Simplifying and empowering transformers for large-graph representations
Learning representations on large-sized graphs is a long-standing challenge due to the inter-
dependence nature involved in massive data points. Transformers, as an emerging class of …
dependence nature involved in massive data points. Transformers, as an emerging class of …
Graph neural networks are inherently good generalizers: Insights by bridging gnns and mlps
Graph neural networks (GNNs), as the de-facto model class for representation learning on
graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional …
graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional …
Kagnns: Kolmogorov-arnold networks meet graph learning
In recent years, Graph Neural Networks (GNNs) have become the de facto tool for learning
node and graph representations. Most GNNs typically consist of a sequence of …
node and graph representations. Most GNNs typically consist of a sequence of …
Lignn: Graph neural networks at linkedin
F Borisyuk, S He, Y Ouyang, M Ramezani… - Proceedings of the 30th …, 2024 - dl.acm.org
In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs)
Framework. We share our insight on developing and deployment of GNNs at large scale at …
Framework. We share our insight on developing and deployment of GNNs at large scale at …
Coslight: Co-optimizing collaborator selection and decision-making to enhance traffic signal control
Effective multi-intersection collaboration is pivotal for reinforcement-learning-based traffic
signal control to alleviate congestion. Existing work mainly chooses neighboring …
signal control to alleviate congestion. Existing work mainly chooses neighboring …
Decoupled graph knowledge distillation: A general logits-based method for learning mlps on graphs
Y Tian, S Xu, M Li - Neural Networks, 2024 - Elsevier
Abstract While Graph Neural Networks (GNNs) have demonstrated their effectiveness in
processing non-Euclidean structured data, the neighborhood fetching of GNNs is time …
processing non-Euclidean structured data, the neighborhood fetching of GNNs is time …
Editable graph neural network for node classifications
Despite Graph Neural Networks (GNNs) have achieved prominent success in many graph-
based learning problem, such as credit risk assessment in financial networks and fake news …
based learning problem, such as credit risk assessment in financial networks and fake news …
Carl-g: Clustering-accelerated representation learning on graphs
Self-supervised learning on graphs has made large strides in achieving great performance
in various downstream tasks. However, many state-of-the-art methods suffer from a number …
in various downstream tasks. However, many state-of-the-art methods suffer from a number …
Node duplication improves cold-start link prediction
Graph Neural Networks (GNNs) are prominent in graph machine learning and have shown
state-of-the-art performance in Link Prediction (LP) tasks. Nonetheless, recent studies show …
state-of-the-art performance in Link Prediction (LP) tasks. Nonetheless, recent studies show …
On the initialization of graph neural networks
Abstract Graph Neural Networks (GNNs) have displayed considerable promise in graph
representation learning across various applications. The core learning process requires the …
representation learning across various applications. The core learning process requires the …