Graph neural networks (GNN) are specialized artificial neural networks that are designed for tasks whose inputs are graphs. [1] [2] [3] [4] [5] One prominent example is molecular drug design. [6] …

We introduce a backtracking search algorithm over a set of relaxed graph substitutions to find optimized networks and use a flow-based graph split algorithm to recursively split a …

Sep 2, 2021 · A GNN is an optimizable transformation on all attributes of the graph (nodes, edges, global-context) that preserves graph symmetries (permutation invariances).

Mar 4, 2025 · Graph Neural Networks (GNNs) are a class of neural networks designed specifically to work with graph-structured data. They’re used to learn patterns and relationships between …

Aug 21, 2024 · Graph neural networks (GNNs) are a class of deep learning models that operate on graph-structured data. As graphs are ubiquitous in the real world, representing …

s paper introduces a systematic approach for effectively scheduling DNN computational graphs on DSA platforms. By fully taking into account hardware architecture when parti-tioning a …

Jan 3, 2023 · We present oneDNN Graph Compiler, a tensor compiler that employs a hybrid approach of using techniques from both compiler optimization and expert-tuned kernels for …

Jun 24, 2024 · In addition, we develop GraphPipe, a distributed system that exploits GPP strategies to enable performant and scalable DNN training. GraphPipe partitions a DNN into a …

May 23, 2023 · Graph Neural Networks (GNNs) are an emerging research field. This specialized Deep Neural Network (DNN) architecture is capable of processing graph structured data and …

In this work, we formally de-ne the Optimizing Computation Graph using Graph Sub-stitutions (OCGGS) problem, and prove it to be NP-hard and Poly-APX-complete. We develop two exact …