Abstract: Graph Convolution Networks (GCNs) have achieved remarkable success in representation of structured graph data. As we know that traditional GCNs are generally defined on the fixed first-order ...

Abstract: In this paper, we present a novel convolution theorem which encompasses the well known convolution theorem in (graph) signal processing as well as the one related to time-varying filters.

This year, for the first time since 2015, I’m not doing a “best graphic novels of the year” list. There are too many great works out there to read, too many ways to evaluate how they are “best,” and ...

KernelOptimizer is an open-source tool that automates CUDA kernel optimization for PyTorch workloads using large language models (LLMs). Inspired by Stanford CRFM’s fast kernel research, it leverages ...

Install Pytorch 1.8.1 (Note that the results reported in the paper are obtained by running the code on this Pytorch version. As raised by the issue, using higher version of Pytorch may seem to have a ...