14,130 Hits in 6.8 sec

Graph Self-Supervised Learning: A Survey [article]

Yixin Liu, Ming Jin, Shirui Pan, Chuan Zhou, Yu Zheng, Feng Xia, Philip S. Yu
2022 arXiv   pre-print
Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data.  ...  We construct a unified framework that mathematically formalizes the paradigm of graph SSL.  ...  Hybrid augmentations It is worth noting that a given graph augmentation may involve not only the attributive but also the topological augmentations simultaneously, where we define it as the hybrid augmentation  ... 
arXiv:2103.00111v4 fatcat:y3zfg4ennnbnhhvmujd5rvltty


Anna Shvets, Samer Darkazanli, Tiffon Vincent, Bell Jonathan, de Paiva Santana Charles
2022 Zenodo  
The article proposes a perspective on the use of generative artificial models in a context of the VR project "Graphs in harmony learning".  ...  The efficiency of the novel data encoding scheme, along with the design patterns based on the system of graphs, are shown.  ...  The representation methodology has been proven efficient in a multi-step pedagogical experiment in a context of hybrid learning.  ... 
doi:10.5281/zenodo.6668965 fatcat:vgz64v3cdze27ktvrwelvnpwt4

A Distributed Multi-GPU System for Large-Scale Node Embedding at Tencent [article]

Wanjing Wei, Yangzihao Wang, Pin Gao, Shijie Sun, Donghai Yu
2021 arXiv   pre-print
Comparing with the current state-of-the-art multi-GPU single-node embedding system, our system achieves 5.9x-14.4x speedup on average with competitive or better accuracy on open datasets.  ...  Scaling node embedding systems to efficiently support these applications remains a challenging problem. In this paper we present a high-performance multi-GPU node embedding system.  ...  We also thank Stanley Tzeng for his proofreading of the manuscript.  ... 
arXiv:2005.13789v3 fatcat:e7c7u6zpmzf23hjk6jjny2bora

A review of machine learning approaches, challenges and prospects for computational tumor pathology [article]

Liangrui Pan, Zhichao Feng, Shaoliang Peng
2022 arXiv   pre-print
better-integrated solutions for whole-slide images, multi-omics data, and clinical informatics.  ...  Finally, the challenges and prospects of machine learning in computational pathology applications are discussed.  ...  (e.g., DenseNet-121, ICIAR 2018(400 Breast H&E Classification ResNet-50, multi-level InceptionV3, and multi-level VGG-16), dual- [110] images) network orthogonal low-rank learning (DOLL) CNN、LSTM, CNN  ... 
arXiv:2206.01728v1 fatcat:g7r7fsw2bzafpkkyg6hpzjyt5e

Graph Augmentation Learning [article]

Shuo Yu, Huafei Huang, Minh N. Dao, Feng Xia
2022 arXiv   pre-print
The aggregation mechanism of augmentation strategies and graph learning models are also discussed by different application scenarios, i.e., data-specific, model-specific, and hybrid scenarios.  ...  Graph Augmentation Learning (GAL) provides outstanding solutions for graph learning in handling incomplete data, noise data, etc.  ...  1 : An overall framework for GAL.  ... 
arXiv:2203.09020v1 fatcat:72esohvrxbdzdlnahaa27pftqm

2021 Index IEEE Transactions on Parallel and Distributed Systems Vol. 32

2022 IEEE Transactions on Parallel and Distributed Systems  
., +, TPDS Jan. 2021 147-159 The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs With Hybrid Parallelism.  ...  Li, X., +, TPDS July 2021 1690- 1701 The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs With Hybrid Parallelism.  ...  Graph coloring Feluca: A Two-Stage Graph Coloring Algorithm With Color-Centric Paradigm on GPU. Zheng, Z., +,  ... 
doi:10.1109/tpds.2021.3107121 fatcat:e7bh2xssazdrjcpgn64mqh4hb4

Table of Contents

2018 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA)  
Level Fusion of Otsu Segmentation Augmented with Thepade's N-ary Sorted Block Truncation Coding 197 Face Gender Recognition using Multi Layer Perceptron with OTSU Segmentation 198 Global Windowing  ...  Patterns of Social Media Users 92 Application of Artificial Bee Colony Method For Unit Commitment 93 Adaptive and Automated Assessment System to decide the difficulty level of Questions 94 Exploration  ... 
doi:10.1109/iccubea.2018.8697655 fatcat:jvjgmcrh3fhxtkf4kyydawnkiq

Recent Advances in Heterogeneous Relation Learning for Recommendation [article]

Chao Huang
2021 arXiv   pre-print
We discuss the learning approaches in each category, such as matrix factorization, attention mechanism and graph neural networks, for effectively distilling heterogeneous contextual information.  ...  Finally, we present an exploratory outlook to highlight several promising directions and opportunities in heterogeneous relational learning frameworks for recommendation.  ...  Hybrid Learning Methods.  ... 
arXiv:2110.03455v1 fatcat:fskj4qdsibfnxefklazdli3tgu

