Kenli Li

Liang Li, Siwei Wang, Xinwang Liu et al.

Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels. Constructing precise and local kernel matrices is proved to be of vital significance in applications since the unreliable distant-distance similarity estimation would degrade clustering per-formance. Although existing localized MKC algorithms exhibit improved performance compared to globally-designed competi-tors, most of them widely adopt KNN mechanism to localize kernel matrix by accounting for τ -nearest neighbors. However, such a coarse manner follows an unreasonable strategy that the ranking importance of different neighbors is equal, which is impractical in applications. To alleviate such problems, this paper proposes a novel local sample-weighted multiple kernel clustering (LSWMKC) model. We first construct a consensus discriminative affinity graph in kernel space, revealing the latent local structures. Further, an optimal neighborhood kernel for the learned affinity graph is output with naturally sparse property and clear block diagonal structure. Moreover, LSWMKC im-plicitly optimizes adaptive weights on different neighbors with corresponding samples. Experimental results demonstrate that our LSWMKC possesses better local manifold representation and outperforms existing kernel or graph-based clustering algo-rithms. The source code of LSWMKC can be publicly accessed from https://github.com/liliangnudt/LSWMKC.

Zihan Jiang, Wanling Gao, Lei Wang et al.

In recent years, with the trend of applying deep learning (DL) in high performance scientific computing, the unique characteristics of emerging DL workloads in HPC raise great challenges in designing, implementing HPC AI systems. The community needs a new yard stick for evaluating the future HPC systems. In this paper, we propose HPC AI500 --- a benchmark suite for evaluating HPC systems that running scientific DL workloads. Covering the most representative scientific fields, each workload from HPC AI500 is based on real-world scientific DL applications. Currently, we choose 14 scientific DL benchmarks from perspectives of application scenarios, data sets, and software stack. We propose a set of metrics for comprehensively evaluating the HPC AI systems, considering both accuracy, performance as well as power and cost. We provide a scalable reference implementation of HPC AI500. HPC AI500 is a part of the open-source AIBench project, the specification and source code are publicly available from \url{http://www.benchcouncil.org/AIBench/index.html}.

Zhiwei Zuo, Zhuo Tang, Bin Wang et al.

New categories may be introduced over time, or existing categories may need to be reclassified. Class incremental learning (CIL) is employed for the gradual acquisition of knowledge about new categories while preserving information about previously learned ones in such dynamic environments. It might also be necessary to also eliminate the influence of related categories on the model to adapt to reclassification. We thus introduce class-level machine unlearning (MU) within CIL. Typically, MU methods tend to be time-consuming and can potentially harm the model's performance. A continuous stream of unlearning requests could lead to catastrophic forgetting. To address these issues, we propose a non-destructive eCIL-MU framework based on embedding techniques to map data into vectors and then be stored in vector databases. Our approach exploits the overlap between CIL and MU tasks for acceleration. Experiments demonstrate the capability of achieving unlearning effectiveness and orders of magnitude (upto $\sim 278\times$) of acceleration.

Hao Li, Wei Wang, Cong Wang et al.

Single-domain generalized object detection aims to enhance a model's generalizability to multiple unseen target domains using only data from a single source domain during training. This is a practical yet challenging task as it requires the model to address domain shift without incorporating target domain data into training. In this paper, we propose a novel phrase grounding-based style transfer (PGST) approach for the task. Specifically, we first define textual prompts to describe potential objects for each unseen target domain. Then, we leverage the grounded language-image pre-training (GLIP) model to learn the style of these target domains and achieve style transfer from the source to the target domain. The style-transferred source visual features are semantically rich and could be close to imaginary counterparts in the target domain. Finally, we employ these style-transferred visual features to fine-tune GLIP. By introducing imaginary counterparts, the detector could be effectively generalized to unseen target domains using only a single source domain for training. Extensive experimental results on five diverse weather driving benchmarks demonstrate our proposed approach achieves state-of-the-art performance, even surpassing some domain adaptive methods that incorporate target domain images into the training process.The source codes and pre-trained models will be made available.

