Results 61 to 70 of about 1,367 (116)

Spontaneous metastasis xenograft models link CD44 isoform 4 to angiogenesis, hypoxia, EMT and mitochondria‐related pathways in colorectal cancer

Molecular Oncology, Volume 18, Issue 1, Page 62-90, January 2024.
Pan‐CD44 knockdown decreases spontaneous metastasis in human colorectal cancer xenograft models. Concurrent intratumoral gene expression alterations significantly correlate with genes differentially regulated among CD44 isoform 4 (but not isoform 3) high vs. low patients (TCGA).
Arun Everest‐Dass, Stepan Nersisyan, Hanna Maar, Victor Novosad, Jennifer Schröder‐Schwarz, Vera Freytag, Johanna L. Stuke, Mia C. Beine, Alina Schiecke, Marie‐Therese Haider, Malte Kriegs, Omar Elakad, Hanibal Bohnenberger, Lena‐Christin Conradi, Maria Raygorodskaya, Linda Krause, Mark von Itzstein, Alexander Tonevitsky, Udo Schumacher, Diana Maltseva, Daniel Wicklein, Tobias Lange   +21 more
wiley   +1 more source

Review of book-Ultrasound in Otorhinolaryngology [PDF]

Ultrasonic therapy for certain diseases is discussed.
Soldatov, I. V.
core   +1 more source

Revisiting the Message Passing in Heterophilous Graph Neural Networks

CoRR
Graph Neural Networks (GNNs) have demonstrated strong performance in graph mining tasks due to their message-passing mechanism, which is aligned with the homophily assumption that adjacent nodes exhibit similar behaviors. However, in many real-world graphs, connected nodes may display contrasting behaviors, termed as heterophilous patterns, which has ...
Zhuonan Zheng, Yuanchen Bei, Sheng Zhou 0004, Yao Ma 0001, Ming Gu 0014, Hongjia Xu, Chengyu Lai, Jiawei Chen 0007, Jiajun Bu   +8 more
openaire   +2 more sources

Exploring the Potential of Large Language Models for Heterophilic Graphs

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we can more effectively interpret and utilize textual data to better characterize heterophilic graphs, where neighboring nodes often have
Yuxia Wu, Shujie Li 0003, Yuan Fang 0001, Chuan Shi 0001   +3 more
openaire   +2 more sources

Graph Neural Convection-Diffusion with Heterophily

, 2023
Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.
Kang, Qiyu, She, Rui, Song, Yang, Tay, Wee Peng, Wang, Sijie, Zhao, Kai   +5 more
core  

Representation Learning on Heterophilic Graph with Directional Neighborhood Attention

CoRR
Graph Attention Network (GAT) is one of the most popular Graph Neural Network (GNN) architecture, which employs the attention mechanism to learn edge weights and has demonstrated promising performance in various applications. However, since it only incorporates information from immediate neighborhood, it lacks the ability to capture long-range and ...
Qincheng Lu, Jiaqi Zhu, Sitao Luan, Xiao-Wen Chang   +3 more
openaire   +2 more sources

HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs

CoRR
Graph neural networks (GNNs) have demonstrated success in modeling relational data primarily under the assumption of homophily. However, many real-world graphs exhibit heterophily, where linked nodes belong to different categories or possess diverse attributes.
Shujie Li 0003, Yuxia Wu, Chuan Shi 0001, Yuan Fang 0001   +3 more
openaire   +2 more sources

Power in the Heterogeneous Connections Model: The Emergence of Core-Periphery Networks [PDF]

The heterogeneous connections model is a generalization of the homogeneous connections model of Jackson and Wolinsky (1996) in which the intrinsic value of each connection is set by a discrete, positive and symmetric function that depends solely on the ...
Dotan Persitz
core  

Exploring Adaptive Structure Learning for Heterophilic Graphs

CoRR
Graph Convolutional Networks (GCNs) gained traction for graph representation learning, with recent attention on improving performance on heterophilic graphs for various real-world applications. The localized feature aggregation in a typical message-passing paradigm hinders the capturing of long-range dependencies between non-local nodes of the same ...
openaire   +2 more sources

Contrastive Learning for Non-Local Graphs with Multi-Resolution Structural Views

, 2023
Learning node-level representations of heterophilic graphs is crucial for various applications, including fraudster detection and protein function prediction.
Khan, Asif, Storkey, Amos
core