Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL may complement …
Graph neural networks (GNNs) are a powerful architecture for tackling graph learning tasks, yet have been shown to be oblivious to eminent substructures such as cycles. We present …
Graph Neural Networks (GNNs) are proven to be a powerful machinery for learning complex dependencies in multivariate spatio-temporal processes. However, most existing GNNs …
Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in …
Z Yan, T Ma, L Gao, Z Tang… - … conference on machine …, 2021 - proceedings.mlr.press
Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our …
S Zheng, Y Zhang, H Wagner… - Advances in Neural …, 2021 - proceedings.neurips.cc
Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through …
Y Chen, Y Gel, HV Poor - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Graph neural networks (GNNs) offer a new powerful alternative for multivariate time series forecasting, demonstrating remarkable success in a variety of spatio-temporal applications …
S Zeng, F Graf, C Hofer, R Kwitt - Advances in neural …, 2021 - proceedings.neurips.cc
The problem of (point) forecasting univariate time series is considered. Most approaches, ranging from traditional statistical methods to recent learning-based techniques with neural …
In computer-aided drug discovery (CADD), virtual screening (VS) is used for comparing a library of compounds against known active ligands to identify the drug candidates that are …