Zhiwei Zuo, Zhuo Tang, Kenli Li et al.

Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based unlearning is a general approach, but it typically involves globally modifying the parameters. We propose fine-grained Top-K and Random-k parameters perturbed inexact machine unlearning strategies that address the privacy needs while keeping the computational costs tractable. In order to demonstrate the efficacy of our strategies we also tackle the challenge of evaluating the effectiveness of machine unlearning by considering the model's generalization performance across both unlearning and remaining data. To better assess the unlearning effect and model generalization, we propose novel metrics, namely, the forgetting rate and memory retention rate. However, for inexact machine unlearning, current metrics are inadequate in quantifying the degree of forgetting that occurs after unlearning strategies are applied. To address this, we introduce SPD-GAN, which subtly perturbs the distribution of data targeted for unlearning. Then, we evaluate the degree of unlearning by measuring the performance difference of the models on the perturbed unlearning data before and after the unlearning process. By implementing these innovative techniques and metrics, we achieve computationally efficacious privacy protection in machine learning applications without significant sacrifice of model performance. Furthermore, this approach provides a novel method for evaluating the degree of unlearning.

Meng Wang, Fan Wu, Ruihui Li et al.

3D Semantic Scene Completion (SSC) provides comprehensive scene geometry and semantics for autonomous driving perception, which is crucial for enabling accurate and reliable decision-making. However, existing SSC methods are limited to capturing sparse information from the current frame or naively stacking multi-frame temporal features, thereby failing to acquire effective scene context. These approaches ignore critical motion dynamics and struggle to achieve temporal consistency. To address the above challenges, we propose a novel temporal SSC method FlowScene: Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance. By leveraging optical flow, FlowScene can integrate motion, different viewpoints, occlusions, and other contextual cues, thereby significantly improving the accuracy of 3D scene completion. Specifically, our framework introduces two key components: (1) a Flow-Guided Temporal Aggregation module that aligns and aggregates temporal features using optical flow, capturing motion-aware context and deformable structures; and (2) an Occlusion-Guided Voxel Refinement module that injects occlusion masks and temporally aggregated features into 3D voxel space, adaptively refining voxel representations for explicit geometric modeling. Experimental results demonstrate that FlowScene achieves state-of-the-art performance on the SemanticKITTI and SSCBench-KITTI-360 benchmarks.

Hao Li, Xiangyuan Yang, Mengzhu Wang et al.

Object detection is a critical task in computer vision, with applications in various domains such as autonomous driving and urban scene monitoring. However, deep learning-based approaches often demand large volumes of annotated data, which are costly and difficult to acquire, particularly in complex and unpredictable real-world environments. This dependency significantly hampers the generalization capability of existing object detection techniques. To address this issue, we introduce a novel single-domain object detection generalization method, named GoDiff, which leverages a pre-trained model to enhance generalization in unseen domains. Central to our approach is the Pseudo Target Data Generation (PTDG) module, which employs a latent diffusion model to generate pseudo-target domain data that preserves source domain characteristics while introducing stylistic variations. By integrating this pseudo data with source domain data, we diversify the training dataset. Furthermore, we introduce a cross-style instance normalization technique to blend style features from different domains generated by the PTDG module, thereby increasing the detector's robustness. Experimental results demonstrate that our method not only enhances the generalization ability of existing detectors but also functions as a plug-and-play enhancement for other single-domain generalization methods, achieving state-of-the-art performance in autonomous driving scenarios.

Zihao Zeng, Chubo Liu, Xin He et al.

Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation, with improvements scaling proportionally with model size. However, the limitations of GPU memory have restricted LLM training accessibility for many researchers. Existing heterogeneous training methods significantly expand the scale of trainable models but introduce substantial communication overheads and CPU workloads. In this work, we propose AutoHete, an automatic and efficient heterogeneous training system compatible with both single-GPU and multi-GPU environments. AutoHete dynamically adjusts activation checkpointing, parameter offloading, and optimizer offloading based on the specific hardware configuration and LLM training needs. Additionally, we design a priority-based scheduling mechanism that maximizes the overlap between operations across training iterations, enhancing throughput. Compared to state-of-the-art heterogeneous training systems, AutoHete delivers a 1.32x~1.91x throughput improvement across various model sizes and training configurations.

Ting Xiang, Changjian Chen, Zhuo Tang et al.

The performance of computer vision models in certain real-world applications, such as medical diagnosis, is often limited by the scarcity of available images. Expanding datasets using pre-trained generative models is an effective solution. However, due to the uncontrollable generation process and the ambiguity of natural language, noisy images may be generated. Re-weighting is an effective way to address this issue by assigning low weights to such noisy images. We first theoretically analyze three types of supervision for the generated images. Based on the theoretical analysis, we develop TriReWeight, a triplet-connection-based sample re-weighting method to enhance generative data augmentation. Theoretically, TriReWeight can be integrated with any generative data augmentation methods and never downgrade their performance. Moreover, its generalization approaches the optimal in the order $O(\sqrt{d\ln (n)/n})$. Our experiments validate the correctness of the theoretical analysis and demonstrate that our method outperforms the existing SOTA methods by $7.9\%$ on average over six natural image datasets and by $3.4\%$ on average over three medical datasets. We also experimentally validate that our method can enhance the performance of different generative data augmentation methods.

Changjian Chen, Pengcheng Wang, Fei Lyu et al.

Hybrid rice breeding crossbreeds different rice lines and cultivates the resulting hybrids in fields to select those with desirable agronomic traits, such as higher yields. Recently, genomic selection has emerged as an efficient way for hybrid rice breeding. It predicts the traits of hybrids based on their genes, which helps exclude many undesired hybrids, largely reducing the workload of field cultivation. However, due to the limited accuracy of genomic prediction models, breeders still need to combine their experience with the models to identify regulatory genes that control traits and select hybrids, which remains a time-consuming process. To ease this process, in this paper, we proposed a visual analysis method to facilitate interactive hybrid rice breeding. Regulatory gene identification and hybrid selection naturally ensemble a dual-analysis task. Therefore, we developed a parametric dual projection method with theoretical guarantees to facilitate interactive dual analysis. Based on this dual projection method, we further developed a gene visualization and a hybrid visualization to verify the identified regulatory genes and hybrids. The effectiveness of our method is demonstrated through the quantitative evaluation of the parametric dual projection method, identified regulatory genes and desired hybrids in the case study, and positive feedback from breeders.

Huihui Guo, Huilong Pi, Yunchuan Qin et al.

With the rapid advancement of artificial intelligence, there is an increasing demand for intelligent robots capable of assisting humans in daily tasks and performing complex operations. Such robots not only require task planning capabilities but must also execute tasks with stability and robustness. In this paper, we present a closed-loop task planning and acting system, LLM-PAS, which is assisted by a pre-trained Large Language Model (LLM). While LLM-PAS plans long-horizon tasks in a manner similar to traditional task and motion planners, it also emphasizes the execution phase of the task. By transferring part of the constraint-checking process from the planning phase to the execution phase, LLM-PAS enables exploration of the constraint space and delivers more accurate feedback on environmental anomalies during execution. The reasoning capabilities of the LLM allow it to handle anomalies that cannot be addressed by the robust executor. To further enhance the system's ability to assist the planner during replanning, we propose the First Look Prompting (FLP) method, which induces LLM to generate effective PDDL goals. Through comparative prompting experiments and systematic experiments, we demonstrate the effectiveness and robustness of LLM-PAS in handling anomalous conditions during task execution.

Meng Wang, Fan Wu, Yunchuan Qin et al.

The vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, the presence of dynamic objects in the scene seriously affects the accuracy of the model inferring 3D structures from 2D images. Existing methods simply stack multiple frames of image input to increase dense scene semantic information, but ignore the fact that dynamic objects and non-texture areas violate multi-view consistency and matching reliability. To address these issues, we propose a novel method, CDScene: Vision-based Robust Semantic Scene Completion via Capturing Dynamic Representations. First, we leverage a multimodal large-scale model to extract 2D explicit semantics and align them into 3D space. Second, we exploit the characteristics of monocular and stereo depth to decouple scene information into dynamic and static features. The dynamic features contain structural relationships around dynamic objects, and the static features contain dense contextual spatial information. Finally, we design a dynamic-static adaptive fusion module to effectively extract and aggregate complementary features, achieving robust and accurate semantic scene completion in autonomous driving scenarios. Extensive experimental results on the SemanticKITTI, SSCBench-KITTI360, and SemanticKITTI-C datasets demonstrate the superiority and robustness of CDScene over existing state-of-the-art methods.

Yufeng Zhang, Wanwei Liu, Zhenbang Chen et al.

Kullback-Leibler (KL) divergence is one of the most important divergence measures between probability distributions. In this paper, we prove several properties of KL divergence between multivariate Gaussian distributions. First, for any two $n$-dimensional Gaussian distributions $\mathcal{N}_1$ and $\mathcal{N}_2$, we give the supremum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ when $KL(\mathcal{N}_2||\mathcal{N}_1)\leq \varepsilon\ (\varepsilon>0)$. For small $\varepsilon$, we show that the supremum is $\varepsilon + 2\varepsilon^{1.5} + O(\varepsilon^2)$. This quantifies the approximate symmetry of small KL divergence between Gaussians. We also find the infimum of $KL(\mathcal{N}_1||\mathcal{N}_2)$ when $KL(\mathcal{N}_2||\mathcal{N}_1)\geq M\ (M>0)$. We give the conditions when the supremum and infimum can be attained. Second, for any three $n$-dimensional Gaussians $\mathcal{N}_1$, $\mathcal{N}_2$, and $\mathcal{N}_3$, we find an upper bound of $KL(\mathcal{N}_1||\mathcal{N}_3)$ if $KL(\mathcal{N}_1||\mathcal{N}_2)\leq \varepsilon_1$ and $KL(\mathcal{N}_2||\mathcal{N}_3)\leq \varepsilon_2$ for $\varepsilon_1,\varepsilon_2\ge 0$. For small $\varepsilon_1$ and $\varepsilon_2$, we show the upper bound is $3\varepsilon_1+3\varepsilon_2+2\sqrt{\varepsilon_1\varepsilon_2}+o(\varepsilon_1)+o(\varepsilon_2)$. This reveals that KL divergence between Gaussians follows a relaxed triangle inequality. Importantly, all the bounds in the theorems presented in this paper are independent of the dimension $n$. Finally, We discuss the applications of our theorems in explaining counterintuitive phenomenon of flow-based model, deriving deep anomaly detection algorithm, and extending one-step robustness guarantee to multiple steps in safe reinforcement learning.

Jianguo Chen, Kenli Li, Keqin Li et al.

As a new generation of Public Bicycle-sharing Systems (PBS), the dockless PBS (DL-PBS) is an important application of cyber-physical systems and intelligent transportation. How to use AI to provide efficient bicycle dispatching solutions based on dynamic bicycle rental demand is an essential issue for DL-PBS. In this paper, we propose a dynamic bicycle dispatching algorithm based on multi-objective reinforcement learning (MORL-BD) to provide the optimal bicycle dispatching solution for DL-PBS. We model the DL-PBS system from the perspective of CPS and use deep learning to predict the layout of bicycle parking spots and the dynamic demand of bicycle dispatching. We define the multi-route bicycle dispatching problem as a multi-objective optimization problem by considering the optimization objectives of dispatching costs, dispatch truck's initial load, workload balance among the trucks, and the dynamic balance of bicycle supply and demand. On this basis, the collaborative multi-route bicycle dispatching problem among multiple dispatch trucks is modeled as a multi-agent MORL model. All dispatch paths between parking spots are defined as state spaces, and the reciprocal of dispatching costs is defined as a reward. Each dispatch truck is equipped with an agent to learn the optimal dispatch path in the dynamic DL-PBS network. We create an elite list to store the Pareto optimal solutions of bicycle dispatch paths found in each action, and finally, get the Pareto frontier. Experimental results on the actual DL-PBS systems show that compared with existing methods, MORL-BD can find a higher quality Pareto frontier with less execution time.

