Results 101 to 110 of about 649,217 (300)
Towards Inference of Original Graph Data Information from Graph Embeddings
, 2023 This paper studies to what extent an adversary (without the original graph data) can recover the original raw graph data from graph embeddings. To quantify the original graph data information leakage from graph embeddings, we develop a deep neural ...
Hu, Yiwen +4 more
core +1 more source
Molecular Oncology, EarlyView.Tumour heterogeneity and clonal evolution of metastatic salivary gland cancer were evaluated in two patients with adenoid carcinoma and one patient with myoepithelial carcinoma. Radiology‐guided autopsy enabled multi‐region sampling (total samples n = 149), followed by whole‐genome sequencing and phylogenetic reconstruction (17 tumour samples, 4–7 per ...
Gerben Lassche +10 more
wiley +1 more source
Accurate graph classification via two-staged contrastive curriculum learning.
PLoS ONEGiven a graph dataset, how can we generate meaningful graph representations that maximize classification accuracy? Learning representative graph embeddings is important for solving various real-world graph-based tasks.
Sooyeon Shim +3 more
doaj +1 more source
Frontiers in PhysiologyIntroductionAccurate classification of colonoscopic images is essential for early detection and characterization of colorectal diseases. Recent advances in deep learning, particularly transformer-based architectures and graph neural networks (GNNs ...
Chaohui Zhen +7 more
doaj +1 more source
Molecular Oncology, EarlyView.Arginine methylation can be viewed as a persistence‐prone post‐translational modification regulated by a network of PRMTs. Competitive and compensatory interactions among PRMTs can redistribute methylation across substrate pools shaped by sequence, structural, spatial, and environmental layers, reinforcing RNA‐processing, chromatin, and signaling ...
So Hyun Kwon, Ji Min Lee
wiley +1 more source
CoRR, 2019 Graph embedding is a popular algorithmic approach for creating vector representations for individual vertices in networks. Training these algorithms at scale is important for creating embeddings that can be used for classification, ranking, recommendation and other common applications in industry.
C. Bayan Bruss +5 more
openaire +3 more sources
Ensemble graph auto-encoders for clustering and link prediction [PDF]
PeerJ Computer ScienceGraph auto-encoders are a crucial research area within graph neural networks, commonly employed for generating graph embeddings while minimizing errors in unsupervised learning.
Chengxin Xie +5 more
doaj +2 more sources
Bernoulli Embeddings for Graphs
Proceedings of the AAAI Conference on Artificial Intelligence, 2018 Just as semantic hashing can accelerate information retrieval, binary valued embeddings can significantly reduce latency in the retrieval of graphical data. We introduce a simple but effective model for learning such binary vectors for nodes in a graph.
Vinith Misra, Sumit Bhatia
openaire +2 more sources
Molecular Oncology, EarlyView.High‐risk bladder cancer is typically treated with Bacillus Calmette‐Guérin (BCG), but 30–40% of patients relapse. No FDA‐ or CE‐approved biomarkers currently predict or prognosticate BCG failure. We systematically reviewed the literature and identified 72 eligible studies, revealing several promising biomarkers associated with BCG treatment response ...
Rui Ribeiro‐Pereira +7 more
wiley +1 more source
Evaluating the involvement of autolysosomes in the nuclear translocation of fluorescent proteins
FEBS Open Bio, EarlyView.Endogenously expressed fluorescent proteins can be degraded by autophagy and transported to cell nuclei via the nuclear pore complex. But in some cell lines, for example, HeLa cells which are positive for immunoreactivity of a receptor ligand, such as UCN I, in cell nuclei, fusion of autolysosome with the nuclear envelope is involved in the nuclear ...
Keiichi Ikeda
wiley +1 more source