Article
Computer Science, Artificial Intelligence
Ngoc-Thao Le, Bay Vo, Unil Yun, Bac Le
Summary: Mining a weighted single large graph has become a popular research topic. This paper introduces a novel algorithm called AWeGraMi, which solves the problem of calculating average value in a domain with the same role for all values. AWeGraMi calculates the weight based on the average value and applies the MaxMin measure as an upper-bound to prune the search space. Experimental results show that AWeGraMi outperforms post-processing GraMi in terms of search space, running time, and memory consumption.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Software Engineering
K. Lakshmi, T. Meyyappan
Summary: This paper discusses the application of complex networks in various scientific disciplines and the challenges of mining important frequent patterns from graph databases. Existing algorithms perform well on medium networks but struggle with large graphs, whereas the proposed algorithm in this paper is efficient and scalable on very large graph databases.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Md Ashraful Islam, Mahfuzur Rahman Rafi, Al-amin Azad, Jesan Ahammed Ovi
Summary: Data mining is the study of extracting useful information from massive amounts of data, with sequential pattern mining being a major branch. Weighted sequential pattern mining is more feasible in today's datasets due to items having different importance in real-life scenarios. This research introduces a new pruning technique and framework to generate a small number of candidate sequences faster without compromising completeness, significantly outperforming other existing approaches.
APPLIED INTELLIGENCE
(2022)
Article
Chemistry, Multidisciplinary
Wenhua Guo, Wenqian Feng, Yiyan Qi, Pinghui Wang, Jing Tao
Summary: This paper proposes a novel motif sampling method, Mosar, to estimate motif frequencies. By sampling frequent and rare motifs with different probabilities and tending to sample motifs with low frequencies, the method greatly reduces the estimation errors of rare motifs.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Xiang Huang, Yixin He, Bin Yan, Wei Zeng
Summary: In this research, a new session-based recommender system is proposed, which utilizes both the local and global information of item sequences and considers the importance of frequent sub-sequences. By constructing local and global session graphs and using a gated layer to control their contributions, our method is able to learn accurate session-level and global-level item embeddings.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Saihua Cai, Li Li, Jinfu Chen, Kaiyi Zhao, Gang Yuan, Ruizhi Sun, Longxia Huang, Rexford Nii Ayitey Sosu
Summary: The study proposes a new outlier detection approach that improves accuracy in handling uncertain data streams and effectively detects potential outliers. Through two phases, namely pattern mining and outlier detection phases, more accurate outlier detection is achieved. Experimental results demonstrate that this method is not only accurate but also consumes less time.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Giulia Preti, Gianmarco De Francisci Morales, Matteo Riondato
Summary: We propose a sampling-based randomized algorithm called MANIACS for computing high-quality approximations of frequent subgraph patterns in large vertex-labeled graphs. MANIACS provides strong probabilistic guarantees by using the empirical VC dimension and probabilistic tail bounds. It leverages the MNI frequency properties to aggressively prune the pattern search space, resulting in faster exploration of subspaces without frequent patterns. Experimental evaluation shows that MANIACS returns high-quality collections of frequent patterns in large graphs up to two orders of magnitude faster than the exact algorithm.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2023)
Article
Geochemistry & Geophysics
Guoming Gao, Baisen Liu, Xiangrong Zhang, Xudong Jin, Yanfeng Gu
Summary: A new method of multitemporal intrinsic image decomposition (MIID) is proposed in this article, which can effectively extract the common spectral reflectance from multitemporal images, leading to more accurate and easier multitemporal classification, change detection, and index extraction. The MIID methods not only achieve better results in spectral reflectance extraction, but also show good performance in multitemporal classification and change detection.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Kaouthar Driss, Wadii Boulila, Aurelie Leborgne, Pierre Gancarski
Summary: Recent research focuses on cases where patterns differ from their occurrences, proposing a novel FMP algorithm that can identify structural differences in patterns and mine patterns within directed graphs.
INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY
(2021)
Article
Computer Science, Information Systems
Ho Sub Lee, Sung In Cho
Summary: The proposed image segmentation method effectively combines color and spatial information through spatial-color histograms, clustering, and texture-aware region merging, with the use of a total variation-based regularizer to improve accuracy and overcome issues of over-segmentation and boundary displacement observed in previous methods. Results show significant improvements compared to previous histogram-based methods and promising segmentation quality with fast operation speed when compared to state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Longxu Sun, Xin Huang, Rong-Hua Li, Byron Choi, Jianliang Xu
Summary: In this paper, we propose an efficient framework called LEKS for finding intimate-core groups in graphs. We also introduce a weighted-core index (WC-index) and two new algorithms based on the WC-index to improve the efficiency of the search. The effectiveness and efficiency of our proposed methods are validated through extensive experiments on real-life networks with ground-truth communities.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Huong Bui, Bay Vo, Tu-Anh Nguyen-Hoang, Unil Yun
Summary: The study introduces an efficient algorithm NFWCI for mining frequent weighted closed itemsets (FWCIs) using the WN-list structure and early pruning strategy, showing superior performance compared to existing algorithms in experimental results.
