches via an auto-encoder. Then for a downstream task, supervised fine-tuning the pretrained encoder remarkably surpasses the conventional ``supervised learning'' (SL) trained from scratch. However, it is still unclear 1) how MRP performs semantic feature learning in the pretraining phase and 2) why it helps in downstream tasks. To solve these problems, we first theoretically show that on an auto-encoder of a two/one-layered convolution encoder/decoder, MRP can capture all discriminative features of each potential semantic class in the pretraining dataset. Then considering the fact that the pretraining dataset is of huge size and high diversity and thus covers most features in downstream dataset, in fine-tuning phase, the pretrained encoder can capture as much features as it can in downstream datasets, and would not lost these features with theoretical guarantees. In contrast, SL only randomly captures some features due to lottery ticket hypothesis. So MRP provably achieves better performance than SL on the classification tasks. Experimental results testify to our data assumptions and also our theoretical implications.

Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph-based tasks such as node classification and graph classification. However, many recent works have demonstrated that an attacker can mislead GNN models by slightly perturbing the graph structure. Existing attacks to GNNs are either under the less practical threat model where the attacker is assumed to access the GNN model parameters, or under the practical black-box threat model but consider perturbing node features that are shown to be not enough effective. In this paper, we aim to bridge this gap and consider black-box attacks to GNNs with structure perturbation as well as with theoretical guarantees. We propose to address this challenge through bandit techniques. Specifically, we formulate our attack as an online optimization with bandit feedback. This original problem is essentially NP-hard due to the fact that perturbing the graph structure is a binary optimization problem. We then propose an online attack based on bandit optimization which is proven to be {sublinear} to the query number $T$, i.e., $\mathcal{O}(\sqrt{N}T^{3/4})$ where $N$ is the number of nodes in the graph. Finally, we evaluate our proposed attack by conducting experiments over multiple datasets and GNN models. The experimental results on various citation graphs and image graphs show that our attack is both effective and efficient. Source code is available at~\url{https://github.com/Metaoblivion/Bandit_GNN_Attack}, Comment: Accepted by CVPR 2022 Oral presentation

Recent studies show that Transformer has strong capability of building long-range dependencies, yet is incompetent in capturing high frequencies that predominantly convey local information. To tackle this issue, we present a novel and general-purpose Inception Transformer, or iFormer for short, that effectively learns comprehensive features with both high- and low-frequency information in visual data. Specifically, we design an Inception mixer to explicitly graft the advantages of convolution and max-pooling for capturing the high-frequency information to Transformers. Different from recent hybrid frameworks, the Inception mixer brings greater efficiency through a channel splitting mechanism to adopt parallel convolution/max-pooling path and self-attention path as high- and low-frequency mixers, while having the flexibility to model discriminative information scattered within a wide frequency range. Considering that bottom layers play more roles in capturing high-frequency details while top layers more in modeling low-frequency global information, we further introduce a frequency ramp structure, i.e. gradually decreasing the dimensions fed to the high-frequency mixer and increasing those to the low-frequency mixer, which can effectively trade-off high- and low-frequency components across different layers. We benchmark the iFormer on a series of vision tasks, and showcase that it achieves impressive performance on image classification, COCO detection and ADE20K segmentation. For example, our iFormer-S hits the top-1 accuracy of 83.4% on ImageNet-1K, much higher than DeiT-S by 3.6%, and even slightly better than much bigger model Swin-B (83.3%) with only 1/4 parameters and 1/3 FLOPs. Code and models will be released at https://github.com/sail-sg/iFormer., Comment: Code and models will be released at https://github.com/sail-sg/iFormer

Edge devices in federated learning usually have much more limited computation and communication resources compared to servers in a data center. Recently, advanced model compression methods, like the Lottery Ticket Hypothesis, have already been implemented on federated learning to reduce the model size and communication cost. However, Backdoor Attack can compromise its implementation in the federated learning scenario. The malicious edge device trains the client model with poisoned private data and uploads parameters to the center, embedding a backdoor to the global shared model after unwitting aggregative optimization. During the inference phase, the model with backdoors classifies samples with a certain trigger as one target category, while shows a slight decrease in inference accuracy to clean samples. In this work, we empirically demonstrate that Lottery Ticket models are equally vulnerable to backdoor attacks as the original dense models, and backdoor attacks can influence the structure of extracted tickets. Based on tickets' similarities between each other, we provide a feasible defense for federated learning against backdoor attacks on various datasets.