Neural Graph Matching for Pre-training Graph Neural Networks [article]

Yupeng Hou, Binbin Hu, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou, Ji-Rong Wen
2022 arXiv   pre-print
In this way, we can learn adaptive representations for a given graph when paired with different graphs, and both node- and graph-level characteristics are naturally considered in a single pre-training  ...  Extensive experiments on multi-domain, out-of-distribution benchmarks have demonstrated the effectiveness of our approach. The code is available at:  ...  Xin Zhao is the corresponding author.  ... 
arXiv:2203.01597v1 fatcat:fq6zrtbbcvdd5dgcxp2cgwgazy

Hybrid intelligent framework for automated medical learning

Asma Belhadi, Youcef Djenouri, Vicente Garcia Diaz, Essam H. Houssein, Jerry Chun‐Wei Lin
2021 Expert systems  
Multi agents system is proposed by using distributed deep learning, and knowledge graph for learning medical data.  ...  This paper investigates the automated medical learning and proposes hybrid intelligent framework, called Hybrid Automated Medical Learning (HAML).  ...  We present a new framework, called Hybrid Automated Medical Learning (HAML), which adopts distributed deep learning, multi agents systems, and knowledge graph for automated medical learning.  ... 
doi:10.1111/exsy.12737 fatcat:alshb2hrejak3nhpcqgtbxyphq

Deep Convolutional Neural Networks For Environmental Sound Classification

2022 International Journal for Research in Applied Science and Engineering Technology  
We perform Data Augmentation techniques to extract best features from the given audio to classify which class of sound.  ...  Our deep convolutional neural network architecture uses stacked convolutional and pooling layers to extract highlevel feature representations from spectrogram-like features from the given input.  ...  reliable decibel levels at the type/class 2 level.  ... 
doi:10.22214/ijraset.2022.45778 fatcat:46wwpkuslba3rhvhfdjjmjchxa

2020-2021 Index IEEE Transactions on Computers Vol. 70

2021 IEEE transactions on computers  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  Note that the item title is found only under the primary entry in the Author Index.  ...  ., +, TC Sept. 2021 1427-1442 MulTa-HDC: A Multi-Task Learning Framework For Hyperdimensional Computing.  ... 
doi:10.1109/tc.2021.3134810 fatcat:p5otlsapynbwvjmqogj47kv5qa

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Sanskrit Dependency Parsing [article]

Jivnesh Sandhan, Laxmidhar Behera, Pawan Goyal
2022 arXiv   pre-print
We experiment with five strategies, namely, data augmentation, sequential transfer learning, cross-lingual/mono-lingual pretraining, multi-task learning and self-training.  ...  Existing state of the art approaches for Sanskrit Dependency Parsing (SDP), are hybrid in nature, and rely on a lexicon-driven shallow parser for linguistically motivated feature engineering.  ...  ACKNOWLEDGMENTS We thank Amba Kulkarni for providing Sanskrit dependency treebank data, Anupama Ryali for Sisupālavadha dataset and the anonymous reviewers for their constructive feedback towards improving  ... 
arXiv:2201.11374v1 fatcat:m5qe6q6cnzeqbjovb2ag237ssy

2020 Index IEEE Transactions on Knowledge and Data Engineering Vol. 32

2021 IEEE Transactions on Knowledge and Data Engineering  
Hybrid E-Learning Recommendation Approach Based on Learners' Influence Propagation. Wan, S., +, TKDE May 2020 827-840 Semi-Supervised Learning with Auto-Weighting Feature and Adaptive Graph.  ...  Computer aided instruction A Hybrid E-Learning Recommendation Approach Based on Learners' Influence Propagation.  ... 
doi:10.1109/tkde.2020.3038549 fatcat:75f5fmdrpjcwrasjylewyivtmu

Geometry Contrastive Learning on Heterogeneous Graphs [article]

Shichao Zhu, Chuan Zhou, Anfeng Cheng, Shirui Pan, Shuaiqiang Wang, Dawei Yin, Bin Wang
2022 arXiv   pre-print
Self-supervised learning (especially contrastive learning) methods on heterogeneous graphs can effectively get rid of the dependence on supervisory data.  ...  Meanwhile, most existing representation learning methods embed the heterogeneous graphs into a single geometric space, either Euclidean or hyperbolic.  ...  DGI [50] maximizes MI between node and graph representations for learning a better graph encoder. GRACE proposes a hybrid scheme for generating graph views on both structure and attribute levels.  ... 
arXiv:2206.12547v1 fatcat:dfjnsdw7rfcnrn3mzmvtquof3q
« Previous Showing results 1 — 15 out of 14,130 results