Yuxin Wang

Zhenheng Tang, Xiaowen Chu, Ryan Yide Ran et al.

Federated Learning (FL) enables collaborations among clients for train machine learning models while protecting their data privacy. Existing FL simulation platforms that are designed from the perspectives of traditional distributed training, suffer from laborious code migration between simulation and production, low efficiency, low GPU utility, low scalability with high hardware requirements and difficulty of simulating stateful clients. In this work, we firstly demystify the challenges and bottlenecks of simulating FL, and design a new FL system named as FedML \texttt{Parrot}. It improves the training efficiency, remarkably relaxes the requirements on the hardware, and supports efficient large-scale FL experiments with stateful clients by: (1) sequential training clients on devices; (2) decomposing original aggregation into local and global aggregation on devices and server respectively; (3) scheduling tasks to mitigate straggler problems and enhance computing utility; (4) distributed client state manager to support various FL algorithms. Besides, built upon our generic APIs and communication interfaces, users can seamlessly transform the simulation into the real-world deployment without modifying codes. We evaluate \texttt{Parrot} through extensive experiments for training diverse models on various FL datasets to demonstrate that \texttt{Parrot} can achieve simulating over 1000 clients (stateful or stateless) with flexible GPU devices setting ($4 \sim 32$) and high GPU utility, 1.2 $\sim$ 4 times faster than FedScale, and 10 $\sim$ 100 times memory saving than FedML. And we verify that \texttt{Parrot} works well with homogeneous and heterogeneous devices in three different clusters. Two FL algorithms with stateful clients and four algorithms with stateless clients are simulated to verify the wide adaptability of \texttt{Parrot} to different algorithms.

Zixiao Wang, Hongtao Xie, YuXin Wang et al.

Existing scene text removal (STR) task suffers from insufficient training data due to the expensive pixel-level labeling. In this paper, we aim to address this issue by introducing a Text-aware Masked Image Modeling algorithm (TMIM), which can pretrain STR models with low-cost text detection labels (e.g., text bounding box). Different from previous pretraining methods that use indirect auxiliary tasks only to enhance the implicit feature extraction ability, our TMIM first enables the STR task to be directly trained in a weakly supervised manner, which explores the STR knowledge explicitly and efficiently. In TMIM, first, a Background Modeling stream is built to learn background generation rules by recovering the masked non-text region. Meanwhile, it provides pseudo STR labels on the masked text region. Second, a Text Erasing stream is proposed to learn from the pseudo labels and equip the model with end-to-end STR ability. Benefiting from the two collaborative streams, our STR model can achieve impressive performance only with the public text detection datasets, which greatly alleviates the limitation of the high-cost STR labels. Experiments demonstrate that our method outperforms other pretrain methods and achieves state-of-the-art performance (37.35 PSNR on SCUT-EnsText). Code will be available at https://github.com/wzx99/TMIM.

Yuxin Wang, Hongtao Xie, Shancheng Fang et al.

In this paper, we abandon the dominant complex language model and rethink the linguistic learning process in the scene text recognition. Different from previous methods considering the visual and linguistic information in two separate structures, we propose a Visual Language Modeling Network (VisionLAN), which views the visual and linguistic information as a union by directly enduing the vision model with language capability. Specially, we introduce the text recognition of character-wise occluded feature maps in the training stage. Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e.g. occlusion, noise, etc.). As the linguistic information is acquired along with visual features without the need of extra language model, VisionLAN significantly improves the speed by 39% and adaptively considers the linguistic information to enhance the visual features for accurate recognition. Furthermore, an Occlusion Scene Text (OST) dataset is proposed to evaluate the performance on the case of missing character-wise visual cues. The state of-the-art results on several benchmarks prove our effectiveness. Code and dataset are available at https://github.com/wangyuxin87/VisionLAN.

Yuxin Wang, Hongtao Xie, Shancheng Fang et al.

Scene text removal (STR) contains two processes: text localization and background reconstruction. Through integrating both processes into a single network, previous methods provide an implicit erasure guidance by modifying all pixels in the entire image. However, there exists two problems: 1) the implicit erasure guidance causes the excessive erasure to non-text areas; 2) the one-stage erasure lacks the exhaustive removal of text region. In this paper, we propose a ProgrEssively Region-based scene Text eraser (PERT), introducing an explicit erasure guidance and performing balanced multi-stage erasure for accurate and exhaustive text removal. Firstly, we introduce a new region-based modification strategy (RegionMS) to explicitly guide the erasure process. Different from previous implicitly guided methods, RegionMS performs targeted and regional erasure on only text region, and adaptively perceives stroke-level information to improve the integrity of non-text areas with only bounding box level annotations. Secondly, PERT performs balanced multi-stage erasure with several progressive erasing stages. Each erasing stage takes an equal step toward the text-erased image to ensure the exhaustive erasure of text regions. Compared with previous methods, PERT outperforms them by a large margin without the need of adversarial loss, obtaining SOTA results with high speed (71 FPS) and at least 25% lower parameter complexity. Code is available at https://github.com/wangyuxin87/PERT.

Yuxin Wang, Zeyu Ding, Yingtai Xiao et al.

Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with a noise-free (non-private) algorithm. The designer then decides where to add noise, and how much of it to add. This can be a non-trivial process -- if not done carefully, the algorithm might either violate differential privacy or have low utility. In this paper, we present DPGen, a program synthesizer that takes in non-private code (without any noise) and automatically synthesizes its differentially private version (with carefully calibrated noise). Under the hood, DPGen uses novel algorithms to automatically generate a sketch program with candidate locations for noise, and then optimize privacy proof and noise scales simultaneously on the sketch program. Moreover, DPGen can synthesize sophisticated mechanisms that adaptively process queries until a specified privacy budget is exhausted. When evaluated on standard benchmarks, DPGen is able to generate differentially private mechanisms that optimize simple utility functions within 120 seconds. It is also powerful enough to synthesize adaptive privacy mechanisms.