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability and how to bound it? Is there a way to reduce the adversarial transferability in order to improve the robustness of an ensemble ML model? To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness. Our theoretical analysis shows that only promoting the orthogonality between gradients of base models is not enough to ensure low transferability; in the meantime, the model smoothness is an important factor to control the transferability. We also provide the lower and upper bounds of adversarial transferability under certain conditions. Inspired by our theoretical analysis, we propose an effective Transferability Reduced Smooth(TRS) ensemble training strategy to train a robust ensemble with low transferability by enforcing both gradient orthogonality and model smoothness between base models. We conduct extensive experiments on TRS and compare with 6 state-of-the-art ensemble baselines against 8 whitebox attacks on different datasets, demonstrating that the proposed TRS outperforms all baselines significantly., Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underlying semantic similarity between a query and its positives and negatives, and impairs performance, since some negatives are semantically similar to the query or even share the same semantic class as the query. In this work, we first prove that for contrastive learning, inaccurate label assignment heavily impairs its generalization for semantic instance discrimination, while accurate labels benefit its generalization. Inspired by this theory, we propose a novel self-labeling refinement approach for contrastive learning. It improves the label quality via two complementary modules: (i) self-labeling refinery (SLR) to generate accurate labels and (ii) momentum mixup (MM) to enhance similarity between query and its positive. SLR uses a positive of a query to estimate semantic similarity between a query and its positive and negatives, and combines estimated similarity with vanilla label assignment in contrastive learning to iteratively generate more accurate and informative soft labels. We theoretically show that our SLR can exactly recover the true semantic labels of label-corrupted data, and supervises networks to achieve zero prediction error on classification tasks. MM randomly combines queries and positives to increase semantic similarity between the generated virtual queries and their positives so as to improves label accuracy. Experimental results on CIFAR10, ImageNet, VOC and COCO show the effectiveness of our method. PyTorch code and model will be released online., Comment: under review. arXiv admin note: substantial text overlap with arXiv:1903.11680 by other authors

Multi-view clustering has wide applications in many image processing scenarios. In these scenarios, original image data often contain missing instances and noises, which is ignored by most multi-view clustering methods. However, missing instances may make these methods difficult to use directly and noises will lead to unreliable clustering results. In this paper, we propose a novel Auto-weighted Noisy and Incomplete Multi-view Clustering framework (ANIMC) via a soft auto-weighted strategy and a doubly soft regular regression model. Firstly, by designing adaptive semi-regularized nonnegative matrix factorization (adaptive semi-RNMF), the soft auto-weighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Secondly, by proposing{\theta}-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different{\theta}. Compared with existing methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our framework in different scenarios, thereby improving its generalization ability; 2) it automatically learns a proper weight for each view, thereby reducing the influence of noises; 3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results demonstrate its superior advantages over other state-of-the-art methods., Comment: Publisheded in IEEE Transactions on Artificial Intelligence

Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly reveals the impact of skip connections to fast network optimization and its competitive advantage over other types of operations in DARTS. Then we propose a theory-inspired path-regularized DARTS that consists of two key modules: (i) a differential group-structured sparse binary gate introduced for each operation to avoid unfair competition among operations, and (ii) a path-depth-wise regularization used to incite search exploration for deep architectures that often converge slower than shallow ones as shown in our theory and are not well explored during the search. Experimental results on image classification tasks validate its advantages., NeurIPS 2020 (oral)

Federated learning (FL) enables collaboratively training deep learning models on decentralized data. However, there are three types of heterogeneities in FL setting bringing about distinctive challenges to the canonical federated learning algorithm (FedAvg). First, due to the Non-IIDness of data, the global shared model may perform worse than local models that solely trained on their private data; Second, the objective of center server and clients may be different, where center server seeks for a generalized model whereas client pursue a personalized model, and clients may run different tasks; Third, clients may need to design their customized model for various scenes and tasks; In this work, we present a novel federated learning paradigm, named Federated Mutual Leaning (FML), dealing with the three heterogeneities. FML allows clients training a generalized model collaboratively and a personalized model independently, and designing their private customized models. Thus, the Non-IIDness of data is no longer a bug but a feature that clients can be personally served better. The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.

