Published inTowards Data ScienceCross-Entropy, Negative Log-Likelihood, and All That JazzTwo closely related mathematical formulations widely used in data science, and notes on their implementations in PyTorchMar 8, 20222Mar 8, 20222
Published inTowards Data ScienceA unified view of Graph Neural NetworksGraph attention, graph convolution, network propagation are all special cases of message passing in graph neural networks.Jun 27, 2021Jun 27, 2021
Published inTowards Data ScienceNetwork Learning — from Network Propagation to Graph ConvolutionTwo different views of network propagation, a popular method in computational biology, and its connection with graph convolutionJun 20, 2021Jun 20, 2021
Published inTowards Data ScienceExplainable Graph Neural NetworksA step forward in explainable AI, and why it is hard to adapt existing explanation methods to GNNsJun 13, 20211Jun 13, 20211
Published inTowards Data ScienceRun node2vec ultrafast with less memory using PecanPyMay 31, 20213May 31, 20213
Published inThe CitadelTowards an Unbiased Development of New Bioinformatics MethodsAdvancements in artificial intelligence and machine learning have led to many new methods in the areas of bioinformatics and computational…May 12, 2021May 12, 2021