Jianguo Chen, Kenli Li, Keqin Li et al.

Benefiting from convenient cycling and flexible parking locations, the Dockless Public Bicycle-sharing (DL-PBS) network becomes increasingly popular in many countries. However, redundant and low-utility stations waste public urban space and maintenance costs of DL-PBS vendors. In this paper, we propose a Bicycle Station Dynamic Planning (BSDP) system to dynamically provide the optimal bicycle station layout for the DL-PBS network. The BSDP system contains four modules: bicycle drop-off location clustering, bicycle-station graph modeling, bicycle-station location prediction, and bicycle-station layout recommendation. In the bicycle drop-off location clustering module, candidate bicycle stations are clustered from each spatio-temporal subset of the large-scale cycling trajectory records. In the bicycle-station graph modeling module, a weighted digraph model is built based on the clustering results and inferior stations with low station revenue and utility are filtered. Then, graph models across time periods are combined to create a graph sequence model. In the bicycle-station location prediction module, the GGNN model is used to train the graph sequence data and dynamically predict bicycle stations in the next period. In the bicycle-station layout recommendation module, the predicted bicycle stations are fine-tuned according to the government urban management plan, which ensures that the recommended station layout is conducive to city management, vendor revenue, and user convenience. Experiments on actual DL-PBS networks verify the effectiveness, accuracy and feasibility of the proposed BSDP system.

Jianguo Chen, Kenli Li, Zhaolei Zhang et al.

The COVID-19 pandemic caused by the SARS-CoV-2 virus has spread rapidly worldwide, leading to a global outbreak. Most governments, enterprises, and scientific research institutions are participating in the COVID-19 struggle to curb the spread of the pandemic. As a powerful tool against COVID-19, artificial intelligence (AI) technologies are widely used in combating this pandemic. In this survey, we investigate the main scope and contributions of AI in combating COVID-19 from the aspects of disease detection and diagnosis, virology and pathogenesis, drug and vaccine development, and epidemic and transmission prediction. In addition, we summarize the available data and resources that can be used for AI-based COVID-19 research. Finally, the main challenges and potential directions of AI in fighting against COVID-19 are discussed. Currently, AI mainly focuses on medical image inspection, genomics, drug development, and transmission prediction, and thus AI still has great potential in this field. This survey presents medical and AI researchers with a comprehensive view of the existing and potential applications of AI technology in combating COVID-19 with the goal of inspiring researchers to continue to maximize the advantages of AI and big data to fight COVID-19.

Yufeng Zhang, Jialu Pan, Wanwei Liu et al.

Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data than in-distribution (ID) data. However, we cannot sample OOD data from the model. This counterintuitive phenomenon has not been satisfactorily explained and brings obstacles to OOD detection with flow-based models. In this paper, we prove theorems to investigate the Kullback-Leibler divergence in flow-based model and give two explanations for the above phenomenon. Based on our theoretical analysis, we propose a new method \PADmethod\ to leverage KL divergence and local pixel dependence of representations to perform anomaly detection. Experimental results on prevalent benchmarks demonstrate the effectiveness and robustness of our method. For group anomaly detection, our method achieves 98.1\% AUROC on average with a small batch size of 5. On the contrary, the baseline typicality test-based method only achieves 64.6\% AUROC on average due to its failure on challenging problems. Our method also outperforms the state-of-the-art method by 9.1\% AUROC. For point-wise anomaly detection, our method achieves 90.7\% AUROC on average and outperforms the baseline by 5.2\% AUROC. Besides, our method has the least notable failures and is the most robust one.