Recent studies have revealed the vulnerability of graph convolutional networks (GCNs) to edge-perturbing attacks, such as maliciously inserting or deleting graph edges. However, a theoretical proof of such vulnerability remains a big challenge, and effective defense schemes are still open issues. In this paper, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks. Following this, an anonymous graph convolutional network, named AN-GCN, is proposed to counter against edge-perturbing attacks. Specifically, we present a node localization theorem to demonstrate how the GCN locates nodes during its training phase. In addition, we design a staggered Gaussian noise based node position generator, and devise a spectral graph convolution based discriminator in detecting the generated node positions. Further, we give the optimization of the above generator and discriminator. AN-GCN can classify nodes without taking their position as input. It is demonstrated that the AN-GCN is secure against edge-perturbing attacks in node classification tasks, as AN-GCN classifies nodes without the edge information and thus makes it impossible for attackers to perturb edges anymore. Extensive evaluations demonstrated the effectiveness of the general edge-perturbing attack model in manipulating the classification results of the target nodes. More importantly, the proposed AN-GCN can achieve 82.7% in node classification accuracy without the edge-reading permission, which outperforms the state-of-the-art GCN., 15 pages, 11 figures

Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly since it is unstable and not bounded. To address this issue confronted with existing works, we adopt Categorical Deep Q-Network. We also describe how to design an efficient communication protocol to exploit heterogeneous knowledge among multiple distributed agents. Our proposed framework, namely Learning and Teaching Categorical Reinforcement (LTCR), shows promising performance on stabilizing and accelerating learning progress with improved team-wide reward in four typical experimental environments., 7 pages, 7 figures

Although the challenge of the device connection is much relieved in 5G networks, the training latency is still an obstacle preventing Federated Learning (FL) from being largely adopted. One of the most fundamental problems that lead to large latency is the bad candidate-selection for FL. In the dynamic environment, the mobile devices selected by the existing reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL, because the FL parameter server only knows the currently-observed resources of all candidates. To this end, we study the proactive candidate-selection for FL in this paper. We first let each candidate device predict the qualities of both its training and reporting phases locally using LSTM. Then, the proposed candidateselection algorithm is implemented by the Deep Reinforcement Learning (DRL) framework. Finally, the real-world trace-driven experiments prove that the proposed approach outperforms the existing reactive algorithms, We found significant technique errors in our previous version. The proposed DRL-based algorithm cannot solve the large-scale scheduling for federated learning. For the health of relevant research communities, we decide to withdraw our submission

Link prediction in dynamic graphs (LPDG) is an important research problem that has diverse applications such as online recommendations, studies on disease contagion, organizational studies, etc. Various LPDG methods based on graph embedding and graph neural networks have been recently proposed and achieved state-of-the-art performance. In this paper, we study the vulnerability of LPDG methods and propose the first practical black-box evasion attack. Specifically, given a trained LPDG model, our attack aims to perturb the graph structure, without knowing to model parameters, model architecture, etc., such that the LPDG model makes as many wrong predicted links as possible. We design our attack based on a stochastic policy-based RL algorithm. Moreover, we evaluate our attack on three real-world graph datasets from different application domains. Experimental results show that our attack is both effective and efficient.

It is not clear yet why ADAM-alike adaptive gradient algorithms suffer from worse generalization performance than SGD despite their faster training speed. This work aims to provide understandings on this generalization gap by analyzing their local convergence behaviors. Specifically, we observe the heavy tails of gradient noise in these algorithms. This motivates us to analyze these algorithms through their Levy-driven stochastic differential equations (SDEs) because of the similar convergence behaviors of an algorithm and its SDE. Then we establish the escaping time of these SDEs from a local basin. The result shows that (1) the escaping time of both SGD and ADAM~depends on the Radon measure of the basin positively and the heaviness of gradient noise negatively; (2) for the same basin, SGD enjoys smaller escaping time than ADAM, mainly because (a) the geometry adaptation in ADAM~via adaptively scaling each gradient coordinate well diminishes the anisotropic structure in gradient noise and results in larger Radon measure of a basin; (b) the exponential gradient average in ADAM~smooths its gradient and leads to lighter gradient noise tails than SGD. So SGD is more locally unstable than ADAM~at sharp minima defined as the minima whose local basins have small Radon measure, and can better escape from them to flatter ones with larger Radon measure. As flat minima here which often refer to the minima at flat or asymmetric basins/valleys often generalize better than sharp ones , our result explains the better generalization performance of SGD over ADAM. Finally, experimental results confirm our heavy-tailed gradient noise assumption and theoretical affirmation., Comment: NeurIPS 2020

