Results 31 to 40 of about 78,912 (260)
A review on graph-based semi-supervised learning methods for hyperspectral image classification
Egyptian Journal of Remote Sensing and Space Sciences, 2020 In this article, a comprehensive review of the state-of-art graph-based learning methods for classification of the hyperspectral images (HSI) is provided, including a spectral information based graph semi-supervised classification and a spectral-spatial ...
Shrutika S. Sawant, Manoharan Prabukumar
doaj +1 more source
Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level [PDF]
Jisuanji kexue, 2022 Knowledge representation of scientific paper data is a problem to be solved,and how to learn the representation of paper nodes in scientific paper heterogeneous network is the core to solve this problem.This paper proposes an unsupervised cluster-level ...
SONG Jie, LIANG Mei-yu, XUE Zhe, DU Jun-ping, KOU Fei-fei
doaj +1 more source
Temporal network embedding framework with causal anonymous walks representations [PDF]
PeerJ Computer Science, 2022 Many tasks in graph machine learning, such as link prediction and node classification, are typically solved using representation learning. Each node or edge in the network is encoded via an embedding.
Ilya Makarov +7 more
doaj +2 more sources
Inductive Representation Learning on Temporal Graphs
CoRR, 2020 Inductive representation learning on temporal graphs is an important step toward salable machine learning on real-world dynamic networks. The evolving nature of temporal dynamic graphs requires handling new nodes as well as capturing temporal patterns. The node embeddings, which are now functions of time, should represent both the static node features ...
Da Xu +4 more
openaire +3 more sources
Knowledge Management & E-Learning: An International JournalSound waves are one of the important topics studied in physics. However, students’ graph representation is still low, leading to their low concept understanding of physics learning.
Pramudya Wahyu Pradana, Supahar
doaj +1 more source
CAAI Transactions on Intelligence Technology, 2023 Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently. However, there are still two challenges.
Beibei Han +3 more
doaj +1 more source
Structure-Preserving Graph Representation Learning
2022 IEEE International Conference on Data Mining (ICDM), 2022 Accepted by the IEEE International Conference on Data Mining (ICDM) 2022.
Ruiyi Fang +3 more
openaire +2 more sources
Graph-Based Text Representation and Matching: A Review of the State of the Art and Future Challenges
IEEE Access, 2020 Graph-based text representation is one of the important preprocessing steps in data and text mining, Natural Language Processing (NLP), and information retrieval approaches. The graph-based methods focus on how to represent text documents in the shape of
Ahmed Hamza Osman, Omar Mohammed Barukub
doaj +1 more source
Deep Learning for Learning Graph Representations
, 2019 Mining graph data has become a popular research topic in computer science and has been widely studied in both academia and industry given the increasing amount of network data in the recent years. However, the huge amount of network data has posed great challenges for efficient analysis.
Wenwu Zhu 0001 +2 more
openaire +2 more sources