Jianguo Chen, Kenli Li, Qingying Deng et al.

In this paper, we propose a Distributed Intelligent Video Surveillance (DIVS) system using Deep Learning (DL) algorithms and deploy it in an edge computing environment. We establish a multi-layer edge computing architecture and a distributed DL training model for the DIVS system. The DIVS system can migrate computing workloads from the network center to network edges to reduce huge network communication overhead and provide low-latency and accurate video analysis solutions. We implement the proposed DIVS system and address the problems of parallel training, model synchronization, and workload balancing. Task-level parallel and model-level parallel training methods are proposed to further accelerate the video analysis process. In addition, we propose a model parameter updating method to achieve model synchronization of the global DL model in a distributed EC environment. Moreover, a dynamic data migration approach is proposed to address the imbalance of workload and computational power of edge nodes. Experimental results showed that the EC architecture can provide elastic and scalable computing power, and the proposed DIVS system can efficiently handle video surveillance and analysis tasks.

Jianguo Chen, Kenli Li, Kashif Bilal et al.

Protein interactions constitute the fundamental building block of almost every life activity. Identifying protein communities from Protein-Protein Interaction (PPI) networks is essential to understand the principles of cellular organization and explore the causes of various diseases. It is critical to integrate multiple data resources to identify reliable protein communities that have biological significance and improve the performance of community detection methods for large-scale PPI networks. In this paper, we propose a Multi-source Learning based Protein Community Detection (MLPCD) algorithm by integrating Gene Expression Data (GED) and a parallel solution of MLPCD using cloud computing technology. To effectively discover the biological functions of proteins that participating in different cellular processes, GED under different conditions is integrated with the original PPI network to reconstruct a Weighted-PPI (WPPI) network. To flexibly identify protein communities of different scales, we define community modularity and functional cohesion measurements and detect protein communities from WPPI using an agglomerative method. In addition, we respectively compare the detected communities with known protein complexes and evaluate the functional enrichment of protein function modules using Gene Ontology annotations. Moreover, we implement a parallel version of the MLPCD algorithm on the Apache Spark platform to enhance the performance of the algorithm for large-scale realistic PPI networks. Extensive experimental results indicate the superiority and notable advantages of the MLPCD algorithm over the relevant algorithms in terms of accuracy and performance.

Jianguo Chen, Kenli Li, Huigui Rong et al.

In the era of big data, practical applications in various domains continually generate large-scale time-series data. Among them, some data show significant or potential periodicity characteristics, such as meteorological and financial data. It is critical to efficiently identify the potential periodic patterns from massive time-series data and provide accurate predictions. In this paper, a Periodicity-based Parallel Time Series Prediction (PPTSP) algorithm for large-scale time-series data is proposed and implemented in the Apache Spark cloud computing environment. To effectively handle the massive historical datasets, a Time Series Data Compression and Abstraction (TSDCA) algorithm is presented, which can reduce the data scale as well as accurately extracting the characteristics. Based on this, we propose a Multi-layer Time Series Periodic Pattern Recognition (MTSPPR) algorithm using the Fourier Spectrum Analysis (FSA) method. In addition, a Periodicity-based Time Series Prediction (PTSP) algorithm is proposed. Data in the subsequent period are predicted based on all previous period models, in which a time attenuation factor is introduced to control the impact of different periods on the prediction results. Moreover, to improve the performance of the proposed algorithms, we propose a parallel solution on the Apache Spark platform, using the Streaming real-time computing module. To efficiently process the large-scale time-series datasets in distributed computing environments, Distributed Streams (DStreams) and Resilient Distributed Datasets (RDDs) are used to store and calculate these datasets. Extensive experimental results show that our PPTSP algorithm has significant advantages compared with other algorithms in terms of prediction accuracy and performance.