Meta-learning aims to perform fast adaptation on a new task through learning a "prior" from multiple existing tasks. A common practice in meta-learning is to perform a train-validation split (\emph{train-val method}) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split. Despite its prevalence, the importance of the train-validation split is not well understood either in theory or in practice, particularly in comparison to the more direct \emph{train-train method}, which uses all the per-task data for both training and evaluation. We provide a detailed theoretical study on whether and when the train-validation split is helpful in the linear centroid meta-learning problem. In the agnostic case, we show that the expected loss of the train-val method is minimized at the optimal prior for meta testing, and this is not the case for the train-train method in general without structural assumptions on the data. In contrast, in the realizable case where the data are generated from linear models, we show that both the train-val and train-train losses are minimized at the optimal prior in expectation. Further, perhaps surprisingly, our main result shows that the train-train method achieves a \emph{strictly better} excess loss in this realizable case, even when the regularization parameter and split ratio are optimally tuned for both methods. Our results highlight that sample splitting may not always be preferable, especially when the data is realizable by the model. We validate our theories by experimentally showing that the train-train method can indeed outperform the train-val method, on both simulations and real meta-learning tasks.

This paper presents Prototypical Contrastive Learning (PCL), an unsupervised representation learning method that addresses the fundamental limitations of instance-wise contrastive learning. PCL not only learns low-level features for the task of instance discrimination, but more importantly, it implicitly encodes semantic structures of the data into the learned embedding space. Specifically, we introduce prototypes as latent variables to help find the maximum-likelihood estimation of the network parameters in an Expectation-Maximization framework. We iteratively perform E-step as finding the distribution of prototypes via clustering and M-step as optimizing the network via contrastive learning. We propose ProtoNCE loss, a generalized version of the InfoNCE loss for contrastive learning, which encourages representations to be closer to their assigned prototypes. PCL outperforms state-of-the-art instance-wise contrastive learning methods on multiple benchmarks with substantial improvement in low-resource transfer learning. Code and pretrained models are available at https://github.com/salesforce/PCL.

Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new variational GAN training framework which enjoys superior training stability. Our approach is inspired by a connection of GANs and reinforcement learning under a variational perspective. The connection leads to (1) probability ratio clipping that regularizes generator training to prevent excessively large updates, and (2) a sample re-weighting mechanism that improves discriminator training by downplaying bad-quality fake samples. Moreover, our variational GAN framework can provably overcome the training issue in many GANs that an optimal discriminator cannot provide any informative gradient to training generator. By plugging the training approach in diverse state-of-the-art GAN architectures, we obtain significantly improved performance over a range of tasks, including text generation, text style transfer, and image generation., Comment: NeurIPS 2020 camera ready version (citations updated)

Recently, there has been increasing interest in the challenge of how to discriminatively vectorize graphs. To address this, we propose a method called Iterative Graph Self-Distillation (IGSD) which learns graph-level representation in an unsupervised manner through instance discrimination using a self-supervised contrastive learning approach. IGSD involves a teacher-student distillation process that uses graph diffusion augmentations and constructs the teacher model using an exponential moving average of the student model. The intuition behind IGSD is to predict the teacher network representation of the graph pairs under different augmented views. As a natural extension, we also apply IGSD to semi-supervised scenarios by jointly regularizing the network with both supervised and self-supervised contrastive loss. Finally, we show that finetuning the IGSD-trained models with self-training can further improve the graph representation power. Empirically, we achieve significant and consistent performance gain on various graph datasets in both unsupervised and semi-supervised settings, which well validates the superiority of IGSD., Comment: The Workshop on Self-Supervised Learning for the Web

Graph neural networks (GNNs) have achieved state-of-the-art performance in many graph-related tasks, e.g., node classification. However, recent works show that GNNs are vulnerable to evasion attacks, i.e., an attacker can slightly perturb the graph structure to fool GNN models. Existing evasion attacks to GNNs have several key drawbacks: 1) they are limited to attack two-layer GNNs; 2) they are not efficient; or/and 3) they need to know GNN model parameters. We address the above drawbacks in this paper and propose an influence-based evasion attack against GNNs. Specifically, we first introduce two influence functions, i.e., feature-label influence and label influence, that are defined on GNNs and label propagation (LP), respectively. Then, we build a strong connection between GNNs and LP in terms of influence. Next, we reformulate the evasion attack against GNNs to be related to calculating label influence on LP, which is applicable to multi-layer GNNs and does not need to know the GNN model. We also propose an efficient algorithm to calculate label influence. Finally, we evaluate our influence-based attack on three benchmark graph datasets. Our experimental results show that, compared to state-of-the-art attack, our attack can achieve comparable attack performance, but has a 5-50x speedup when attacking two-layer GNNs. Moreover, our attack is effective to attack multi-layer GNNs.

Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models. As data are distributed from cloud-centric to edge nodes, a big challenge for distributed machine learning systems is how to handle native and natural non-independent and identically distributed (non-IID) data for training. Previous asynchronous training methods do not have a satisfying performance on non-IID data because it would result in that the training process fluctuates greatly which leads to an abnormal convergence. We propose a gradient scheduling algorithm with partly averaged gradients and global momentum (GSGM) for non-IID data distributed asynchronous training. Our key idea is to apply global momentum and local average to the biased gradient after scheduling, in order to make the training process steady. Experimental results show that for non-IID data training under the same experimental conditions, GSGM on popular optimization algorithms can achieve a 20% increase in training stability with a slight improvement in accuracy on Fashion-Mnist and CIFAR-10 datasets. Meanwhile, when expanding distributed scale on CIFAR-100 dataset that results in sparse data distribution, GSGM can perform a 37% improvement on training stability. Moreover, only GSGM can converge well when the number of computing nodes grows to 30, compared to the state-of-the-art distributed asynchronous algorithms. At the same time, GSGM is robust to different degrees of non-IID data., This paper has many grammatical errors. For example, in Section II.A "This means the loss function $F_k(w)$ on each worker participates in the overall optimization goal, and it determine..." should be "This means the loss function $F_k(w)$ on each worker participates in the overall optimization goal, and it determines..."

This work studies the Tensor Robust Principal Component Analysis (TRPCA) problem, which aims to exactly recover the low-rank and sparse components from their sum. Our model is motivated by the recently proposed linear transforms based tensor-tensor product and tensor SVD. We define a new transforms depended tensor rank and the corresponding tensor nuclear norm. Then we solve the TRPCA problem by convex optimization whose objective is a weighted combination of the new tensor nuclear norm and the $\ell_1$-norm. In theory, we show that under certain incoherence conditions, the convex program exactly recovers the underlying low-rank and sparse components. It is of great interest that our new TRPCA model generalizes existing works. In particular, if the studied tensor reduces to a matrix, our TRPCA model reduces to the known matrix RPCA. Our new TRPCA which is allowed to use general linear transforms can be regarded as an extension of our former TRPCA work which uses the discrete Fourier transform. But their proof of the recovery guarantee is different. Numerical experiments verify our results and the application on image recovery demonstrates the superiority of our method., Comment: arXiv admin note: text overlap with arXiv:1804.03728; text overlap with arXiv:1311.6182 by other authors

This work aims to provide understandings on the remarkable success of deep convolutional neural networks (CNNs) by theoretically analyzing their generalization performance and establishing optimization guarantees for gradient descent based training algorithms. Specifically, for a CNN model consisting of $l$ convolutional layers and one fully connected layer, we prove that its generalization error is bounded by $\mathcal{O}(\sqrt{\dt\widetilde{\varrho}/n})$ where $\theta$ denotes freedom degree of the network parameters and $\widetilde{\varrho}=\mathcal{O}(\log(\prod_{i=1}^{l}\rwi{i} (\ki{i}-\si{i}+1)/p)+\log(\rf))$ encapsulates architecture parameters including the kernel size $\ki{i}$, stride $\si{i}$, pooling size $p$ and parameter magnitude $\rwi{i}$. To our best knowledge, this is the first generalization bound that only depends on $\mathcal{O}(\log(\prod_{i=1}^{l+1}\rwi{i}))$, tighter than existing ones that all involve an exponential term like $\mathcal{O}(\prod_{i=1}^{l+1}\rwi{i})$. Besides, we prove that for an arbitrary gradient descent algorithm, the computed approximate stationary point by minimizing empirical risk is also an approximate stationary point to the population risk. This well explains why gradient descent training algorithms usually perform sufficiently well in practice. Furthermore, we prove the one-to-one correspondence and convergence guarantees for the non-degenerate stationary points between the empirical and population risks. It implies that the computed local minimum for the empirical risk is also close to a local minimum for the population risk, thus ensuring the good generalization performance of CNNs., Comment: This paper was accepted by ICML. It has 38 pages

