Nowadays, foundation models become one of fundamental infrastructures in artificial intelligence, paving ways to the general intelligence. However, the reality presents two urgent challenges: existing foundation models are dominated by the English-language community; users are often given limited resources and thus cannot always use foundation models. To support the development of the Chinese-language community, we introduce an open-source project, called Fengshenbang, which leads by the research center for Cognitive Computing and Natural Language (CCNL). Our project has comprehensive capabilities, including large pre-trained models, user-friendly APIs, benchmarks, datasets, and others. We wrap all these in three sub-projects: the Fengshenbang Model, the Fengshen Framework, and the Fengshen Benchmark. An open-source roadmap, Fengshenbang, aims to re-evaluate the open-source community of Chinese pre-trained large-scale models, prompting the development of the entire Chinese large-scale model community. We also want to build a user-centered open-source ecosystem to allow individuals to access the desired models to match their computing resources. Furthermore, we invite companies, colleges, and research institutions to collaborate with us to build the large-scale open-source model-based ecosystem. We hope that this project will be the foundation of Chinese cognitive intelligence.
Capacity is one of the most important performance metrics for wireless communication networks. It describes the maximum rate at which the information can be transmitted of a wireless communication system. To support the growing demand for wireless traffic, wireless networks are becoming more dense and complicated, leading to a higher difficulty to derive the capacity. Unfortunately, most existing methods for the capacity calculation take a polynomial time complexity. This will become unaffordable for future ultra-dense networks, where both the number of base stations (BSs) and the number of users are extremely large. In this paper, we propose a fast algorithm TOSE to estimate the capacity for ultra-dense wireless networks. Based on the spiked model of random matrix theory (RMT), our algorithm can avoid the exact eigenvalue derivations of large dimensional matrices, which are complicated and inevitable in conventional capacity calculation methods. Instead, fast eigenvalue estimations can be realized based on the spike approximations in our TOSE algorithm. Our simulation results show that TOSE is an accurate and fast capacity approximation algorithm. Its estimation error is below 5%, and it runs in linear time, which is much lower than the polynomial time complexity of existing methods. In addition, TOSE has superior generality, since it is independent of the distributions of BSs and users, and the shape of network areas.
Transformer-based models have achieved top performance on major video recognition benchmarks. Benefiting from the self-attention mechanism, these models show stronger ability of modeling long-range dependencies compared to CNN-based models. However, significant computation overheads, resulted from the quadratic complexity of self-attention on top of a tremendous number of tokens, limit the use of existing video transformers in applications with limited resources like mobile devices. In this paper, we extend Mobile-Former to Video Mobile-Former, which decouples the video architecture into a lightweight 3D-CNNs for local context modeling and a Transformer modules for global interaction modeling in a parallel fashion. To avoid significant computational cost incurred by computing self-attention between the large number of local patches in videos, we propose to use very few global tokens (e.g., 6) for a whole video in Transformers to exchange information with 3D-CNNs with a cross-attention mechanism. Through efficient global spatial-temporal modeling, Video Mobile-Former significantly improves the video recognition performance of alternative lightweight baselines, and outperforms other efficient CNN-based models at the low FLOP regime from 500M to 6G total FLOPs on various video recognition tasks. It is worth noting that Video Mobile-Former is the first Transformer-based video model which constrains the computational budget within 1G FLOPs.
Data augmentation greatly increases the amount of data obtained based on labeled data to save on expenses and labor for data collection and labeling. We present a new approach for data augmentation called nine-dot MLS (ND-MLS). This approach is proposed based on the idea of image defor-mation. Images are deformed based on control points, which are calculated by ND-MLS. The method can generate over 2000 images for one exist-ing dataset in a short time. To verify this data augmentation method, extensive tests were performed covering 3 main tasks of computer vision, namely, classification, detection and segmentation. The results show that 1) in classification, 10 images per category were used for training, and VGGNet can obtain 92% top-1 acc on the MNIST dataset of handwritten digits by ND-MLS. In the Omniglot dataset, the few-shot accuracy usu-ally decreases with the increase in character categories. However, the ND-MLS method has stable performance and obtains 96.5 top-1 acc in Res-Net on 100 different handwritten character classification tasks; 2) in segmentation, under the premise of only ten original images, DeepLab obtains 93.5%, 85%, and 73.3% m_IOU(10) on the bottle, horse, and grass test datasets, respectively, while the cat test dataset obtains 86.7% m_IOU(10) with the SegNet model; 3) with only 10 original images from each category in object detection, YOLO v4 obtains 100% and 97.2% bottle and horse detection, respectively, while the cat dataset obtains 93.6% with YOLO v3. In summary, ND-MLS can perform well on classification, object detec-tion, and semantic segmentation tasks by using only a few data.
