Mlpinit: Embarrassingly simple gnn training acceleration with mlp initialization
Training graph neural networks (GNNs) on large graphs is complex and extremely time
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …
consuming. This is attributed to overheads caused by sparse matrix multiplication, which are …
Submix: Learning to mix graph sampling heuristics
S Abu-El-Haija, JV Dillon, B Fatemi… - Uncertainty in …, 2023 - proceedings.mlr.press
Sampling subgraphs for training Graph Neural Networks (GNNs) is receiving much attention
from the GNN community. While a variety of methods have been proposed, each method …
from the GNN community. While a variety of methods have been proposed, each method …
Asynchronous algorithmic alignment with cocycles
State-of-the-art neural algorithmic reasoners make use of message passing in graph neural
networks (GNNs). But typical GNNs blur the distinction between the definition and invocation …
networks (GNNs). But typical GNNs blur the distinction between the definition and invocation …
Let your graph do the talking: Encoding structured data for llms
How can we best encode structured data into sequential form for use in large language
models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly …
models (LLMs)? In this work, we introduce a parameter-efficient method to explicitly …
A network science perspective of graph convolutional networks: A survey
The mining and exploitation of graph structural information have been the focal points in the
study of complex networks. Traditional structural measures in Network Science focus on the …
study of complex networks. Traditional structural measures in Network Science focus on the …
Ugsl: A unified framework for benchmarking graph structure learning
Graph neural networks (GNNs) demonstrate outstanding performance in a broad range of
applications. While the majority of GNN applications assume that a graph structure is given …
applications. While the majority of GNN applications assume that a graph structure is given …
Zero-shot transfer learning within a heterogeneous graph via knowledge transfer networks
Data continuously emitted from industrial ecosystems such as social or e-commerce
platforms are commonly represented as heterogeneous graphs (HG) composed of multiple …
platforms are commonly represented as heterogeneous graphs (HG) composed of multiple …
Optimizing zx-diagrams with deep reinforcement learning
M Nägele, F Marquardt - arXiv preprint arXiv:2311.18588, 2023 - pure.mpg.de
ZX-diagrams are a powerful graphical language for the description of quantum processes
with applications in fundamental quantum mechanics, quantum circuit optimization, tensor …
with applications in fundamental quantum mechanics, quantum circuit optimization, tensor …
Graph learning indexer: A contributor-friendly and metadata-rich platform for graph learning benchmarks
Establishing open and general benchmarks has been a critical driving force behind the
success of modern machine learning techniques. As machine learning is being applied to …
success of modern machine learning techniques. As machine learning is being applied to …
Edge Graph Intelligence: Reciprocally Empowering Edge Networks with Graph Intelligence
Recent years have witnessed a thriving growth of computing facilities connected at the
network edge, cultivating edge computing networks as a fundamental infrastructure for …
network edge, cultivating edge computing networks as a fundamental infrastructure for …