All news

4 articles

Min score

paperIEEE Xplore·1 Nov 20263.6
ESR-HGNN: Eliminating Semantic Redundancy for Efficient Mini-Batch HGNN Inference
ESR-HGNN removes redundant semantic computation to speed up mini-batch heterogeneous GNN inference.
ml-inference graph-neural-networks
blogHugging Face Blog·22 Oct 20263.4
NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
NVIDIA Kumo Relational is a pretrained relational foundation model that predicts churn or fraud directly from database tables with no training.
data-engineering graph-neural-networks
paperACM Digital Library·20 Oct 20263.4
GraphLLM4CTR: Large Language Model-enhanced Graph Neural Networks for Click-through Rate Prediction in Recommender Systems
LLM-enhanced GNNs for CTR prediction.
recommender-systems graph-neural-networks
paperarXiv (systems, data, ML)·23 Oct 20263.3
On the Token Collapse Phenomenon in Textual Graph Soft Prompting
Finds token collapse in graph soft prompting for LLMs.
graph-neural-networks