Zeyu Ding, Daniel Kifer, Sayed M. Saghaian N. E. et al.

The permute-and-flip mechanism is a recently proposed differentially private selection algorithm that was shown to outperform the exponential mechanism. In this paper, we show that permute-and-flip is equivalent to the well-known report noisy max algorithm with exponential noise.

Zeyu Ding, Yuxin Wang, Yingtai Xiao et al.

Private selection algorithms, such as the Exponential Mechanism, Noisy Max and Sparse Vector, are used to select items (such as queries with large answers) from a set of candidates, while controlling privacy leakage in the underlying data. Such algorithms serve as building blocks for more complex differentially private algorithms. In this paper we show that these algorithms can release additional information related to the gaps between the selected items and the other candidates for free (i.e., at no additional privacy cost). This free gap information can improve the accuracy of certain follow-up counting queries by up to 66%. We obtain these results from a careful privacy analysis of these algorithms. Based on this analysis, we further propose novel hybrid algorithms that can dynamically save additional privacy budget.

Hanchuan Xu, Xiao Wang, Yuxin Wang et al.

Various types of services, such as web APIs, IoT services, O2O services, and many others, have flooded on the Internet. Interconnections among these services have resulted in a new phenomenon called "Internet of Services" (IoS). By IoS,people don't need to request multiple services by themselves to fulfill their daily requirements, but it is an IoS platform that is responsible for constructing integrated solutions for them. Since user requirements (URs) are usually coarse-grained and transboundary, IoS platforms have to integrate services from multiple domains to fulfill the requirements. Considering there are too many available services in IoS, a big challenge is how to look for a tradeoff between the construction efficiency and the precision of final solutions. For this challenge, we introduce a framework and a platform for transboundary user requirement oriented solution design in IoS. The main idea is to make use of domain priori knowledge derived from the commonness and similarities among massive historical URs and among historical integrated service solutions(ISSs). Priori knowledge is classified into three types: requirement patterns (RPs), service patterns (SPs), and probabilistic matching matrix (PMM) between RPs and SPs. A UR is modeled in the form of an intention tree (ITree) along with a set of constraints on intention nodes, and then optimal RPs are selected to cover the I-Tree as much as possible. By taking advantage of the PMM, a set of SPs are filtered out and composed together to form the final ISS. Finally, the design of a platform supporting the above process is introduced.

Shuoheng Yang, Yuxin Wang, Xiaowen Chu

In recent years, natural language processing (NLP) has got great development with deep learning techniques. In the sub-field of machine translation, a new approach named Neural Machine Translation (NMT) has emerged and got massive attention from both academia and industry. However, with a significant number of researches proposed in the past several years, there is little work in investigating the development process of this new technology trend. This literature survey traces back the origin and principal development timeline of NMT, investigates the important branches, categorizes different research orientations, and discusses some future research trends in this field.

Zeyu Ding, Yuxin Wang, Danfeng Zhang et al.

Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms can release additional information for free (i.e., at no additional privacy cost). Noisy Max is used to return the approximate maximizer among a set of queries. We show that it can also release for free the noisy gap between the approximate maximizer and runner-up. This free information can improve the accuracy of certain subsequent counting queries by up to 50%. Sparse Vector is used to return a set of queries that are approximately larger than a fixed threshold. We show that it can adaptively control its privacy budget (use less budget for queries that are likely to be much larger than the threshold) in order to increase the amount of queries it can process. These results follow from a careful privacy analysis.

Shaohuai Shi, Qiang Wang, Kaiyong Zhao et al.

Distributed synchronous stochastic gradient descent (S-SGD) has been widely used in training large-scale deep neural networks (DNNs), but it typically requires very high communication bandwidth between computational workers (e.g., GPUs) to exchange gradients iteratively. Recently, Top-$k$ sparsification techniques have been proposed to reduce the volume of data to be exchanged among workers. Top-$k$ sparsification can zero-out a significant portion of gradients without impacting the model convergence. However, the sparse gradients should be transferred with their irregular indices, which makes the sparse gradients aggregation difficult. Current methods that use AllGather to accumulate the sparse gradients have a communication complexity of $O(kP)$, where $P$ is the number of workers, which is inefficient on low bandwidth networks with a large number of workers. We observe that not all top-$k$ gradients from $P$ workers are needed for the model update, and therefore we propose a novel global Top-$k$ (gTop-$k$) sparsification mechanism to address the problem. Specifically, we choose global top-$k$ largest absolute values of gradients from $P$ workers, instead of accumulating all local top-$k$ gradients to update the model in each iteration. The gradient aggregation method based on gTop-$k$ sparsification reduces the communication complexity from $O(kP)$ to $O(k\log P)$. Through extensive experiments on different DNNs, we verify that gTop-$k$ S-SGD has nearly consistent convergence performance with S-SGD, and it has only slight degradations on generalization performance. In terms of scaling efficiency, we evaluate gTop-$k$ on a cluster with 32 GPU machines which are interconnected with 1 Gbps Ethernet. The experimental results show that our method achieves $2.7-12\times$ higher scaling efficiency than S-SGD and $1.1-1.7\times$ improvement than the existing Top-$k$ S-SGD.