APPLIED INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Fanchen Bu, Shinhwan Kang, Kijung Shin
Summary: This study explores the relations between edge weights and topology in real-world graphs and proposes an algorithm called PEAR to assign realistic edge weights based on these patterns. The algorithm relies on only two parameters, preserves all the observed patterns, and produces more realistic weights than the baseline methods with more parameters.
DATA MINING AND KNOWLEDGE DISCOVERY
(2023)
Article
Geochemistry & Geophysics
Xiangrong Zhang, Qi Zhen, Zhenyu Li, Xiao Han, Puhua Chen, Xu Tang, Licheng Jiao
Summary: In this study, a spectral-spatial distribution consistent (SSDC) network based on meta-learning is proposed to address the problem of insufficient labeled samples in hyperspectral images (HSIs). The network achieves data distribution alignment and improves classification accuracy in cross-domain classification tasks through steps such as spectral feature extraction, singular value decomposition, and spatial topological information retrieval.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Remote Sensing
Baokai Zu, Hongyuan Wang, Jianqiang Li, Ziping He, Yafang Li, Zhixian Yin
Summary: Recently, deep learning techniques have been successfully applied to hyperspectral image classification, particularly using convolutional neural network (CNN)-based models. However, CNN models perform poorly on hyperspectral data due to its sequential nature. To address this, we propose a Weighted Residual Self-attention Graph-based Transformer (RSAGformer) model that effectively solves the network degradation problem. Experimental results on six public hyperspectral datasets demonstrate that the RSAGformer achieves competitive classification performance.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Lei Mou, Yitian Zhao, Huazhu Fu, Yonghuai Liu, Jun Cheng, Yalin Zheng, Pan Su, Jianlong Yang, Li Chen, Alejandro F. Frangi, Masahiro Akiba, Jiang Liu
Summary: This paper proposes a convolutional neural network for the segmentation of curvilinear structures in medical images, utilizing self-attention mechanism to learn hierarchical representations and attention modules to enhance feature extraction. Experimental results demonstrate the superiority of the proposed method across multiple datasets.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuhui Ma, Huaying Hao, Jianyang Xie, Huazhu Fu, Jiong Zhang, Jianlong Yang, Zhen Wang, Jiang Liu, Yalin Zheng, Yitian Zhao
Summary: In this study, a new dataset ROSE for retinal vessel OCTA images was constructed, and a novel vessel segmentation network OCTA-Net was proposed with superior performance. Experimental results demonstrated potential advantages in studying neurodegenerative diseases through fractal dimension analysis.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2021)
Article
Health Care Sciences & Services
Andreas Maunz, Fethallah Benmansour, Yvonna Li, Thomas Albrecht, Yan-Ping Zhang, Filippo Arcadu, Yalin Zheng, Savita Madhusudhan, Jayashree Sahni
Summary: The study evaluated the performance of a machine-learning algorithm in detecting and classifying CNV related to AMD on SD-OCT images, showing that the ML model can accurately detect CNV presence and subtypes in patients.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Ethics
Frank G. Preston, Yanda Meng, Yalin Zheng, James Hsuan, Kevin J. Hamill, Austin G. McCormick
Summary: This study determined the effectiveness of three deidentification methods and found the most effective option. These findings provide valuable information for informed consent discussions.
JOURNAL OF EMPIRICAL RESEARCH ON HUMAN RESEARCH ETHICS
(2022)
Article
Computer Science, Interdisciplinary Applications
Yanda Meng, Hongrun Zhang, Yitian Zhao, Xiaoyun Yang, Yihong Qiao, Ian J. C. MacCormick, Xiaowei Huang, Yalin Zheng
Summary: This study introduces a novel deep learning framework based on graph neural networks, with multiple graph reasoning modules to explicitly incorporate region and boundary features, along with iterative message aggregation and node update mechanism. By utilizing multi-level feature node embeddings in different parallel graph reasoning modules, the model can concurrently address region and boundary feature reasoning and aggregation at various feature levels.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Environmental Sciences
Mohd Hanafiah Ahmad Hijazi, Mohammad Saffree Jeffree, Nicholas Tze Ping Pang, Syed Sharizman Syed Abdul Rahim, Azizan Omar, Fatimah Ahmedy, Mohd Hanafi Ahmad Hijazi, Mohd Rohaizat Hassan, Rozita Hod, Azmawati Mohammed Nawi, Sylvia Daim, Walton Wider
Summary: This study aimed to determine the seroprevalence of COVID-19 and the prevalence of psychological distress, and to explore factors that may contribute to the development of psychological distress. The results showed a COVID-19 seroprevalence of 8.3%, with non-healthcare workers having a higher prevalence. The prevalence of depression, anxiety, and stress among front liners was low. Younger people and healthcare workers had a higher prevalence of psychological distress, with dysfunctional coping and psychological inflexibility being identified as predictors.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Article
Cardiac & Cardiovascular Systems
Joshua Bridge, Lu Fu, Weidong Lin, Yumei Xue, Gregory Y. H. Lip, Yalin Zheng
Summary: A rapid, inexpensive, and accurate means to detect abnormal ECGs using artificial intelligence (AI) has been developed. The use of AI enables mass automated review of ECGs in community settings, flagging abnormal ones for detailed clinical review by healthcare professionals.
