Convolutional neural networks on graphs with chebyshev approximation, revisited

M He, Z Wei, JR Wen - Advances in neural information …, 2022 - proceedings.neurips.cc
Designing spectral convolutional networks is a challenging problem in graph learning.
ChebNet, one of the early attempts, approximates the spectral graph convolutions using …

iGRLDTI: an improved graph representation learning method for predicting drug–target interactions over heterogeneous biological information network

BW Zhao, XR Su, PW Hu, YA Huang, ZH You… - …, 2023 - academic.oup.com
Motivation The task of predicting drug–target interactions (DTIs) plays a significant role in
facilitating the development of novel drug discovery. Compared with laboratory-based …

Graph attention multi-layer perceptron

W Zhang, Z Yin, Z Sheng, Y Li, W Ouyang, X Li… - Proceedings of the 28th …, 2022 - dl.acm.org
Graph neural networks (GNNs) have achieved great success in many graph-based
applications. However, the enormous size and high sparsity level of graphs hinder their …

Graph neural networks with learnable and optimal polynomial bases

Y Guo, Z Wei - International Conference on Machine …, 2023 - proceedings.mlr.press
Polynomial filters, a kind of Graph Neural Networks, typically use a predetermined
polynomial basis and learn the coefficients from the training data. It has been observed that …

A review of graph neural networks and pretrained language models for knowledge graph reasoning

J Ma, B Liu, K Li, C Li, F Zhang, X Luo, Y Qiao - Neurocomputing, 2024 - Elsevier
Abstract Knowledge Graph (KG) stores human knowledge facts in an intuitive graphical
structure but faces challenges such as incomplete construction or inability to handle new …

Pasca: A graph neural architecture search system under the scalable paradigm

W Zhang, Y Shen, Z Lin, Y Li, X Li, W Ouyang… - Proceedings of the …, 2022 - dl.acm.org
Graph neural networks (GNNs) have achieved state-of-the-art performance in various graph-
based tasks. However, as mainstream GNNs are designed based on the neural message …

Model degradation hinders deep graph neural networks

W Zhang, Z Sheng, Z Yin, Y Jiang, Y **a… - Proceedings of the 28th …, 2022 - dl.acm.org
Graph Neural Networks (GNNs) have achieved great success in various graph mining tasks.
However, drastic performance degradation is always observed when a GNN is stacked with …

A geometric deep learning framework for drug repositioning over heterogeneous information networks

BW Zhao, XR Su, PW Hu, YP Ma… - Briefings in …, 2022 - academic.oup.com
Drug repositioning (DR) is a promising strategy to discover new indicators of approved
drugs with artificial intelligence techniques, thus improving traditional drug discovery and …

Regulation-aware graph learning for drug repositioning over heterogeneous biological network

BW Zhao, XR Su, Y Yang, DX Li, GD Li, PW Hu… - Information …, 2025 - Elsevier
Drug repositioning (DR) is crucial for identifying new disease indications for existing drugs
and enhancing their clinical utility. Despite the effectiveness of various artificial intelligence …

Node-wise diffusion for scalable graph learning

K Huang, J Tang, J Liu, R Yang, X **ao - Proceedings of the ACM Web …, 2023 - dl.acm.org
Graph Neural Networks (GNNs) have shown superior performance for semi-supervised
learning of numerous web applications, such as classification on web services and pages …