Jianguo Chen, Kenli Li, Huigui Rong et al.

It is crucial to provide compatible treatment schemes for a disease according to various symptoms at different stages. However, most classification methods might be ineffective in accurately classifying a disease that holds the characteristics of multiple treatment stages, various symptoms, and multi-pathogenesis. Moreover, there are limited exchanges and cooperative actions in disease diagnoses and treatments between different departments and hospitals. Thus, when new diseases occur with atypical symptoms, inexperienced doctors might have difficulty in identifying them promptly and accurately. Therefore, to maximize the utilization of the advanced medical technology of developed hospitals and the rich medical knowledge of experienced doctors, a Disease Diagnosis and Treatment Recommendation System (DDTRS) is proposed in this paper. First, to effectively identify disease symptoms more accurately, a Density-Peaked Clustering Analysis (DPCA) algorithm is introduced for disease-symptom clustering. In addition, association analyses on Disease-Diagnosis (D-D) rules and Disease-Treatment (D-T) rules are conducted by the Apriori algorithm separately. The appropriate diagnosis and treatment schemes are recommended for patients and inexperienced doctors, even if they are in a limited therapeutic environment. Moreover, to reach the goals of high performance and low latency response, we implement a parallel solution for DDTRS using the Apache Spark cloud platform. Extensive experimental results demonstrate that the proposed DDTRS realizes disease-symptom clustering effectively and derives disease treatment recommendations intelligently and accurately.

Jianguo Chen, Kenli Li, Kashif Bilal et al.

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-layer parallel training for multiple CNN subnetworks on separate data subsets, and (b) an inner-layer parallel training for each subnetwork. In the outer-layer parallelism, we address critical issues of distributed and parallel computing, including data communication, synchronization, and workload balance. A heterogeneous-aware Incremental Data Partitioning and Allocation (IDPA) strategy is proposed, where large-scale training datasets are partitioned and allocated to the computing nodes in batches according to their computing power. To minimize the synchronization waiting during the global weight update process, an Asynchronous Global Weight Update (AGWU) strategy is proposed. In the inner-layer parallelism, we further accelerate the training process for each CNN subnetwork on each computer, where computation steps of convolutional layer and the local weight training are parallelized based on task-parallelism. We introduce task decomposition and scheduling strategies with the objectives of thread-level load balancing and minimum waiting time for critical paths. Extensive experimental results indicate that the proposed BPT-CNN effectively improves the training performance of CNNs while maintaining the accuracy.

Mingxing Duan, Kenli Li, Qi Tian

Face multi-attribute prediction benefits substantially from multi-task learning (MTL), which learns multiple face attributes simultaneously to achieve shared or mutually related representations of different attributes. The most widely used MTL convolutional neural network is heuristically or empirically designed by sharing all of the convolutional layers and splitting at the fully connected layers for task-specific losses. However, it is improper to view all low and mid-level features for different attributes as being the same, especially when these attributes are only loosely related. In this paper, we propose a novel multi-attribute tensor correlation neural network (MTCN) for face attribute prediction. The structure shares the information in low-level features (e.g., the first two convolutional layers) but splits that in high-level features (e.g., from the third convolutional layer to the fully connected layer). At the same time, during high-level feature extraction, each subnetwork (e.g., Age-Net, Gender-Net, ..., and Smile-Net) excavates closely related features from other networks to enhance its features. Then, we project the features of the C9 layers of the fine-tuned subnetworks into a highly correlated space by using a novel tensor correlation analysis algorithm (NTCCA). The final face attribute prediction is made based on the correlation matrix. Experimental results on benchmarks with multiple face attributes (CelebA and LFWA) show that the proposed approach has superior performance compared to state-of-the-art methods.