Byzantine-robust Federated Learning (FL) aims to counter malicious clients and to train an accurate global model while maintaining an extremely low attack success rate. Most of the existing systems, however, are only robust in honest/semi-honest majority settings. FLTrust (NDSS '21) extends the context to the malicious majority for clients but with a strong restriction that the server should be provided with an auxiliary dataset before training in order to filter malicious inputs. Private FLAME/FLGUARD (USENIX '22) gives a solution to guarantee both robustness and updates confidentiality in the semi-honest majority context. It is so far impossible to balance the trade-off among malicious context, robustness, and updates confidentiality. To tackle this problem, we propose a novel Byzantine-robust and privacy-preserving FL system, called BRIEF, to capture malicious minority and majority for server and client sides. Specifically, based on the DBSCAN algorithm, we design a new method for clustering via pairwise adjusted cosine similarity to boost the accuracy of the clustering results. To thwart attacks of malicious majority, we develop an algorithm called Model Segmentation, where local updates in the same cluster are aggregated together, and the aggregations are sent back to corresponding clients correctly. We also leverage multiple cryptographic tools to conduct clustering tasks without sacrificing training correctness and updates confidentiality. We present detailed security proof and empirical evaluation along with convergence analysis for BRIEF. The experimental results demonstrate that the testing accuracy of BRIEF is practically close to the FL baseline (0.8% gap on average). At the same time, the attack success rate is around 0%-5%. We further optimize our design so that the communication overhead and runtime can be decreased by {67%-89.17% and 66.05%-68.75%}, respectively.
Binary matrix optimization commonly arise in the real world, e.g., multi-microgrid network structure design problem (MGNSDP), which is to minimize the total length of the power supply line under certain constraints. Finding the global optimal solution for these problems faces a great challenge since such problems could be large-scale, sparse and multimodal. Traditional linear programming is time-consuming and cannot solve nonlinear problems. To address this issue, a novel improved feasibility rule based differential evolution algorithm, termed LBMDE, is proposed. To be specific, a general heuristic solution initialization method is first proposed to generate high-quality solutions. Then, a binary-matrix-based DE operator is introduced to produce offspring. To deal with the constraints, we proposed an improved feasibility rule based environmental selection strategy. The performance and searching behaviors of LBMDE are examined by a set of benchmark problems.
Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transformer for efficient deployment in realistic industrial scenarios, namely Next-ViT, which dominates both CNNs and ViTs from the perspective of latency/accuracy trade-off. In this work, the Next Convolution Block (NCB) and Next Transformer Block (NTB) are respectively developed to capture local and global information with deployment-friendly mechanisms. Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks. Extensive experiments show that Next-ViT significantly outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks. On TensorRT, Next-ViT surpasses ResNet by 5.4 mAP (from 40.4 to 45.8) on COCO detection and 8.2% mIoU (from 38.8% to 47.0%) on ADE20K segmentation under similar latency. Meanwhile, it achieves comparable performance with CSWin, while the inference speed is accelerated by 3.6x. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.2% to 48.7%) on ADE20K segmentation under similar latency. Code will be released recently.
Multimodal multi-objective problems (MMOPs) commonly arise in real-world problems where distant solutions in decision space correspond to very similar objective values. To obtain all solutions for MMOPs, many multimodal multi-objective evolutionary algorithms (MMEAs) have been proposed. For now, few studies have encompassed most of the recently proposed representative MMEAs and made a comparative comparison. In this study, we first review the related works during the last two decades. Then, we choose 12 state-of-the-art algorithms that utilize different diversity-maintaining techniques and compared their performance on existing test suites. Experimental results indicate the strengths and weaknesses of different techniques on different types of MMOPs, thus providing guidance on how to select/design MMEAs in specific scenarios.
It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the "multi-modality problem", including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenge to the standard cross entropy (XE) loss in NAT and is under studied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to use different loss functions for different kinds of syntactic multi-modality.
The accumulation of time series data and the absence of labels make time-series Anomaly Detection (AD) a self-supervised deep learning task. Single-assumption-based methods may only touch on a certain aspect of the whole normality, not sufficient to detect various anomalies. Among them, contrastive learning methods adopted for AD always choose negative pairs that are both normal to push away, which is objecting to AD tasks' purpose. Existing multi-assumption-based methods are usually two-staged, firstly applying a pre-training process whose target may differ from AD, so the performance is limited by the pre-trained representations. This paper proposes a deep Contrastive One-Class Anomaly detection method of time series (COCA), which combines the normality assumptions of contrastive learning and one-class classification. The key idea is to treat the representation and reconstructed representation as the positive pair of negative-samples-free contrastive learning, and we name it sequence contrast. Then we apply a contrastive one-class loss function composed of invariance and variance terms, the former optimizing loss of the two assumptions simultaneously, and the latter preventing hypersphere collapse. Extensive experiments conducted on four real-world time-series datasets show the superior performance of the proposed method achieves state-of-the-art. The code is publicly available at https://github.com/ruiking04/COCA.