JOURNAL OF ARRHYTHMIA
(2022)
Editorial Material
Cardiac & Cardiovascular Systems
Emily Shipley, Martha Joddrell, Gregory Y. H. Lip, Yalin Zheng
ARRHYTHMIA & ELECTROPHYSIOLOGY REVIEW
(2022)
Article
Computer Science, Interdisciplinary Applications
Lei Mou, Hong Qi, Yonghuai Liu, Yalin Zheng, Peter Matthew, Pan Su, Jiang Liu, Jiong Zhang, Yitian Zhao
Summary: This paper proposes a fully automated deep learning method for grading the tortuosity of corneal nerves. The method surpasses existing methods in accuracy and can be applied in clinical decision-making.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Information Systems
T. Nanthakumaran Thulasy, Puteri N. E. Nohuddin, Istas Fahrurrazi Nusyirwan, Mohd Hanafi Ahmad Hijazi, Musaddak Maher Abdul Zahra
Summary: 3D scanning technology plays a crucial role in aerospace maintenance, and the Royal Malaysian Air Force conducted a study on using 3D scanning in Su-30MKM maintenance. The study describes the process of scanning the aircraft and proposes a 3D Scanning Maintenance System to accelerate reverse engineering and aircraft maintenance operations.
Article
Physics, Applied
Nigel D. Browning, Jony Castagna, Angus I. Kirkland, Amirafshar Moshtaghpour, Daniel Nicholls, Alex W. Robinson, Jack Wells, Yalin Zheng
Summary: Images and spectra obtained from aberration corrected STEM are widely used for quantitative analysis of nanostructures and materials/biological systems. However, achieving atomic resolution observations with these capabilities is challenging due to potential electron beam modification during image acquisition, especially for in situ observations. This paper describes a methodology of sub-sampling and Inpainting to efficiently use the dose and minimize beam effects, as well as discusses the potential of Inpainting for real-time dynamic experiments.
APPLIED PHYSICS LETTERS
(2023)
Article
Ophthalmology
Jianyang Xie, Quanyong Yi, Yufei Wu, Yalin Zheng, Yonghuai Liu, Antonella Macerollo, Huazhu Fu, Yanwu Xu, Jiong Zhang, Ardhendu Behera, Chenlei Fan, Alejandro F. Frangi, Jiang Liu, Qinkang Lu, Hong Qi, Yitian Zhao
Summary: This study developed a standardized OCTA analysis framework for retinal microvascular assessment and compared the parameters extracted from OCTA images between controls, Alzheimer’s Disease (AD), and mild cognitive impairment (MCI) groups. The results showed significant reductions in vessel area, length densities, and bifurcation numbers in AD group compared to controls. The MCI group demonstrated decreases in vascular parameters, fractal dimension, and bifurcation numbers in both superficial and inner vascular complexes, as well as increased vascular tortuosity and roundness of foveal avascular zone (FAZ). The study suggests that OCTA can be a useful tool for the diagnosis of AD and MCI.
BRITISH JOURNAL OF OPHTHALMOLOGY
(2023)
Article
Computer Science, Interdisciplinary Applications
Yanda Meng, Hongrun Zhang, Yitian Zhao, Dongxu Gao, Barbra Hamill, Godhuli Patri, Tunde Peto, Savita Madhusudhan, Yalin Zheng
Summary: Glaucoma is a progressive eye disease that leads to permanent vision loss. The vertical cup to disc ratio (vCDR) in color fundus images is crucial for glaucoma screening and assessment. We propose a weakly and semi-supervised graph-based network that utilizes geometric associations and domain knowledge to improve the segmentation and vCDR estimation.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Engineering, Civil
Yanda Meng, Joshua Bridge, Yitian Zhao, Martha Joddrell, Yihong Qiao, Xiaoyun Yang, Xiaowei Huang, Yalin Zheng
Summary: This paper proposes an adaptive auxiliary task learning-based approach for transport object counting problems. The approach combines a standard Convolution Neural Network (CNN) and a Graph Convolution Network (GCN) for feature extraction and reasoning, and fuses features across different task branches of the adaptive CNN backbone. Experimental results show superior performance compared to state-of-the-art counting methods. The code is publicly available.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Interdisciplinary Applications
Shuaib K. Memon, Kashif Nisar, Mohd Hanafi Ahmad Hijazi, B. S. Chowdhry, Ali Hassan Sodhro, Sandeep Pirbhulal, Joel J. P. C. Rodrigues
Summary: IEEE 802.11 WLAN is widely deployed around the world for real-time multimedia applications and emergency services. Time-sensitive applications and emergency traffic require strict requirements for packet delays, jitter, and losses. Providing a strict QoS guarantee and supporting emergency traffic under high loads in WLANs is a challenging task that requires further research.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2021)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)