This paper studies the landscape of empirical risk of deep neural networks by theoretically analyzing its convergence behavior to the population risk as well as its stationary points and properties. For an $l$-layer linear neural network, we prove its empirical risk uniformly converges to its population risk at the rate of $\mathcal{O}(r^{2l}\sqrt{d\log(l)}/\sqrt{n})$ with training sample size of $n$, the total weight dimension of $d$ and the magnitude bound $r$ of weight of each layer. We then derive the stability and generalization bounds for the empirical risk based on this result. Besides, we establish the uniform convergence of gradient of the empirical risk to its population counterpart. We prove the one-to-one correspondence of the non-degenerate stationary points between the empirical and population risks with convergence guarantees, which describes the landscape of deep neural networks. In addition, we analyze these properties for deep nonlinear neural networks with sigmoid activation functions. We prove similar results for convergence behavior of their empirical risks as well as the gradients and analyze properties of their non-degenerate stationary points. To our best knowledge, this work is the first one theoretically characterizing landscapes of deep learning algorithms. Besides, our results provide the sample complexity of training a good deep neural network. We also provide theoretical understanding on how the neural network depth $l$, the layer width, the network size $d$ and parameter magnitude determine the neural network landscapes.

Deep neural networks (DNNs) have recently achieved great success in many visual recognition tasks. However, existing deep neural network models are computationally expensive and memory intensive, hindering their deployment in devices with low memory resources or in applications with strict latency requirements. Therefore, a natural thought is to perform model compression and acceleration in deep networks without significantly decreasing the model performance. During the past five years, tremendous progress has been made in this area. In this paper, we review the recent techniques for compacting and accelerating DNN models. In general, these techniques are divided into four categories: parameter pruning and quantization, low-rank factorization, transferred/compact convolutional filters, and knowledge distillation. Methods of parameter pruning and quantization are described first, after that the other techniques are introduced. For each category, we also provide insightful analysis about the performance, related applications, advantages, and drawbacks. Then we go through some very recent successful methods, for example, dynamic capacity networks and stochastic depths networks. After that, we survey the evaluation matrices, the main datasets used for evaluating the model performance, and recent benchmark efforts. Finally, we conclude this paper, discuss remaining the challenges and possible directions for future work., Comment: Published in IEEE Signal Processing Magazine, updated version including more recent works

The Massive Open Online Course (MOOC) has expanded significantly in recent years. With the widespread of MOOC, the opportunity to study the fascinating courses for free has attracted numerous people of diverse educational backgrounds all over the world. In the big data era, a key research topic for MOOC is how to mine the needed courses in the massive course databases in cloud for each individual student accurately and rapidly as the number of courses is increasing fleetly. In this respect, the key challenge is how to realize personalized course recommendation as well as to reduce the computing and storage costs for the tremendous course data. In this paper, we propose a big data-supported, context-aware online learning-based course recommender system that could handle the dynamic and infinitely massive datasets, which recommends courses by using personalized context information and historical statistics. The context-awareness takes the personal preferences into consideration, making the recommendation suitable for people with different backgrounds. Besides, the algorithm achieves the sublinear regret performance, which means it can gradually recommend the mostly preferred and matched courses to students. In addition, our storage module is expanded to the distributed-connected storage nodes, where the devised algorithm can handle massive course storage problems from heterogeneous sources of course datasets. Comparing to existing algorithms, our proposed algorithms achieve the linear time complexity and space complexity. Experiment results verify the superiority of our algorithms when comparing with existing ones in the MOOC big data setting.

Online learning has been in the spotlight from the machine learning society for a long time. To handle massive data in Big Data era, one single learner could never efficiently finish this heavy task. Hence, in this paper, we propose a novel distributed online learning algorithm to solve the problem. Comparing to typical centralized online learner, the distributed learners optimize their own learning parameters based on local data sources and timely communicate with neighbors. However, communication may lead to a privacy breach. Thus, we use differential privacy to preserve the privacy of learners, and study the influence of guaranteeing differential privacy on the utility of the distributed online learning algorithm. Furthermore, by using the results from Kakade and Tewari (2009), we use the regret bounds of online learning to achieve fast convergence rates for offline learning algorithms in distributed scenarios, which provides tighter utility performance than the existing state-of-the-art results. In simulation, we demonstrate that the differentially private offline learning algorithm has high variance, but we can use mini-batch to improve the performance. Finally, the simulations show that the analytical results of our proposed theorems are right and our private distributed online learning algorithm is a general framework.