Duplication of nodes is a common problem encountered when building knowledge graphs (KGs) from heterogeneous datasets, where it is crucial to be able to merge nodes having the same meaning.
This shockingly small sample size (~10) allows for only limited scientific insight into the problem.
While many networks are signed or directed, or both, there is a lack of unified software packages on graph neural networks (GNNs) specially designed for signed and directed networks.
Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning.
1 code implementation • 10 Feb 2022 • Benedek Rozemberczki, Charles Tapley Hoyt, Anna Gogleva, Piotr Grabowski, Klas Karis, Andrej Lamov, Andriy Nikolov, Sebastian Nilsson, Michael Ughetto, Yu Wang, Tyler Derr, Benjamin M Gyori
In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task.
For Artificial Intelligence to have a greater impact in biology and medicine, it is crucial that recommendations are both accurate and transparent.
In recent years, numerous machine learning models which attempt to solve polypharmacy side effect identification, drug-drug interaction prediction and combination therapy design tasks have been proposed.
We propose the molecular omics network (MOOMIN) a multimodal graph neural network used by AstraZeneca oncologists to predict the synergy of drug combinations for cancer treatment.
4 code implementations • 15 Apr 2021 • Benedek Rozemberczki, Paul Scherer, Yixuan He, George Panagopoulos, Alexander Riedel, Maria Astefanoaei, Oliver Kiss, Ferenc Beres, Guzmán López, Nicolas Collignon, Rik Sarkar
We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing.
Recurrent graph convolutional neural networks are highly effective machine learning techniques for spatiotemporal signal processing.
Proximity preserving and structural role-based node embeddings have become a prime workhorse of applied graph mining.
We argue that the Shapley value of models in these games is an effective decision metric for choosing a high performing subset of models from the ensemble.
Additional results from a challenging suite of node classification experiments show how PDNs can learn a wider class of functions than existing baselines.
Private machine learning involves addition of noise while training, resulting in lower accuracy.
In this paper, we describe Little Ball of Fur a Python library that includes more than twenty graph sampling algorithms.
In this paper, we propose a flexible notion of characteristic functions defined on graph vertices to describe the distribution of vertex features at multiple scales.
We present Karate Club a Python framework combining more than 30 state-of-the-art graph mining algorithms which can solve unsupervised machine learning tasks.
A graph embedding is a representation of graph vertices in a low-dimensional space, which approximately preserves properties such as distances between nodes.
We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram.
A graph embedding is a representation of the vertices of a graph in a low dimensional space, which approximately preserves proper-ties such as distances between nodes.
In this paper we propose GEMSEC a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their features.
Ranked #1 on Community Detection on Facebook Athletes
Social and Information Networks